The clinical decision analysis using decision tree

Markov models for clinical decision-making in radiation oncology: A systematic review

The intrinsic stochasticity of patients' response to treatment is a major consideration for clinical decision-making in radiation therapy. Markov models are powerful tools to capture this stochasticity and render effective treatment decisions. This paper provides an overview of the Markov models for clinical decision analysis in radiation oncology. A comprehensive literature search was conducted within MEDLINE using PubMed, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Only studies published from 2000 to 2023 were considered. Selected publications were summarized in two categories: (i) studies that compare two (or more) fixed treatment policies using Monte Carlo simulation and (ii) studies that seek an optimal treatment policy through Markov Decision Processes (MDPs). Relevant to the scope of this study, 61 publications were selected for detailed review. The majority of these publications (n = 56) focused on comparative analysis of two or more fixed treatment policies using Monte Carlo simulation. Classifications based on cancer site, utility measures and the type of sensitivity analysis are presented. Five publications considered MDPs with the aim of computing an optimal treatment policy; a detailed statement of the analysis and results is provided for each work. As an extension of Markov model-based simulation analysis, MDP offers a flexible framework to identify an optimal treatment policy among a possibly large set of treatment policies. However, the applications of MDPs to oncological decision-making have been understudied, and the full capacity of this framework to render complex optimal treatment decisions warrants further consideration.

The Machine Learning Model for Predicting Inadequate Bowel Preparation Before Colonoscopy: A Multicenter Prospective Study

INTRODUCTION

Colonoscopy is a critical diagnostic tool for colorectal diseases; however, its effectiveness depends on adequate bowel preparation (BP). This study aimed to develop a machine learning predictive model based on Chinese adults for inadequate BP.

METHODS

A multicenter prospective study was conducted on adult outpatients undergoing colonoscopy from January 2021 to May 2023. Data on patient characteristics, comorbidities, medication use, and BP quality were collected. Logistic regression and 4 machine learning models (support vector machines, decision trees, extreme gradient boosting, and bidirectional projection network) were used to identify risk factors and predict inadequate BP.

RESULTS

Of 3,217 patients, 21.14% had inadequate BP. The decision trees model demonstrated the best predictive capacity with an area under the receiver operating characteristic curve of 0.80 in the validation cohort. The risk factors at the nodes included body mass index, education grade, use of simethicone, diabetes, age, history of inadequate BP, and longer interval.

DISCUSSION

The decision trees model we created and the identified risk factors can be used to identify patients at higher risk of inadequate BP before colonoscopy, for whom more polyethylene glycol or auxiliary medication should be used.

Predictive model for identifying mild cognitive impairment in patients with type 2 diabetes mellitus: A CHAID decision tree analysis

BACKGROUND

As the population ages, mild cognitive impairment (MCI) and type 2 diabetes mellitus (T2DM) become common conditions that often coexist. Evidence has shown that MCI could lead to reduced treatment compliance, medication management, and self-care ability in T2DM patients. Therefore, early identification of those with increased risk of MCI is crucial from a preventive perspective. Given the growing utilization of decision trees in prediction of health-related outcomes, this study aimed to identify MCI in T2DM patients using the decision tree approach.

METHODS

This hospital-based case-control study was performed in the Endocrinology Department of Xiangya Hospital affiliated to Central South University between March 2021 and December 2022. MCI was defined based on the Petersen criteria. Demographic characteristics, lifestyle factors, and T2DM-related information were collected. The study sample was randomly divided into the training and validation sets in a 7:3 ratio. Univariate and multivariate analyses were performed, and a decision tree model was established using the chi-square automatic interaction detection (CHAID) algorithm to identify key predictor variables associated with MCI. The area under the curve (AUC) value was used to evaluate the performance of the established decision tree model, and the performance of multivariate regression model was also evaluated for comparison.

RESULTS

A total of 1001 participants (705 in the training set and 296 in the validation set) were included in this study. The mean age of participants in the training and validation sets was 60.2  ±  10.3 and 60.4  ±  9.5 years, respectively. There were no significant differences in the characteristics between the training and validation sets (p > .05). The CHAID decision tree analysis identified six key predictor variables associated with MCI, including age, educational level, household income, regular physical activity, diabetic nephropathy, and diabetic retinopathy. The established decision tree model had 15 nodes composed of 4 layers, and age is the most significant predictor variable. It performed well (AUC = .75 [95% confidence interval (CI): .71-.78] and .67 [95% CI: .61-.74] in the training and validation sets, respectively), was internally validated, and had comparable predictive value compared to the multivariate logistic regression model (AUC = .76 [95% CI: .72-.80] and .69 [95% CI: .62-.75] in the training and validation sets, respectively).

CONCLUSION

The established decision tree model based on age, educational level, household income, regular physical activity, diabetic nephropathy, and diabetic retinopathy performed well with comparable predictive value compared to the multivariate logistic regression model and was internally validated. Due to its superior classification accuracy and simple presentation as well as interpretation of collected data, the decision tree model is more recommended for the prediction of MCI in T2DM patients in clinical practice.

Case studies of clinical decision-making through prescriptive models based on machine learning

BACKGROUND

The development of computational methodologies to support clinical decision-making is of vital importance to reduce morbidity and mortality rates. Specifically, prescriptive analytic is a promising area to support decision-making in the monitoring, treatment and prevention of diseases. These aspects remain a challenge for medical professionals and health authorities.

MATERIALS AND METHODS

In this study, we propose a methodology for the development of prescriptive models to support decision-making in clinical settings. The prescriptive model requires a predictive model to build the prescriptions. The predictive model is developed using fuzzy cognitive maps and the particle swarm optimization algorithm, while the prescriptive model is developed with an extension of fuzzy cognitive maps that combines them with genetic algorithms. We evaluated the proposed approach in three case studies related to monitoring (warfarin dose estimation), treatment (severe dengue) and prevention (geohelminthiasis) of diseases.

RESULTS

The performance of the developed prescriptive models demonstrated the ability to estimate warfarin doses in coagulated patients, prescribe treatment for severe dengue and generate actions aimed at the prevention of geohelminthiasis. Additionally, the predictive models can predict coagulation indices, severe dengue mortality and soil-transmitted helminth infections.

CONCLUSIONS

The developed models performed well to prescribe actions aimed to monitor, treat and prevent diseases. This type of strategy allows supporting decision-making in clinical settings. However, validations in health institutions are required for their implementation.

Assessment of a venous thromboembolism prophylaxis shared decision-making intervention (DASH-TOP) using the decisional conflict scale: a mixed-method study

BACKGROUND

Venous thromboembolism (VTE) in pregnancy is a major cause of maternal morbidity and death. The use of low-molecular-weight heparin (LMWH), despite being the standard of care to prevent VTE, comes with some challenges. Shared decision-making (SDM) interventions are recommended to support patients and clinicians in making preference-sensitive decisions. The quality of the SