Evaluating the World Health Organization's SkinNTDs App as a Training Tool for Skin Neglected Tropical Diseases in Ghana and Kenya: Cross-Sectional Study

BACKGROUND

Neglected tropical diseases (NTDs) affect over 1.5 billion people worldwide, primarily impoverished populations in low- and middle-income countries. Skin NTDs, a significant subgroup, manifest primarily as skin lesions and require extensive diagnosis and treatment resources, including trained personnel and financial backing. The World Health Organization has introduced the SkinNTDs app, a mobile health tool designed to train and be used as a decision support tool for frontline health care workers. As most digital health guidelines prioritize the thorough evaluation of mobile health interventions, it is essential to conduct a rigorous and validated assessment of this app.

OBJECTIVE

This study aims to assess the usability and user experience of World Health Organization SkinNTDs app (version 3) as a capacity-building tool and decision-support tool for frontline health care workers.

METHODS

A cross-sectional study was conducted in Ghana and Kenya. Frontline health care workers dealing with skin NTDs were recruited through snowball sampling. They used the SkinNTDs app for at least 5 days before completing a web-based survey containing demographic variables and the user version of the Mobile Application Rating Scale (uMARS), a validated scale for assessing health apps. A smaller group of participants took part in semistructured interviews and one focus group. Quantitative data were analyzed using SPSS with a 95% CI and P≤.05 for statistical significance and qualitative data using ATLAS.ti to identify attributes, cluster themes, and code various dimensions that were explored.

RESULTS

Overall, 60 participants participated in the quantitative phase and 17 in the qualitative phase. The SkinNTDs app scored highly on the uMARS questionnaire, with an app quality mean score of 4.02 (SD 0.47) of 5, a subjective quality score of 3.82 (SD 0.61) of 5, and a perceived impact of 4.47 (SD 0.56) of 5. There was no significant association between the app quality mean score and any of the categorical variables examined, according to Pearson correlation analysis; app quality mean score vs age (P=.37), sex (P=.70), type of health worker (P=.35), country (P=.94), work context (P=.17), frequency of dealing with skin NTDs (P=.09), and dermatology experience (P=.63). Qualitative results echoed the quantitative outcomes, highlighting the ease of use, the offline functionality, and the potential utility for frontline health care workers in remote and resource-constrained settings. Areas for improvement were identified, such as enhancing the signs and symptoms section.

CONCLUSIONS

The SkinNTDs app demonstrates notable usability and user-friendliness. The results indicate that the app could play a crucial role in improving capacity building of frontline health care workers dealing with skin NTDs. It could be improved in the future by including new features such as epidemiological context and direct contact with experts. The possibility of using the app as a diagnostic tool should be considered.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.2196/39393.

Interpersonal sensitivity predicts slower change and less change in anxiety symptoms in cognitive behavioural therapy

OBJECTIVES

Patients in cognitive behavioural therapy (CBT) who are high in interpersonal sensitivity may have difficulty fully engaging in treatment because therapy sessions require intimate interpersonal interactions that are especially uncomfortable for these individuals. The current study tests the hypotheses that patients who are high in interpersonal sensitivity benefit less from CBT for symptoms of depression and anxiety, show a slower rate of change in those symptoms, and are more likely to drop out of treatment.

METHODS

Participants were 832 outpatients who received naturalistic CBT. We assessed interpersonal sensitivity before treatment began and depression and anxiety symptoms at every therapy session. We assessed early, premature, and uncollaborative termination after treatment ended. We constructed multilevel linear regression models and logistic regression models to assess the effects of baseline interpersonal sensitivity on the treatment outcome, the slope of change in depression and anxiety symptoms, and each type of dropout.

RESULTS

Higher baseline interpersonal sensitivity was associated with a slower rate of change and less overall change in anxiety but not depressive symptoms. Baseline interpersonal sensitivity was not a predictor of dropout.

CONCLUSIONS

Interpersonal sensitivity at baseline predicts less change and a slower rate of change in anxiety symptoms. Early detection of elevated interpersonal sensitivity can help therapists take action to address these barriers to successful treatment and help scientists build decision support tools that accurately predict the trajectory of change in anxiety symptoms for these patients.

Diagnostic clinical prediction rules for categorising low back pain: A systematic review

BACKGROUND

Low back pain (LBP) is a common complex condition, where specific diagnoses are hard to identify. Diagnostic clinical prediction rules (CPRs) are known to improve clinical decision-making. A review of LBP diagnostic-CPRs by Haskins et al. (2015) identified six diagnostic-CPRs in derivation phases of development, with one tool ready for implementation. Recent progress on these tools is unknown. Therefore, this review aimed to investigate developments in LBP diagnostic-CPRs and evaluate their readiness for implementation.

METHODS

A systematic review was performed on five databases (Medline, Amed, Cochrane Library, PsycInfo, and CINAHL) combined with hand-searching and citation-tracking to identify eligible studies. Study and tool quality were appraised for risk of bias (Quality Assessment of Diagnostic Accuracy Studies-2), methodological quality (checklist using accepted CPR methodological standards), and CPR tool appraisal (GRade and ASsess Predictive).

RESULTS

Of 5021 studies screened, 11 diagnostic-CPRs were identified. Of the six previously known, three have been externally validated but not yet undergone impact analysis. Five new tools have been identified since Haskin et al. (2015); all are still in derivation stages. The most validated diagnostic-CPRs include the Lumbar-Spinal-Stenosis-Self-Administered-Self-Reported-History-Questionnaire and Diagnosis-Support-Tool-to-Identify-Lumbar-Spinal-Stenosis, and the StEP-tool which differentiates radicular from axial-LBP.

CONCLUSIONS

This updated review of LBP diagnostic CPRs found five new tools, all in the early stages of development. Three previously known tools have now been externally validated but should be used with caution until impact evaluation studies are undertaken. Future funding should focus on externally validating and assessing the impact of existing CPRs on clinical decision-making.

Learning to safely integrate generative artificial intelligence technology into travel medicine practice

We have entered an exciting era where generative artificial intelligence is finding multiple applications in everyday life and scientific inquiry. This editorial explores the possibility of integrating this technology into the pre-travel consultation, but with careful consideration of its current capabilities, limitations, and potential risks to patient safety.

A Deep Learning-Based Decision Support Tool for Plant-Parasitic Nematode Management

Plant-parasitic nematodes (PPN), especially sedentary endoparasitic nematodes like root-knot nematodes (RKN), pose a significant threat to major crops and vegetables. They are responsible for causing substantial yield losses, leading to economic consequences, and impacting the global food supply. The identification of PPNs and the assessment of their population is a tedious and time-consuming task. This study developed a state-of-the-art deep learning model-based decision support tool to detect and estimate the nematode population. The decision support tool is integrated with the fast inferencing YOLOv5 model and used pretrained nematode weight to detect plant-parasitic nematodes (juveniles) and eggs. The performance of the YOLOv5-640 model at detecting RKN eggs was as follows: precision = 0.992; recall = 0.959; F1-score = 0.975; and mAP = 0.979. YOLOv5-640 was able to detect RKN eggs with an inference time of 3.9 milliseconds, which is faster compared to other detection methods. The deep learning framework was integrated into a user-friendly web application system to build a fast and reliable prototype nematode decision support tool (NemDST). The NemDST facilitates farmers/growers to input image data, assess the nematode population, track the population growths, and recommend immediate actions necessary to control nematode infestation. This tool has the potential for rapid assessment of the nematode population to minimise crop yield losses and enhance financial outcomes.

Feasibility Testing of a Web-Based Reproductive Decision Support Tool for Cystic Fibrosis

BACKGROUND

People with cystic fibrosis (CF) are increasingly considering their reproductive goals. We developed MyVoice:CF, a web-based patient-centered reproductive decision support tool and assessed its implementation in CF care.

METHODS

We conducted a feasibility trial among 18-44-year-old women with CF and multidisciplinary CF providers. Prior to CF clinic visit, patient participants completed a baseline survey, used MyVoice:CF, and assessed acceptability, appropriateness, and usability. After clinic, participants rated impact on reproductive health communication. At 3 months post-use, participants assessed impact on reproductive health outcomes. Provider participants completed a survey and focus group regarding MyVoice:CF feasibility/implementation. We assessed outcomes descriptively. We compared MyVoice:CF's impact on outcomes from baseline to follow-up using McNemar's and Wilcoxon signed rank tests as appropriate.

RESULTS

Forty-three patient participants completed baseline surveys and 40 rated MyVoice:CF's feasibility; 10 providers participated. Patient participants rated MyVoice:CF's acceptability as 4.48±0.50 out of 5, appropriateness as 4.61±0.48 out of 5, and usability as 82.25±11.02 ('A'/excellent). After MyVoice:CF use, participants reported improved reproductive health communication self-efficacy vs. baseline (3.54±1.17vs.3.95±0.93, p<0.001). At baseline, 36% of participants reported any discussion of reproductive goals/plans with their CF team in the past year compared to 59% after first visit post-MyVoice:CF use (p=0.049). Provider participants similarly rated MyVoice:CF as feasible and reported no negative impacts on clinic flow after implementation.

CONCLUSIONS

MyVoice:CF is acceptable, appropriate, and usable for those with CF. Preliminary effectiveness evaluation suggests that MyVoice:CF improves self-efficacy in and frequency of reproductive health communication. Future studies should further assess MyVoice:CF's impact on reproductive health communication and outcomes.

Predicting whether patients will achieve minimal clinically important differences following hip or knee arthroplasty

Aims

A substantial fraction of patients undergoing knee arthroplasty (KA) or hip arthroplasty (HA) do not achieve an improvement as high as the minimal clinically important difference (MCID), i.e. do not achieve a meaningful improvement. Using three patient-reported outcome measures (PROMs), our aim was: 1) to assess machine learning (ML), the simple pre-surgery PROM score, and logistic-regression (LR)-derived performance in their prediction of whether patients undergoing HA or KA achieve an improvement as high or higher than a calculated MCID; and 2) to test whether ML is able to outperform LR or pre-surgery PROM scores in predictive performance.

Methods

MCIDs were derived using the change difference method in a sample of 1,843 HA and 1,546 KA patients. An artificial neural network, a gradient boosting machine, least absolute shrinkage and selection operator (LASSO) regression, ridge regression, elastic net, random forest, LR, and pre-surgery PROM scores were applied to predict MCID for the following PROMs: EuroQol five-dimension, five-level questionnaire (EQ-5D-5L), EQ visual analogue scale (EQ-VAS), Hip disability and Osteoarthritis Outcome Score-Physical Function Short-form (HOOS-PS), and Knee injury and Osteoarthritis Outcome Score-Physical Function Short-form (KOOS-PS).

Results

Predictive performance of the best models per outcome ranged from 0.71 for HOOS-PS to 0.84 for EQ-VAS (HA sample). ML statistically significantly outperformed LR and pre-surgery PROM scores in two out of six cases.

Conclusion

MCIDs can be predicted with reasonable performance. ML was able to outperform traditional methods, although only in a minority of cases.

Barriers and Enablers for Implementation of an Artificial Intelligence-Based Decision Support Tool to Reduce the Risk of Readmission of Patients With Heart Failure: Stakeholder Interviews

BACKGROUND

Artificial intelligence (AI) applications in health care are expected to provide value for health care organizations, professionals, and patients. However, the implementation of such systems should be carefully planned and organized in order to ensure quality, safety, and acceptance. The gathered view of different stakeholders is a great source of information to understand the barriers and enablers for implementation in a specific context.

OBJECTIVE

This study aimed to understand the context and stakeholder perspectives related to the future implementation of a clinical decision support system for predicting readmissions of patients with heart failure. The study was part of a larger project involving model development, interface design, and implementation planning of the system.

METHODS

Interviews were held with 12 stakeholders from the regional and municipal health care organizations to gather their views on the potential effects implementation of such a decision support system could have as well as barriers and enablers for implementation. Data were analyzed based on the categories defined in the nonadoption, abandonment, scale-up, spread, sustainability (NASSS) framework.

RESULTS

Stakeholders had in general a positive attitude and curiosity toward AI-based decision support systems, and mentioned several barriers and enablers based on the experiences of previous implementations of information technology systems. Central aspects to consider for the proposed clinical decision support system were design aspects, access to information throughout the care process, and integration into the clinical workflow. The implementation of such a system could lead to a number of effects related to both clinical outcomes as well as resource allocation, which are all important to address in the planning of implementation. Stakeholders saw, however, value in several aspects of implementing such system, emphasizing the increased quality of life for those patients who can avoid being hospitalized.

CONCLUSIONS

Several ideas were put forward on how the proposed AI system would potentially affect and provide value for patients, professionals, and the organization, and implementation aspects were important parts of that. A successful system can help clinicians to prioritize the need for different types of treatments but also be used for planning purposes within the hospital. However, the system needs not only technological and clinical precision but also a carefully planned implementation process. Such a process should take into consideration the aspects related to all the categories in the NASSS framework. This study further highlighted the importance to study stakeholder needs early in the process of development, design, and implementation of decision support systems, as the data revealed new information on the potential use of the system and the placement of the application in the care process.

A decision support tool has similar high PrEP uptake and increases early PrEP persistence in adolescent girls and young women in South Africa: results from a randomized controlled trial

INTRODUCTION

African adolescent girls and young women (AGYW) have high rates of HIV acquisition and are a priority population for HIV pre-exposure prophylaxis (PrEP). PrEP implementation has been limited by AGYW's low perceived HIV risk and provider demands. A decision support tool (DST) with information about PrEP could improve clients' risk perception, knowledge about PrEP, informed decision-making and motivation to use PrEP based on their risk, facilitating PrEP delivery in primary healthcare (PHC) clinics.

METHODS

We designed MyPrEP, a client-facing DST about PrEP and HIV prevention, with youth-friendly information and images. The impact of the MyPrEP tool was assessed among HIV-negative women aged 18-25 years presenting to a PHC clinic in Johannesburg, South Africa from March 2019 to 2020. AGYW were randomized by day to the DST or a general health website as the control condition. A clinician blinded to DST versus control allocation provided standard of care counselling about PrEP, offered PrEP, administered a questionnaire and conducted sexually transmitted infection testing. The primary outcome was PrEP initiation and the secondary outcome was PrEP persistence at 1 month, determined by pharmacy dispensation records.

RESULTS

Of 386 AGYW screened, 353 were randomized (DST n = 172, control n = 181) with a median age of 21 years (interquartile range [IQR] 20, 23) and 56% (199/353) attending the clinic for HIV testing, 46% (164/353) using contraception, 15% (53/353) using condoms consistently and 37% (108/353) with a curable sexually transmitted infection. PrEP was initiated by 97% in the DST group and 94% in the control group (OR 1.79; 95% confidence interval, CI = 0.79-1.53), of whom two-thirds planned to continue PrEP until they decided if they liked PrEP. At 1 month, PrEP persistence was 19% in the DST and 10% in the control group (OR 1.97, 95% CI 1.08-3.69). Ninety-nine percent randomized to the DST reported satisfaction with MyPrEP.

CONCLUSIONS

Among AGYW attending a South African PHC clinic, PrEP uptake was >90% with two-fold higher PrEP persistence at 1 month in those randomized to use the MyPrEP DST. Given the need for strategies to support PrEP implementation and improve low PrEP persistence among African AGYW, a PrEP DST warrants further evaluation.

Prevalence, risk factors of the use of physical restraint and impact of a decision support tool: A before-and-after study

BACKGROUND

Physical restraint is frequently used in intensive care units to prevent patients' life-threatening removal of indwelling devices. In France, their use is poorly studied. Therefore, to evaluate the need for physical restraint, we have designed and implemented a decision support tool.

AIMS

Besides describing the prevalence of physical restraint use, this study aimed to assess whether the implementation of a nursing decision support tool had an impact on restraint use and to identify the factors associated with this use.

STUDY DESIGN

A large observational, multicentre study with a repeated one-day point prevalence design was conducted. All adult patients hospitalized in intensive care units were eligible for this study. Two study periods were planned: before (control period) and after (intervention period) the deployment of the decision support tool and staff training. A multilevel model was performed to consider the centre effect.

RESULTS

During the control period, 786 patients were included, and 510 were in the intervention period. The prevalence of physical restraint was 28% (95% CI: 25.1%-31.4%) and 25% (95% CI: 21.5%-29.1%) respectively (χ²  = 1.35; p = .24). Restraint was applied by the nurse and/or nurse assistant in 96% of cases in both periods, mainly to wrists (89% vs. 83%, p = .14). The patient-to-nurse ratio was significantly lower in the intervention period (1:3.0 ± 1 vs. 1:2.7 ± 0.7, p < .001). In multivariable analysis, mechanical ventilation was associated with physical restraint (aOR [95% CI] = 6.0 [3.5-10.2]).

CONCLUSION

The prevalence of physical restraint use in France was lower than expected. In our study, the decision support tool did not substantially impact physical restraint use. Hence, the decision support tool would deserve to be assessed in a randomized controlled trial.

RELEVANCE TO CLINICAL PRACTICE

The decision to physically restrain a patient could be protocolised and managed by critical care nurses. A regular evaluation of the level of sedation could allow the most deeply sedated patients to be exempted from physical restraint.

External assessment and refinement of a population pharmacokinetic model to guide tacrolimus dosing in pediatric heart transplant

STUDY OBJECTIVE

The immunosuppressant tacrolimus is a first-line agent to prevent graft rejection following pediatric heart transplant; however, it suffers from extensive inter-patient variability and a narrow therapeutic window. Personalized tacrolimus dosing may improve transplant outcomes by more efficiently achieving and maintaining therapeutic tacrolimus concentrations. We sought to externally validate a previously published population pharmacokinetic (PK) model that was constructed with data from a single site.

DATA SOURCE

Data were collected from Seattle, Texas, and Boston Children's Hospitals, and assessed using standard population PK modeling techniques in NONMEMv7.2.

MAIN RESULTS

While the model was not successfully validated for use with external data, further covariate searching identified weight (p < 0.0001 on both volume and elimination rate) as a model-significant covariate. This refined model acceptably predicted future tacrolimus concentrations when guided by as few as three concentrations (median prediction error = 7%; median absolute prediction error = 27%).

CONCLUSION

These findings support the potential clinical utility of a population PK model to provide personalized tacrolimus dosing guidance.

Evaluation of the EsteR Toolkit for COVID-19 Decision Support: Sensitivity Analysis and Usability Study

BACKGROUND

During the COVID-19 pandemic, local health authorities were responsible for managing and reporting current cases in Germany. Since March 2020, employees had to contain the spread of COVID-19 by monitoring and contacting infected persons as well as tracing their contacts. In the EsteR project, we implemented existing and newly developed statistical models as decision support tools to assist in the work of the local health authorities.

OBJECTIVE

The main goal of this study was to validate the EsteR toolkit in two complementary ways: first, investigating the stability of the answers provided by our statistical tools regarding model parameters in the back end and, second, evaluating the usability and applicability of our web application in the front end by test users.

METHODS

For model stability assessment, a sensitivity analysis was carried out for all 5 developed statistical models. The default parameters of our models as well as the test ranges of the model parameters were based on a previous literature review on COVID-19 properties. The obtained answers resulting from different parameters were compared using dissimilarity metrics and visualized using contour plots. In addition, the parameter ranges of general model stability were identified. For the usability evaluation of the web application, cognitive walk-throughs and focus group interviews were conducted with 6 containment scouts located at 2 different local health authorities. They were first asked to complete small tasks with the tools and then express their general impressions of the web application.

RESULTS

The simulation results showed that some statistical models were more sensitive to changes in their parameters than others. For each of the single-person use cases, we determined an area where the respective model could be rated as stable. In contrast, the results of the group use cases highly depended on the user inputs, and thus, no area of parameters with general model stability could be identified. We have also provided a detailed simulation report of the sensitivity analysis. In the user evaluation, the cognitive walk-throughs and focus group interviews revealed that the user interface needed to be simplified and more information was necessary as guidance. In general, the testers rated the web application as helpful, especially for new employees.

CONCLUSIONS

This evaluation study allowed us to refine the EsteR toolkit. Using the sensitivity analysis, we identified suitable model parameters and analyzed how stable the statistical models were in terms of changes in their parameters. Furthermore, the front end of the web application was improved with the results of the conducted cognitive walk-throughs and focus group interviews regarding its user-friendliness.

Usefulness of cultivar-level calibration of AquaCrop for vegetables depends on the crop and data availability

As a result of climate change, climatic extremes are expected to increase. For high-value crops like vegetables, irrigation is a potentially economically viable adaptation measure in western Europe. To optimally schedule irrigation, decision support systems based on crop models like AquaCrop are increasingly used by farmers. High value vegetable crops like cauliflower or spinach are grown in two distinct growth cycles per year and, additionally, have a high turnover rate of new varieties. To successfully deploy the AquaCrop model in a decision support system, it requires a robust calibration. However, it is not known whether parameters can be conserved over both growth periods, nor whether a cultivar dependent model calibration is always required. Furthermore, when data are collected from farmers' fields, there are constraints in data availability and uncertainty. We collected data from commercial cauliflower and spinach fields in Belgium in 2019, 2020 and 2021 during different growing periods and of different cultivars. With the use of a Bayesian calibration, we confirmed the need for a condition or cultivar specific calibration for cauliflower, while for spinach, splitting the data per cultivar or pooling the data together did not improve uncertainty on the model simulations. However, due to uncertainties arising from field specific soil and weather conditions, or measurement errors from calibration data, real time field specific adjustments are advised to simulations when using AquaCrop as decision support tool. Remotely sensed or in situ ground data may be invaluable information to reduce uncertainty on model simulations.

Erratum: PRAGMATIST: A tool to prioritize foot-and-mouth disease virus antigens held in vaccine banks

[This corrects the article DOI: 10.3389/fvets.2022.1029075.].

PRAGMATIST: A tool to prioritize foot-and-mouth disease virus antigens held in vaccine banks

Antigen banks have been established to supply foot-and-mouth disease virus (FMDV) vaccines at short notice to respond to incursions or upsurges in cases of FMDV infection. Multiple vaccine strains are needed to protect against specific FMDV lineages that circulate within six viral serotypes that are unevenly distributed across the world. The optimal selection of distinct antigens held in a bank must carefully balance the desire to cover these risks with the costs of purchasing and maintaining vaccine antigens. PRAGMATIST is a semi-quantitative FMD vaccine strain selection tool combining three strands of evidence: (1) estimates of the risk of incursion from specific areas (source area score); (2) estimates of the relative prevalence of FMD viral lineages in each specific area (lineage distribution score); and (3) effectiveness of each vaccine against specific FMDV lineages based on laboratory vaccine matching tests (vaccine coverage score). The output is a vaccine score, which identifies vaccine strains that best address the threats, and consequently which are the highest priority for inclusion in vaccine antigen banks. In this paper, data used to populate PRAGMATIST are described, including the results from expert elicitations regarding FMD risk and viral lineage circulation, while vaccine coverage data is provided from vaccine matching tests performed at the WRLFMD between 2011 and 2021 (n = 2,150). These data were tailored to working examples for three hypothetical vaccine antigen bank perspectives (Europe, North America, and Australia). The results highlight the variation in the vaccine antigens required for storage in these different regions, dependent on risk. While the tool outputs are largely robust to uncertainty in the input parameters, variation in vaccine coverage score had the most noticeable impact on the estimated risk covered by each vaccine, particularly for vaccines that provide substantial risk coverage across several lineages.

Joint Models to Predict Dairy Cow Survival from Sensor Data Recorded during the First Lactation

Early predictions of cows' probability of survival to different lactations would help farmers in making successful management and breeding decisions. For this purpose, this research explored the adoption of joint models for longitudinal and survival data in the dairy field. An algorithm jointly modelled daily first-lactation sensor data (milk yield, body weight, rumination time) and survival data (i.e., time to culling) from 6 Holstein dairy farms. The algorithm was set to predict survival to the beginning of the second and third lactations (i.e., second and third calving) from sensor observations of the first 60, 150, and 240 days in milk of cows' first lactation. Using 3-time-repeated 3-fold cross-validation, the performance was evaluated in terms of Area Under the Curve and expected error of prediction. Across the different scenarios and farms, the former varied between 45% and 76%, while the latter was between 3.5% and 26%. Significant results were obtained in terms of expected error of prediction, meaning that the method provided survival probabilities in line with the observed events in the datasets (i.e., culling). Furthermore, the performances were stable among farms. These features may justify further research on the use of joint models to predict the survival of dairy cattle.

Penicillin Allergy label - the unmet needs - causes and potential solutions

Summary

Background. Penicillin allergy is the most prevalent drug allergy. Its overdiagnosis has been associated with inappropriate antibiotic prescribing, increased antimicrobial resistance, worse clinical outcomes, and increased healthcare costs. Methods. 403 inpatients were audited against National Institute of Clinical Excellence (NICE) Clinical Guidance 183 (CG183) on diagnosis, investigations, documentation, and management of penicillin allergy. 50 junior doctors were surveyed to explore barriers to best practice, investigating their knowledge of, and confidence using the NICE CG183 guidelines. Their views on potential solutions were also explored. Results. The audit identified: 13% (54/403) of patients labelled penicillin allergic; 24% (13/54) fulfilled criteria for referral but none were referred to specialists. With regards to documentation: 33% (18/54) documented exact drug name; 72% (39/54) documented signs and symptoms; 20% (11/54) documented reaction severity; 2% (1/54) documented indication for the drug taken; 4% (2/54) documented number of doses taken or days before onset of the reaction and 0% documented route of administration. The survey revealed barriers including: 1- lack of awareness and confidence in applying the NICE CG183 on diagnosis and management; 2- tendency to err on the side of caution when de-labelling patients. All agreed that decision support tools would address barriers to best practice and appropriate penicillin allergy de-labelling Conclusions.The current practice of diagnosing, documenting, and managing penicillin allergies does not meet NICE CG183. A lack of awareness and confidence using NICE CG183 are the main contributing barriers to best practice. Decision support tools, including a drug allergy app, would help overcome these barriers.

A smart, practical, deep learning-based clinical decision support tool for patients in the prostate-specific antigen gray zone: model development and validation

OBJECTIVE

Despite efforts to improve screening and early detection of prostate cancer (PC), no available biomarker has shown acceptable performance in patients with prostate-specific antigen (PSA) gray zones. We aimed to develop a deep learning-based prediction model with minimized parameters and missing value handling algorithms for PC and clinically significant PC (CSPC).

MATERIALS AND METHODS

We retrospectively analyzed data from 18 824 prostate biopsies collected between March 2003 and December 2020 from 2 databases, resulting in 12 739 cases in the PSA gray zone of 2.0-10.0 ng/mL. Dense neural network (DNN) and extreme gradient boosting (XGBoost) models for PC and CSPC were developed with 5-fold cross-validation. The area under the curve of the receiver operating characteristic (AUROC) was compared with that of serum PSA, PSA density, free PSA (fPSA) portion, and prostate health index (PHI).

RESULTS

The AUROC values in the DNN model with the imputation of missing values were 0.739 and 0.708 (PC) and 0.769 and 0.742 (CSPC) in internal and external validation, whereas those of the non-imputed dataset were 0.740 and 0.771 (PC) and 0.807 and 0.771 (CSPC), respectively. The performance of the DNN model was like that of the XGBoost model, but better than all tested clinical biomarkers for both PC and CSPC. The developed DNN model outperformed PHI, serum PSA, and percent-fPSA with or without missing value imputation.

DISCUSSION

DNN models for missing value imputation can be used to predict PC and CSPC. Further validation in real-life scenarios are need to recommend for actual implementation, but the results from our study support the increasing role of deep learning analytics in the clinical setting.

CONCLUSIONS

A deep learning model for PC and CSPC in PSA gray zones using minimal, routinely used clinical parameter variables and data imputation of missing values was successfully developed and validated.

Electronic Decision Support in the Delivery Room Using Augmented Reality to Improve Newborn Life Support Guideline Adherence: A Randomized Controlled Pilot Study

INTRODUCTION

The Newborn Life Support (NLS) guideline aims to provide healthcare professionals a consistent approach during neonatal resuscitation. Adherence to this and analogous guidelines has repetitively been proven to be difficult.This study evaluates adherence to guideline using a novel augmented reality (Microsoft HoloLens) electronic decision support tool during standardized simulated neonatal resuscitation compared with subjects working from memory alone.

METHODS

In this randomized controlled pilot study, 18 professionals responsible for neonatal resuscitation were randomized to the intervention group and 11 to the control group. Demographic characteristics were similar between both groups. A standardized neonatal resuscitation scenario was performed, which was recorded and later assessed for adherence to the NLS algorithm by 2 independent reviewers. Secondary outcomes were error classification in case of algorithm deviation and time to the execution or completion of critical steps in the algorithm to determine delay.

RESULTS

Median (interquartile range) scores of a theoretical maximum of 40 in the intervention group were 34 (32.5-35.5) versus 29 (27-33) in the control group ( P = 0.004). Errors of commission were committed less frequently with the electronic decision support tool 2 (1-2.5) compared with 4 (2-4) in the control group ( P = 0.029). Analysis of time to initiation or completion of key steps in the NLS algorithm showed no significant differences between both groups.

CONCLUSIONS

Healthcare professionals using an electronic decision support tool showed improved adherence to the NLS guideline during simulated neonatal resuscitation.

The development and utility of a multicriteria patient decision aid for people contemplating treatment for osteoarthritis

BACKGROUND

There are a range of treatment options for osteoarthritis (OA) of the knee and hip, each with a unique profile of risks and benefits. Patient decision aids can help incorporate patient preferences in treatment decision-making. The aim of this study was to develop and test the utility of a patient decision aid for OA that was developed using a multicriteria decision analytic framework.

METHODS

People contemplating treatment for OA who had accessed the website myjointpain.org.au were invited to participate in the study by using the online patient decision aid. Two forms of the patient decision aid were created: A shorter form and a longer form, which allowed greater customization that was offered to respondents after they had completed the shorter form. Respondents also completed questions asking about their experience using the patient decision aid.

RESULTS

A total of 625 self-selected respondents completed the short-form and 180 completed the long-form. Across both forms, serious side effects, pain and function were rated as the most important treatment outcomes. Most respondents (64%) who completed the longer form reported that using the tool was a positive experience, 38% reported that using the tool had changed their mind and 48% said that using the tool would improve the quality of their decision-making.

CONCLUSIONS

Overall, the findings suggest that this patient decision aid may be of use to a substantial number of people in facilitating appropriate treatment decision-making.

PATIENT OR PUBLIC CONTRIBUTION

Service users of myjointpain.org.au were involved through their participation in the study, and their feedback will guide the development of future iterations of the tool.

Effects of an Explicit Value Clarification Method With Computer-Tailored Advice on the Effectiveness of a Web-Based Smoking Cessation Decision Aid: Findings From a Randomized Controlled Trial

Background

Smoking continues to be a driver of mortality. Various forms of evidence-based cessation assistance exist; however, their use is limited. The choice between them may also induce decisional conflict. Offering decision aids (DAs) may be beneficial; however, insights into their effective elements are lacking.

Objective

This study tested the added value of an effective element (ie, an “explicit value clarification method” paired with computer-tailored advice indicating the most fitting cessation assistance) of a web-based smoking cessation DA.

Methods

A web-based randomized controlled trial was conducted among smokers motivated to stop smoking within 6 months. The intervention group received a DA with the aforementioned elements, and the control group received the same DA without these elements. The primary outcome measure was 7-day point prevalence abstinence 6 months after baseline (time point 3 [t=3]). Secondary outcome measures were 7-day point prevalence of abstinence 1 month after baseline (time point 2 [t=2]), evidence-based cessation assistance use (t=2 and t=3), and decisional conflict (immediately after DA; time point 1). Logistic and linear regression analyses were performed to assess the outcomes. Analyses were conducted following 2 (decisional conflict) and 3 (smoking cessation) outcome scenarios: complete cases, worst-case scenario (assuming that dropouts still smoked), and multiple imputations. A priori sample size calculation indicated that 796 participants were needed. The participants were mainly recruited on the web (eg, social media). All the data were self-reported.

Results

Overall, 2375 participants were randomized (intervention n=1164, 49.01%), of whom 599 (25.22%; intervention n=275, 45.91%) completed the DAs, and 276 (11.62%; intervention n=143, 51.81%), 97 (4.08%; intervention n=54, 55.67%), and 103 (4.34%; intervention n=56, 54.37%) completed time point 1, t=2, and t=3, respectively. More participants stopped smoking in the intervention group (23/63, 37%) than in the control group (14/52, 27%) after 6 months; however, this was only statistically significant in the worst-case scenario (crude P=.02; adjusted P=.04). Effects on the secondary outcomes were only observed for smoking abstinence after 1 month (15/55, 27%, compared with 7/46, 15%, in the crude and adjusted models, respectively; P=.02) and for cessation assistance uptake after 1 month (26/56, 46% compared with 18/47, 38% only in the crude model; P=.04) and 6 months (38/61, 62% compared with 26/50, 52%; crude P=.01; adjusted P=.02) but only in the worst-case scenario. Nonuse attrition was 34.19% higher in the intervention group than in the control group (P<.001).

Conclusions

Currently, we cannot confidently recommend the inclusion of explicit value clarification methods and computer-tailored advice. However, they might result in higher nonuse attrition rates, thereby limiting their potential. As a lack of statistical power may have influenced the outcomes, we recommend replicating this study with some adaptations based on the lessons learned.

Trial Registration

Netherlands Trial Register NL8270; https://www.trialregister.nl/trial/8270

International Registered Report Identifier (IRRID)

RR2-10.2196/21772

Evaluating Decision Support Tools for Precision Nitrogen Management on Creeping Bentgrass Putting Greens

Nitrogen (N) is the most limiting nutrient for turfgrass growth. Few tools or soil tests exist to help managers guide N fertilizer decisions. Turf growth prediction models have the potential to be useful, but the lone turfgrass growth prediction model only takes into account temperature, limiting its accuracy. This study investigated the ability of a machine learning (ML)-based turf growth model using the random forest (RF) algorithm (ML-RF model) to improve creeping bentgrass (Agrostis stolonifera) putting green management by estimating short-term clipping yield. This method was compared against three alternative N application strategies including (1) PACE Turf growth potential (GP) model, (2) an experience-based method for applying N fertilizer (experience-based method), and (3) the experience-based method guided by a vegetative index, normalized difference red edge (NDRE)-based method. The ML-RF model was built based on a set of variables including 7-day weather, evapotranspiration (ET), traffic intensity, soil moisture content, N fertilization rate, NDRE, and root zone type. The field experiment was conducted on two sand-based research greens in 2020 and 2021. The cumulative applied N fertilizer was 281 kg ha^-1 for the PACE Turf GP model, 190 kg ha^-1 for the experience-based method, 140 kg ha^-1 for the ML-RF model, and around 75 kg ha^-1 NDRE-based method. ML-RF model and NDRE-based method were able to provide customized N fertilization recommendations on different root zones. The methods resulted in different mean turfgrass qualities and NDRE. From highest to lowest, they were PACE Turf GP model, experience-based, ML-RF model, and NDRE-based method, and the first three methods produced turfgrass quality over 7 (on a scale from 1 to 9) and NDRE value over 0.30. N fertilization guided by the ML-RF model resulted in a moderate amount of fertilizer applied and acceptable turfgrass performance characteristics. This application strategy is based on the N cycle and has the potential to assist turfgrass managers in making N fertilization decisions for creeping bentgrass putting greens.

Prediction-Driven Decision Support for Patients With Mild Stroke: A Model Based on Machine Learning Algorithms

Background and Purpose: Treatment for mild stroke remains an open question. We aim to develop a decision support tool based on machine learning (ML) algorithms, called DAMS (Disability After Mild Stroke), to identify mild stroke patients who would be at high risk of post-stroke disability (PSD) if they only received medical therapy and, more importantly, to aid neurologists in making individual clinical decisions in emergency contexts.

Methods: Ischemic stroke patients were prospectively recorded in the National Advanced Stroke Center of Nanjing First Hospital (China) between July 2016 and September 2020. The exclusion criteria were patients who received thrombolytic therapy, age <18 years, lack of 3-month modified Rankin Scale (mRS), disabled before the index stroke, with an admission National Institute of Health stroke scale (NIHSS) > 5. The primary outcome was PSD, corresponding to 3-month mRS ≥ 2. We developed five ML models and assessed the area under curve (AUC) of receiver operating characteristic, calibration curve, and decision curve analysis. The optimal ML model was selected to be DAMS. In addition, SHapley Additive exPlanations (SHAP) approach was introduced to rank the feature importance. Finally, rapid-DAMS (R-DAMS) was constructed for a more urgent situation based on DAMS.

Results: A total of 1,905 mild stroke patients were enrolled in this study, and patients with PSD accounted for 23.4% (447). There was no difference in AUCs between the five models (ranged from 0.691 to 0.823). Although there was similar discriminative performance between ML models, the support vector machine model exhibited higher net benefit and better calibration (Brier score, 0.159, calibration slope, 0.935, calibration intercept, 0.035). Therefore, this model was selected for DAMS. In addition, SHAP approach showed that the most crucial feature was NIHSS on admission. Finally, R-DAMS was constructed and there was similar discriminative performance between R-DAMS and DAMS, but the former performed worse on calibration.

Conclusions: DAMS and R-DAMS, as prediction-driven decision support tools, were designed to aid clinical decision-making for mild stroke patients in emergency contexts. In addition, even within a narrow range of baseline scores, NIHSS on admission is the strongest feature that contributed to the prediction.

A Decision Support Tool for Allogeneic Hematopoietic Stem Cell Transplantation for Children With Sickle Cell Disease: Acceptability and Usability Study

Background

Individuals living with sickle cell disease (SCD) may benefit from a variety of disease-modifying therapies, including hydroxyurea, voxelotor, crizanlizumab, L-glutamine, and chronic blood transfusions. However, allogeneic hematopoietic stem cell transplantation (HCT) remains the only nonexperimental treatment with curative intent. As HCT outcomes can be influenced by the complex interaction of several risk factors, HCT can be a difficult decision for health care providers to make for their patients with SCD.

Objective

The aim of this study is to determine the acceptability and usability of a prototype decision support tool for health care providers in decision-making about HCT for SCD, together with patients and their families.

Methods

On the basis of published transplant registry data, we developed the Sickle Options Decision Support Tool for Children, which provides health care providers with personalized transplant survival and risk estimates for their patients to help them make informed decisions regarding their patients’ management of SCD. To evaluate the tool for its acceptability and usability, we conducted beta tests of the tool and surveys with physicians using the Ottawa Decision Support Framework and mobile health app usability questionnaire, respectively.

Results

According to the mobile health app usability questionnaire survey findings, the overall usability of the tool was high (mean 6.15, SD 0.79; range 4.2-7). According to the Ottawa Decision Support Framework survey findings, acceptability of the presentation of information on the decision support tool was also high (mean 2.94, SD 0.63; range 2-4), but the acceptability regarding the amount of information was mixed (mean 2.59, SD 0.5; range 2-3). Most participants expressed that they would use the tool in their own patient consults (13/15, 87%) and suggested that the tool would ease the decision-making process regarding HCT (8/9, 89%). The 4 major emergent themes from the qualitative analysis of participant beta tests include user interface, data content, usefulness during a patient consult, and potential for a patient-focused decision aid. Most participants supported the idea of a patient-focused decision aid but recommended that it should include more background on HCT and a simplification of medical terminology.

Conclusions

We report the development, acceptability, and usability of a prototype decision support tool app to provide individualized risk and survival estimates to patients interested in HCT in a patient consultation setting. We propose to finalize the tool by validating predictive analytics using a large data set of patients with SCD who have undergone HCT. Such a tool may be useful in promoting physician-patient collaboration in making shared decisions regarding HCT for SCD. Further incorporation of patient-specific measures, including the HCT comorbidity index and the quality of life after transplant, may improve the applicability of the decision support tool in a health care setting.

Initial Results of the American Burn Association (ABA) Observational Multi-Center Evaluation on the Effectiveness of the Burn Navigator

The objective of this multi-center observational study was to evaluate resuscitation volumes and outcomes of patients who underwent fluid resuscitation utilizing the Burn Navigator (BN), a resuscitation clinical decision support tool. Two analyses were performed: examination of the first 24 hours of resuscitation, and the first 24 hours post-burn regardless of when the resuscitation began, to account for patients who presented in a delayed fashion. Patients were classified as having followed the BN (FBN) if all hourly fluid rates were within ±20 mL of BN recommendations for that hour at least 83% of the time, otherwise they were classified as not having followed BN (NFBN). Analysis of resuscitation volumes for FBN patients in the first 24 hours resulted in average volumes for primary crystalloid) and total fluids administered of 4.07 ± 1.76 mL/kg/TBSA (151.48 ± 77.46 mL/kg), and 4.68 ± 2.06 mL/kg/TBSA (175.01 ± 92.22 mL/kg), respectively. Patients who presented in a delayed fashion revealed average volumes for primary and total fluids of 5.28 ± 2.54 mL/kg/TBSA (201.11 ± 106.53 mL/kg), 6.35 ± 2.95 mL/kg/TBSA (244.08 ± 133.5 mL/kg), respectively. There was a significant decrease in the incidence of burn shock in the FBN group (p< 0.05). This study shows that the BN provides comparable resuscitation volumes of primary crystalloid fluid to the Parkland Formula, recommends total fluid infusion less than the Ivy Index, and was associated with a decreased incidence of burn shock. Early initiation of the BN device resulted in lower overall fluid volumes.

Improving the care of term babies at risk of hypoglycaemia: A microsystem approach

AIM

Neonatal hypoglycaemia is a common problem, often requiring admission to the neonatal intensive care unit (NICU). Our aim was to reduce term admissions to NICU for hypoglycaemia by 50% over 4 years.

METHODS

Inborn term babies from 1 January 2015 to 31 December 2018 were included. Using quality-improvement methodology, we designed interventions based on human factors to incorporate best practice recommendations for babies at-risk of hypoglycaemia. This included standardisation of local guidelines, introduction of educational programmes to reiterate changes to practice and a multidisciplinary steering group to review term admissions to better understand the cause of failure of the maternal-neonatal pathway. The outcome measures were the number of term babies admitted to NICU for hypoglycaemia and the proportion of these babies not requiring intravenous (IV) dextrose. Run charts were used to monitor hypoglycaemia admissions and the impact of each intervention.

RESULTS

There was an overall reduction in the number of term babies admitted to NICU for hypoglycaemia from 36 babies in 2014 (baseline) to 5 babies in 2018. The percentage of babies admitted to the neonatal unit who did not require IV dextrose decreased from 22/36 (61%) in 2014 to 0/5 (0%) in 2018. Admissions from the delivery suite decreased from 21/36 (58%) to 1/5 (20%). There were no adverse outcomes observed in the period before or after the intervention.

CONCLUSIONS

We demonstrate a simple, cost-effective quality improvement project using fundamental human factors principles. This initiative successfully reduced the number of term admissions for hypoglycaemia over 4 years.

Improving Medication Regimen Recommendation for Parkinson's Disease Using Sensor Technology

Parkinson's disease medication treatment planning is generally based on subjective data obtained through clinical, physician-patient interactions. The Personal KinetiGraph™ (PKG) and similar wearable sensors have shown promise in enabling objective, continuous remote health monitoring for Parkinson's patients. In this proof-of-concept study, we propose to use objective sensor data from the PKG and apply machine learning to cluster patients based on levodopa regimens and response. The resulting clusters are then used to enhance treatment planning by providing improved initial treatment estimates to supplement a physician's initial assessment. We apply k-means clustering to a dataset of within-subject Parkinson's medication changes-clinically assessed by the MDS-Unified Parkinson's Disease Rating Scale-III (MDS-UPDRS-III) and the PKG sensor for movement staging. A random forest classification model was then used to predict patients' cluster allocation based on their respective demographic information, MDS-UPDRS-III scores, and PKG time-series data. Clinically relevant clusters were partitioned by levodopa dose, medication administration frequency, and total levodopa equivalent daily dose-with the PKG providing similar symptomatic assessments to physician MDS-UPDRS-III scores. A random forest classifier trained on demographic information, MDS-UPDRS-III scores, and PKG time-series data was able to accurately classify subjects of the two most demographically similar clusters with an accuracy of 86.9%, an F1 score of 90.7%, and an AUC of 0.871. A model that relied solely on demographic information and PKG time-series data provided the next best performance with an accuracy of 83.8%, an F1 score of 88.5%, and an AUC of 0.831, hence further enabling fully remote assessments. These computational methods demonstrate the feasibility of using sensor-based data to cluster patients based on their medication responses with further potential to assist with medication recommendations.

Using Automated Machine Learning to Predict the Mortality of Patients With COVID-19: Prediction Model Development Study

BACKGROUND

During a pandemic, it is important for clinicians to stratify patients and decide who receives limited medical resources. Machine learning models have been proposed to accurately predict COVID-19 disease severity. Previous studies have typically tested only one machine learning algorithm and limited performance evaluation to area under the curve analysis. To obtain the best results possible, it may be important to test different machine learning algorithms to find the best prediction model.

OBJECTIVE

In this study, we aimed to use automated machine learning (autoML) to train various machine learning algorithms. We selected the model that best predicted patients' chances of surviving a SARS-CoV-2 infection. In addition, we identified which variables (ie, vital signs, biomarkers, comorbidities, etc) were the most influential in generating an accurate model.

METHODS

Data were retrospectively collected from all patients who tested positive for COVID-19 at our institution between March 1 and July 3, 2020. We collected 48 variables from each patient within 36 hours before or after the index time (ie, real-time polymerase chain reaction positivity). Patients were followed for 30 days or until death. Patients' data were used to build 20 machine learning models with various algorithms via autoML. The performance of machine learning models was measured by analyzing the area under the precision-recall curve (AUPCR). Subsequently, we established model interpretability via Shapley additive explanation and partial dependence plots to identify and rank variables that drove model predictions. Afterward, we conducted dimensionality reduction to extract the 10 most influential variables. AutoML models were retrained by only using these 10 variables, and the output models were evaluated against the model that used 48 variables.

RESULTS

Data from 4313 patients were used to develop the models. The best model that was generated by using autoML and 48 variables was the stacked ensemble model (AUPRC=0.807). The two best independent models were the gradient boost machine and extreme gradient boost models, which had an AUPRC of 0.803 and 0.793, respectively. The deep learning model (AUPRC=0.73) was substantially inferior to the other models. The 10 most influential variables for generating high-performing models were systolic and diastolic blood pressure, age, pulse oximetry level, blood urea nitrogen level, lactate dehydrogenase level, D-dimer level, troponin level, respiratory rate, and Charlson comorbidity score. After the autoML models were retrained with these 10 variables, the stacked ensemble model still had the best performance (AUPRC=0.791).

CONCLUSIONS

We used autoML to develop high-performing models that predicted the survival of patients with COVID-19. In addition, we identified important variables that correlated with mortality. This is proof of concept that autoML is an efficient, effective, and informative method for generating machine learning-based clinical decision support tools.

Real-Time Standard Analysis of Disease Investigation (SADI)-A Toolbox Approach to Inform Disease Outbreak Response

An incursion of an important exotic transboundary animal disease requires a prompt and intensive response. The routine analysis of up-to-date data, as near to real time as possible, is essential for the objective assessment of the patterns of disease spread or effectiveness of control measures and the formulation of alternative control strategies. In this paper, we describe the Standard Analysis of Disease Investigation (SADI), a toolbox for informing disease outbreak response, which was developed as part of New Zealand's biosecurity preparedness. SADI was generically designed on a web-based software platform, Integrated Real-time Information System (IRIS). We demonstrated the use of SADI for a hypothetical foot-and-mouth disease (FMD) outbreak scenario in New Zealand. The data standards were set within SADI, accommodating a single relational database that integrated the national livestock population data, outbreak data, and tracing data. We collected a well-researched, standardised set of 16 epidemiologically relevant analyses for informing the FMD outbreak response, including farm response timelines, interactive outbreak/network maps, stratified epidemic curves, estimated dissemination rates, estimated reproduction numbers, and areal attack rates. The analyses were programmed within SADI to automate the process to generate the reports at a regular interval (daily) using the most up-to-date data. Having SADI prepared in advance and the process streamlined for data collection, analysis and reporting would free a wider group of epidemiologists during an actual disease outbreak from solving data inconsistency among response teams, daily “number crunching,” or providing largely retrospective analyses. Instead, the focus could be directed into enhancing data collection strategies, improving data quality, understanding the limitations of the data available, interpreting the set of analyses, and communicating their meaning with response teams, decision makers and public in the context of the epidemic.

Artificial Intelligence (AI) Decision Support Tools

Artificial intelligence (AI) has made great contributions to the healthcare industry. However, its effect on medical diagnosis has not been well explored. Here, we examined a trial comparing the thinking process between a computer and a master in diagnosis at a clinical conference in Japan, with a focus on general diagnosis. Consequently, not only was AI unable to exhibit its thinking process, it also failed to include the final diagnosis. The following issues were highlighted: (1) input information to AI could not be weighted in order of importance for diagnosis; (2) AI could not deal with comorbidities (see Hickam’s dictum); (3) AI was unable to consider the timeline of the illness (depending on the tool); (4) AI was unable to consider patient context; (5) AI could not obtain input information by themselves. This comparison of the thinking process uncovered a future perspective on the use of diagnostic support tools.

Primary Care Access to an Online Decision Support Tool is Associated With Improvements in Some Aspects of Pediatric Migraine Care

OBJECTIVE

To evaluate whether primary care provider (PCP) access to an online decision support tool is associated with a change in evidence-based primary care medical management of pediatric migraine.

METHODS

In this prospective observational study, PCPs serving a target community were educated on the availability and use of an online clinical decision support tool that was developed to inform treatment of pediatric migraine. For 9 months before and after implementation of the decision tool, the proportions of children with migraine prescribed evidence-based and contraindicated medications by PCPs in the target region were monitored using electronic medical record query and statistically compared to these same proportions for patients in surrounding (control) regions. Rates of visits to the emergency department for migraine also were tracked pre- and postimplementation as an indirect measure of impact of the decision tool. Provider usage of the decision tool was monitored and summarized using web analytics.

RESULTS

Approximately half (56%) of target region PCPs used the online tool at least once over the project period. Relative to control regions and baseline trends, the proportion of children residing in the target region who were prescribed recommended abortive and preventive medications for treating migraine was statistically significantly higher following implementation of the tool. No significant changes to frequency of emergency care visits for migraine by youth in the target region were observed.

CONCLUSIONS

Availability to PCPs of an online decision support tool for pediatric migraine is associated with a modest change in some aspects of evidence-based medical care.

SpaceOAR© hydrogel rectal dose reduction prediction model: a decision support tool

Prostate cancer external beam radiation therapy can result in toxicity due to organ at risk (OAR) dose, potentially impairing quality of life. A polyethylene glycol-based spacer, SpaceOAR© hydrogel (SOH), implanted between prostate gland and rectum may significantly reduce dose received by the rectum and hence risk of rectal toxicity. SOH implant is not equally effective in all patients. Determining patients in which the implant will offer most benefit, in terms of rectal dose reduction, allows for effective management of SOH resources. Several factors have been shown to be correlated with reduction in rectal dose including distance between rectum and planning treatment volume (PTV), volume of rectum in the PTV, and change in rectum volume pre- to post-SOH. Several of these factors along with other pre-SOH CT metrics were able to predict reduction in rectal dose associated with SOH implant. Rectal V55Gy metric, was selected as the dose level of interest in the context of 60 Gy in 20 fraction treatment plans. Models were produced to predict change in RV55Gy and pre-SOH hydrogel RV55Gy. These models offered R-squared between 0.81 and 0.88 with statistical significance in each model. Applying an ω 1  = 3% lower limit of pre-SOH RV55 Gy and an ω 2  = 3.5% lower limit on change in RV55 Gy, retained 60% of patients experiencing the largest rectal dose reduction from the hydrogel. This may offer a clinically useful tool in deciding which patients should receive SOH implant given limited resources. Predictive models, nomograms, and a workflow diagram were produced for clinical management of SOH implant.

Decision aids to support decision-making in dementia care: a systematic review

OBJECTIVES

We aimed to critically evaluate decision aids developed for practitioners and caregivers when providing care for someone with dementia or for use by people with dementia themselves. Decision aids may be videos, booklets, or web-based tools that explicitly state the decision, provide information about the decision, and summarize options along with associated benefits and harms. This helps guide the decision maker through clarifying the values they place on the benefits or harms of the options.

DESIGN

We conducted a systematic review of peer-reviewed literature in electronic databases (CINAHL, The Cochrane Library, EMBASE, MEDLINE, and PsychINFO) in March 2018. Reference lists were searched for relevant papers and citations tracked. Data were synthesized with meta-analysis and narrative synthesis. Papers were included if they met the following criteria: 1) the focus of the paper was on the evaluation of a decision aid; 2) the decision aid was used in dementia care; and 3) the decision aid was aimed at professionals, people with dementia, or caregivers.

RESULTS

We identified 3618 studies, and 10 studies were included, covering three topics across six decision aids: 1) support with eating/feeding options, 2) place of care, and 3) goals of care. The mode of delivery and format of the decision aids varied and included paper-based, video-based, and audio-based decision aids. The decision aids were shown to be effective, increasing knowledge and the quality of communication. The meta-analysis demonstrated that decisions are effective in reducing decisional conflict among caregivers (standardized mean difference = -0.50, 95% confidence interval [ - 0.97, - 0.02]).

CONCLUSION

Decision aids offer a promising approach for providing support for decision-making in dementia care. People are often faced with more than one decision, and decisions are often interrelated. The decision aids identified in this review focus on single topics. There is a need for decision aids that cover multiple topics in one aid to reflect this complexity and better support caregivers.

Does a parenteral nutrition decision support system for total nutrients improve prescription procedure and neonatal growth?

Background and objectives: Parenteral nutrition (PN) is an integral part of the nutritional support of critically ill neonates in the intensive care units (ICU). The evaluation of a decision support system for total nutrients (DSSFTN) is of great importance for clinical practice. This study's aim was to evaluate the impact caused by implementation of a DSSFTN on PN support and neonatal growth. This pilot work was supported by the hospital PN team (PNT) in order to assess possible benefits stemming from the use of DSSFTN.Materials and methods: DSSFTN development is based on the incorporation of pharmaceutical and therapeutic protocols. Thirty-eight neonates were recruited. Inclusion criteria included: patients should (a) be hospitalized in ICU, (b) receive PN support at least for 15 days, (c) have birth weight 550-1600 g. One exclusion criterion was applied: patients should have no inborn error of metabolism. 15 doctors prescribed PN for two groups of neonates. PN was calculated by doctors for Group 1 (19 neonates) and respectively was calculated by the DSSFTN (and checked by doctors) for Group 2 (19 neonates). A questionnaire was completed later by doctors to evaluate DSSFTN.Results: The implementation of DSSFTN led to appropriate composition and administration of PN. Growth was not significantly different between the study groups. Compliance with guidelines was observed. DSSFTN ameliorated intercommunication among doctors.Conclusions: The implementation of DSSFTN enables health professionals to facilitate the complex task of prescribing. It ensures the consistency of PN prescriptions, as it leads to appropriate dosing in all nutrients. DSSFTN provides real-time PN interventions (clinical conditions and enteral amounts are included additionally) and minimizes exposure to human errors.

Implementing an Evidence-Based, Asthma Decision Support Tool for Children Younger Than 5 Years Old

INTRODUCTION

Asthma is underdiagnosed, particularly for children younger than 5 years old. Clinical practice guidelines have been shown to improve asthma diagnosis and management, but are underutilized. This evidence-based practice project aimed to develop, implement, and evaluate a three-page decision support tool (DST) to improve the asthma diagnosis process among children younger than 5 years old.

METHODS

This project used a pre-experimental design and was conducted in a pediatric primary care setting with a predominantly South Asian population. The authors analyzed the utilization of the DST as well as the end-users' perception of the tool.

RESULTS

Despite above-average results in the end-users' usability scale, the DST had poor utilization.

DISCUSSION

Implementation of the DST is recommended at similar pediatric primary care sites. The EBP Project team recommends translating the DST to the electronic health record and improving the roles of the champion.

Survey of Image Processing Techniques for Brain Pathology Diagnosis: Challenges and Opportunities

In recent years, a number of new products introduced to the global market combine intelligent robotics, artificial intelligence and smart interfaces to provide powerful tools to support professional decision making. However, while brain disease diagnosis from the brain scan images is supported by imaging robotics, the data analysis to form a medical diagnosis is performed solely by highly trained medical professionals. Recent advances in medical imaging techniques, artificial intelligence, machine learning and computer vision present new opportunities to build intelligent decision support tools to aid the diagnostic process, increase the disease detection accuracy, reduce error, automate the monitoring of patient's recovery, and discover new knowledge about the disease cause and its treatment. This article introduces the topic of medical diagnosis of brain diseases from the MRI based images. We describe existing, multi-modal imaging techniques of the brain's soft tissue and describe in detail how are the resulting images are analyzed by a radiologist to form a diagnosis. Several comparisons between the best results of classifying natural scenes and medical image analysis illustrate the challenges of applying existing image processing techniques to the medical image analysis domain. The survey of medical image processing methods also identified several knowledge gaps, the need for automation of image processing analysis, and the identification of the brain structures in the medical images that differentiate healthy tissue from a pathology. This survey is grounded in the cases of brain tumor analysis and the traumatic brain injury diagnoses, as these two case studies illustrate the vastly different approaches needed to define, extract, and synthesize meaningful information from multiple MRI image sets for a diagnosis. Finally, the article summarizes artificial intelligence frameworks that are built as multi-stage, hybrid, hierarchical information processing work-flows and the benefits of applying these models for medical diagnosis to build intelligent physician's aids with knowledge transparency, expert knowledge embedding, and increased analytical quality.

Use of seasonal forecasting to manage weather risk in ecological restoration

Ecological restoration has widely variable outcomes from successes to partial or complete failures, and there are diverse perspectives on the factors that influence the likelihood of success. However, not much is known about how these factors are perceived, and whether people's perceptions match realities. We surveyed 307 people involved in the restoration of native vegetation across Australia to identify their perceptions on the factors influencing the success of restoration projects. We found that weather (particularly drought and flooding) has realized impacts on the success of restoration projects, but is not perceived to be an important risk when planning new projects. This highlights the need for better recognition and management of weather risk in restoration and a potential role of seasonal forecasting. We used restoration case studies across Australia to assess the ability of seasonal forecasts provided by the Predictive Ocean Atmosphere Model for Australia, version M24 (POAMA-2) to detect unfavorable weather with sufficient skill and lead time to be useful for restoration projects. We found that rainfall and temperature variables in POAMA-2 predicted 88% of the weather issues encountered in restoration case studies apart from strong winds and cyclones. Of those restoration case studies with predictable weather issues, POAMA-2 had the forecast skill to predict the dominant or first-encountered issue in 67% of cases. We explored the challenges associated with uptake of forecast products through consultation with restoration practitioners and developed a prototype forecast product using a local case study. Integrating seasonal forecasting into decision making through (1) identifying risk management strategies during restoration planning, (2) accessing the forecast a month prior to revegetation activities, and (3) adapting decisions if extreme weather is forecasted, is expected to improve the establishment success of restoration.

Psychiatric service staff perceptions of implementing a shared decision-making tool: a process evaluation study

PURPOSE

Shared decision making, SDM, in psychiatric services, supports users to experience a greater sense of involvement in treatment, self-efficacy, autonomy and reduced coercion. Decision tools adapted to the needs of users have the potential to support SDM and restructure how users and staff work together to arrive at shared decisions. The aim of this study was to describe and analyse the implementation process of an SDM intervention for users of psychiatric services in Sweden.

METHOD

The implementation was studied through a process evaluation utilizing both quantitative and qualitative methods. In designing the process evaluation for the intervention, three evaluation components were emphasized: contextual factors, implementation issues and mechanisms of impact.

RESULTS

The study addresses critical implementation issues related to decision-making authority, the perceived decision-making ability of users and the readiness of the service to increase influence and participation. It also emphasizes the importance of facilitation, as well as suggesting contextual adaptations that may be relevant for the local organizations.

CONCLUSION

The results indicate that staff perceived the decision support tool as user-friendly and useful in supporting participation in decision-making, and suggest that such concrete supports to participation can be a factor in implementation if adequate attention is paid to organizational contexts and structures.

The Future of Health Is Self-Production and Co-Creation Based on Apomediative Decision Support

Cultural changes are needed in medicine if the benefits of technological advances are to benefit healthcare users. The Digital Health Manifesto of ‘medical futurist’ doctor Bertalan Meskó and ‘e-patient’ Dave deBronkart, The Patient Will See You Now by Eric Topol and The Patient as CEO by Robin Farmanfarmaian, are among the proliferating warnings of the approaching paradigm shift in medicine, resulting, above all, from technological advances that gives users independent access to exponentially increasing amounts of information about themselves. We question their messages only in suggesting they do not sufficiently shift the focus from ‘patient’ to ‘person’ and consequently fail to recognise the need for the credible, efficient, ethical and independent decision support that can ensure the ‘democratisation of knowledge’ is person empowering, not overpowering. Such decision support can ensure the ‘democratisation of decision,’ leading to higher quality decisions and fully-informed and preference-based consent to health provider actions. The coming paradigm will therefore be characterised by apomediative (‘direct-to-consumer’) decision support tools, engaged with by the person in the community to help them make health production decisions for themselves (including whether to consult a healthcare professional or provider), as well as intermediative (‘direct-from-clinician’) tools, delivered by a health professional in a ‘shared decision making’ or ‘co-creation of health’ process. This vision paper elaborates on the implementation of these preference-sensitive decision support tools through the technique of Multi-Criteria Decision Analysis.

The first steps in the evaluation of a "black-box" decision support tool: a protocol and feasibility study for the evaluation of Watson for Oncology

BACKGROUND AND AIM

Medical specialists aim to provide evidence-based care based on the most recent scientific insights, but with the ongoing expansion of medical literature it seems unfeasible to remain updated. "Black-box" decision support tools such as Watson for Oncology (Watson) are gaining attention as they offer a promising opportunity to conquer this challenging issue, but it is not known if the advice given is congruent with guidelines or clinically valid in other settings. We present a protocol for the content evaluation of black-box decision support tools and a feasibility study to test the content and usability of Watson using this protocol.

METHODS

The protocol consists of developing synthetic patient cases based on Dutch guidelines and expert opinion, entering the synthetic cases into Watson and Oncoguide, noting the response of each system and evaluating the result using a cross-tabulation scoring system resulting in a score range of -12 to +12. Treatment options that were not recommended according to the Dutch guideline were labeled with a "red flag" if Watson recommended it, and an "orange flag" if Watson suggested it for consideration. To test the feasibility of applying the protocol, we developed synthetic patient cases for the adjuvant treatment of stage I to stage III colon cancer based on relevant patient, clinical and tumor characteristics and followed our protocol. Additionally, for the feasibility study we also compared the recommendations from the NCCN guideline with Watson's advice, and evaluated usability by a cognitive walkthrough method.

RESULTS

In total, we developed 190 synthetic patient cases (stage I: n=8; stage II: n=110; and stage III: n=72). Overall concordance scores per case for Watson versus Oncoguide ranged from a minimum score of -4 (n=6) to a maximum score of+12 (n=17) and from -4 (n=9) to +12 (n=24) for Watson versus the NCCN guidelines). In total, 69 cases (36%) were labeled with red flags, 96 cases (51%) with orange flags and 25 cases (13%) without flags. For the comparison of Watson with the NCCN guidelines, no red or orange flags were identified.

CONCLUSIONS

We developed a research protocol for the evaluation of a black-box decision support tool, which proved useful and usable in testing the content and usability of Watson. Overall concordance scores ranged considerably between synthetic cases for both comparisons between Watson versus Oncoguide and Watson versus NCCN. Non-concordance is partially attributable to guideline differences between the United States and The Netherlands. This implies that further adjustments and localization are required before implementation of Watson outside the United States.

RELEVANCE FOR PATIENTS

This study describes the first steps of content evaluation of a decision support tool before implementation in daily oncological patient care. The ultimate goal of the incorporation of decision support tools in daily practice is to improve personalized medicine and quality of care.

Pharmacogenetic Decision Support Tools: A New Paradigm for Late-Life Depression?

Clinicians still employ a "trial-and-error" approach to optimizing treatment regimens for late-life depression (LLD). With LLD affecting a significant and growing segment of the population, and with only about half of older adults responsive to antidepressant therapy, there is an urgent need for a better treatment paradigm. Pharmacogenetic decision support tools (DSTs), which are emerging technologies that aim to provide clinically actionable information based on a patient's genetic profile, offer a promising solution. Dozens of DSTs have entered the market in the past 15 years, but with varying level of empirical evidence to support their value. In this clinical review, we provide a critical analysis of the peer-reviewed literature on DSTs for major depression management. We then discuss clinical considerations for the use of these tools in treating LLD, including issues related to test interpretation, timing, and patient perspectives. In adult populations, newer generation DSTs show promise for the treatment of major depression. However, there are no primary clinical trials in LLD cohorts. Independent and comparative clinical trials are needed.

Preference-Sensitive Apomediative Decision Support Is Key to Facilitating Self-Produced Health

In the health capital model, the main function of health services is not to produce health, but to support the person in their self-production investments. In the health context there are three types of decision support tools, depending on the role of the provider (e.g. clinician) and person. Non-mediative tools are designed to help the clinician decide what is best for the patient. Intermediative Patient Decision Aids are designed to help the clinician and patient decide together, in an encounter, what is best for the patient. Apomediative Personalised Decision Support Tools are designed to help the person decide what is best for themselves, including whether to seek a professional consultation and/or to prepare for, and engage in, an intermediative consultation. Only preference-sensitive apomediative support tools ensure that the key requirements of self-produced health are met, along with legally informed and preference-based consent to any subsequent provider action. The desirable form of apomediative support is a publicly accessible, direct-to-citizen, provider-independent, multi-criteria analysis-based decision support of the sort available in many other areas of self-production. Which (UK), Tænk (Denmark), Choice (Australia) and numerous other comparison magazines and websites provide independent multi-criterial support for decisions on, for example, which food and transport to buy to self-produce nutrition and movement. A personalised decision support tool for the statin decision is provided as illustration: Should I go to my general practitioner and ask for a statin prescription or go to discuss taking statins, in the light of the preliminary opinion of the tool?

Development and conceptual validation of a questionnaire to help contraceptive choice: CHLOE (Contraception: HeLping for wOmen's choicE)

OBJECTIVE

The aim of this research was to develop a questionnaire to facilitate choice of the most appropriate contraceptive method for individual women.

METHODS

A literature review was conducted to identify key aspects influencing contraceptive choice and inform development of a questionnaire for online completion. Questionnaire development was overseen by a steering committee consisting of eight gynaecologists from across Europe. The initial draft underwent conceptual validation through cognitive debriefing interviews with six native English-speaking women. A qualitative content analysis was conducted to accurately identify potential issues and areas for questionnaire improvement. A revised version of the questionnaire then underwent face-to-face and online evaluation by 115 international gynaecologists/obstetricians with expertise in contraception, prior to development of a final version.

RESULTS

The final conceptually validated Contraception: HeLping for wOmen's choicE (CHLOE) questionnaire takes ≤10 min to complete and includes three sections to elicit general information about the individual, the health conditions that might influence contraceptive choice, and the woman's needs and preferences that might influence contraceptive choice. The questionnaire captures the core aspects of personalisation, efficacy and safety, identified as key attributes influencing contraceptive choice, and consists of 24 closed-ended questions for online completion prior to a health care provider (HCP) consultation. The HCP receives a summary of the responses.

CONCLUSION

The CHLOE questionnaire has been developed to help women choose the contraception that best suits their needs and situation while optimising the HCP's time.

Development of a generally applicable morphokinetic algorithm capable of predicting the implantation potential of embryos transferred on Day 3

STUDY QUESTION

Can a generally applicable morphokinetic algorithm suitable for Day 3 transfers of time-lapse monitored embryos originating from different culture conditions and fertilization methods be developed for the purpose of supporting the embryologist's decision on which embryo to transfer back to the patient in assisted reproduction?

SUMMARY ANSWER

The algorithm presented here can be used independently of culture conditions and fertilization method and provides predictive power not surpassed by other published algorithms for ranking embryos according to their blastocyst formation potential.

WHAT IS KNOWN ALREADY

Generally applicable algorithms have so far been developed only for predicting blastocyst formation. A number of clinics have reported validated implantation prediction algorithms, which have been developed based on clinic-specific culture conditions and clinical environment. However, a generally applicable embryo evaluation algorithm based on actual implantation outcome has not yet been reported.

STUDY DESIGN, SIZE, DURATION

Retrospective evaluation of data extracted from a database of known implantation data (KID) originating from 3275 embryos transferred on Day 3 conducted in 24 clinics between 2009 and 2014. The data represented different culture conditions (reduced and ambient oxygen with various culture medium strategies) and fertilization methods (IVF, ICSI). The capability to predict blastocyst formation was evaluated on an independent set of morphokinetic data from 11 218 embryos which had been cultured to Day 5.

PARTICIPANTS/MATERIALS, SETTING, METHODS

The algorithm was developed by applying automated recursive partitioning to a large number of annotation types and derived equations, progressing to a five-fold cross-validation test of the complete data set and a validation test of different incubation conditions and fertilization methods. The results were expressed as receiver operating characteristics curves using the area under the curve (AUC) to establish the predictive strength of the algorithm.

MAIN RESULTS AND THE ROLE OF CHANCE

By applying the here developed algorithm (KIDScore), which was based on six annotations (the number of pronuclei equals 2 at the 1-cell stage, time from insemination to pronuclei fading at the 1-cell stage, time from insemination to the 2-cell stage, time from insemination to the 3-cell stage, time from insemination to the 5-cell stage and time from insemination to the 8-cell stage) and ranking the embryos in five groups, the implantation potential of the embryos was predicted with an AUC of 0.650. On Day 3 the KIDScore algorithm was capable of predicting blastocyst development with an AUC of 0.745 and blastocyst quality with an AUC of 0.679. In a comparison of blastocyst prediction including six other published algorithms and KIDScore, only KIDScore and one more algorithm surpassed an algorithm constructed on conventional Alpha/ESHRE consensus timings in terms of predictive power.

LIMITATIONS, REASONS FOR CAUTION

Some morphological assessments were not available and consequently three of the algorithms in the comparison were not used in full and may therefore have been put at a disadvantage. Algorithms based on implantation data from Day 3 embryo transfers require adjustments to be capable of predicting the implantation potential of Day 5 embryo transfers. The current study is restricted by its retrospective nature and absence of live birth information. Prospective Randomized Controlled Trials should be used in future studies to establish the value of time-lapse technology and morphokinetic evaluation.

WIDER IMPLICATIONS OF THE FINDINGS

Algorithms applicable to different culture conditions can be developed if based on large data sets of heterogeneous origin.

STUDY FUNDING/COMPETING INTEREST(S)

This study was funded by Vitrolife A/S, Denmark and Vitrolife AB, Sweden. B.M.P.’s company BMP Analytics is performing consultancy for Vitrolife A/S. M.B. is employed at Vitrolife A/S. M.M.’s company ilabcomm GmbH received honorarium for consultancy from Vitrolife AB. D.K.G. received research support from Vitrolife AB.

Shared Decision Making and Choice for Elective Surgical Care: A Systematic Review

OBJECTIVE

Shared decision making (SDM), an integrative patient-provider communication process emphasizing discussion of scientific evidence and patient/family values, may improve quality care delivery, promote evidence-based practice, and reduce overuse of surgical care. Little is known, however, regarding SDM in elective surgical practice. The purpose of this systematic review is to synthesize findings of studies evaluating use and outcomes of SDM in elective surgery.

DATA SOURCES

PubMed, Cochrane CENTRAL, EMBASE, CINAHL, and SCOPUS electronic databases.

REVIEW METHODS

We searched for English-language studies (January 1, 1990, to August 9, 2015) evaluating use of SDM in elective surgical care where choice for surgery could be ascertained. Identified studies were independently screened by 2 reviewers in stages of title/abstract and full-text review. We abstracted data related to population, study design, clinical dilemma, use of SDM, outcomes, treatment choice, and bias.

RESULTS

Of 10,929 identified articles, 24 met inclusion criteria. The most common area studied was spine (7 of 24), followed by joint (5 of 24) and gynecologic surgery (4 of 24). Twenty studies used decision aids or support tools, including modalities that were multimedia/video (13 of 20), written (3 of 20), or personal coaching (4 of 20). Effect of SDM on preference for surgery was mixed across studies, showing a decrease in surgery (9 of 24), no difference (8 of 24), or an increase (1 of 24). SDM tended to improve decision quality (3 of 3) as well as knowledge or preparation (4 of 6) while decreasing decision conflict (4 of 6).

CONCLUSION

SDM reduces decision conflict and improves decision quality for patients making choices about elective surgery. While net findings show that SDM may influence patients to choose surgery less often, the impact of SDM on surgical utilization cannot be clearly ascertained.

Stage-independent, single lead EEG sleep spindle detection using the continuous wavelet transform and local weighted smoothing

Sleep spindles are critical in characterizing sleep and have been associated with cognitive function and pathophysiological assessment. Typically, their detection relies on the subjective and time-consuming visual examination of electroencephalogram (EEG) signal(s) by experts, and has led to large inter-rater variability as a result of poor definition of sleep spindle characteristics. Hitherto, many algorithmic spindle detectors inherently make signal stationarity assumptions (e.g., Fourier transform-based approaches) which are inappropriate for EEG signals, and frequently rely on additional information which may not be readily available in many practical settings (e.g., more than one EEG channels, or prior hypnogram assessment). This study proposes a novel signal processing methodology relying solely on a single EEG channel, and provides objective, accurate means toward probabilistically assessing the presence of sleep spindles in EEG signals. We use the intuitively appealing continuous wavelet transform (CWT) with a Morlet basis function, identifying regions of interest where the power of the CWT coefficients corresponding to the frequencies of spindles (11–16 Hz) is large. The potential for assessing the signal segment as a spindle is refined using local weighted smoothing techniques. We evaluate our findings on two databases: the MASS database comprising 19 healthy controls and the DREAMS sleep spindle database comprising eight participants diagnosed with various sleep pathologies. We demonstrate that we can replicate the experts' sleep spindles assessment accurately in both databases (MASS database: sensitivity: 84%, specificity: 90%, false discovery rate 83%, DREAMS database: sensitivity: 76%, specificity: 92%, false discovery rate: 67%), outperforming six competing automatic sleep spindle detection algorithms in terms of correctly replicating the experts' assessment of detected spindles.

Shared decision making in type 2 diabetes with a support decision tool that takes into account clinical factors, the intensity of treatment and patient preferences: design of a cluster randomised (OPTIMAL) trial

BACKGROUND

No more than 10-15% of type 2 diabetes mellitus (T2DM) patients achieve all treatment goals regarding glycaemic control, lipids and blood pressure. Shared decision making (SDM) should increase that percentage; however, not all support decision tools are appropriate. Because the ADDITION-Europe study demonstrated two (almost) equally effective treatments but with slightly different intensities, it may be a good starting point to discuss with the patients their diabetes treatment, taking into account both the intensity of treatment, clinical factors and patients' preferences. We aim to evaluate whether such an approach increases the proportion of patients that achieve all three treatment goals.

METHODS

In a cluster-randomised trial including 40 general practices, that participated until 2009 in the ADDITION Study, 150 T2DM patients 60-80 years, known with T2DM for 8-15 years, will be included. Practices are randomised a second time, i.e. intervention practices in the ADDITION study could be control practices in the current study and vice versa. For the GPs from the intervention group a 2-hour training in SDM was developed as well as a decision support tool to be used during the consultation. GPs plan the first visit with the patients to decide on the intensity of the treatment, personalised targets and the priorities of treatment. The control group will continue with the treatment they were allocated to in the ADDITION study.

FOLLOW-UP

24 months. The primary outcome is the proportion of patients who achieve all three treatment goals. Secondary outcomes are the proportion of patients who achieve five treatment goals (HbA1c, blood pressure, total cholesterol, body weight, not smoking), evaluation of the SDM process (SDM-Q9 and CPS), satisfaction with the treatment (DTSQ), wellbeing and quality of life (W-BQ12, ADD QoL-19), health status (SF-36, EQ-5D) and coping (DCMQ). The proportions of achieved treatment goals will be compared between both groups. For the secondary outcomes mixed models will be used. The Medical Research Ethics Committee of the University Medical Centre Utrecht has approved the study protocol (Protocol number: 11-153).

DISCUSSION

This trial will provide evidence whether an intervention with a multi-faceted decision support tool increases the proportion of achieved personalised goals in type 2 diabetes patients.

TRIAL REGISTRATION

NCT02285881, November 4, 2014.

A method for calculating minimum biodiversity offset multipliers accounting for time discounting, additionality and permanence

Biodiversity offsetting, which means compensation for ecological and environmental damage caused by development activity, has recently been gaining strong political support around the world. One common criticism levelled at offsets is that they exchange certain and almost immediate losses for uncertain future gains. In the case of restoration offsets, gains may be realized after a time delay of decades, and with considerable uncertainty. Here we focus on offset multipliers, which are ratios between damaged and compensated amounts (areas) of biodiversity. Multipliers have the attraction of being an easily understandable way of deciding the amount of offsetting needed. On the other hand, exact values of multipliers are very difficult to compute in practice if at all possible. We introduce a mathematical method for deriving minimum levels for offset multipliers under the assumption that offsetting gains must compensate for the losses (no net loss offsetting). We calculate absolute minimum multipliers that arise from time discounting and delayed emergence of offsetting gains for a one-dimensional measure of biodiversity. Despite the highly simplified model, we show that even the absolute minimum multipliers may easily be quite large, in the order of dozens, and theoretically arbitrarily large, contradicting the relatively low multipliers found in literature and in practice. While our results inform policy makers about realistic minimal offsetting requirements, they also challenge many current policies and show the importance of rigorous models for computing (minimum) offset multipliers. The strength of the presented method is that it requires minimal underlying information. We include a supplementary spreadsheet tool for calculating multipliers to facilitate application.

A systematic review of shared decision making interventions in chronic conditions: a review protocol

BACKGROUND

Chronic conditions are a major source of morbidity, mortality and cost worldwide. Shared decision making is one way to improve care for patients with chronic conditions. Although it has been widely studied, the effect of shared decision making in the context of chronic conditions is unknown.

METHODS/DESIGN

We will perform a systematic review with the objective of determining the effectiveness of shared decision making interventions for persons diagnosed with chronic conditions. We will search the following databases for relevant articles: PubMed, Scopus, Ovid MEDLINE, Ovid EMBASE, Ovid EBM Reviews CENTRAL, CINAHL, and Ovid PsycInfo. We will also search clinical trial registries and contact experts in the field to identify additional studies. We will include randomized controlled trials studying shared decision making interventions in patients with chronic conditions who are facing an actual decision. Shared decision making interventions will be defined as any intervention aiming to facilitate or improve patient and/or clinician engagement in a decision making process. We will describe all studies and assess their quality. After adjusting for missing data, we will analyze the effect of shared decision making interventions on outcomes in chronic conditions overall and stratified by condition. We will evaluate outcomes according to an importance ranking informed by a variety of stakeholders. We will perform several exploratory analyses including the effect of author contact on the estimates of effect.

DISCUSSION

We anticipate that this systematic review may have some limitations such as heterogeneity and imprecision; however, the results will contribute to improving the quality of care for individuals with chronic conditions and facilitate a process that allows decision making that is most consistent with their own values and preferences.

TRIAL REGISTRATION

PROSPERO Registration Number: CRD42013005784.

Personalized decision support in type 2 diabetes mellitus: current evidence and future directions

The management of type 2 diabetes comprises a complex series of medical decisions regarding goals of care, self-care behaviors, and medical treatments. The quality of these medical decisions is critical to determining whether an individual diabetes patient is treated appropriately, overtreated, or undertreated. It is hypothesized that the quality of these medical decisions can be enhanced by personalized decision support tools that summarize patient clinical characteristics, treatment preferences, and ancillary data at the point of care. We describe the current state of personalized diabetes decision support on the basis of 13 recently described tools. Three tools provided support for personalized decisions based on preferences, while the remaining 10 provided support for treatment decisions designed to achieve standard diabetes goals. For the tools that supported personalized decisions, patient participation in medical decisions improved. Future decision support tools must be designed to account for both clinical characteristics and patient preferences.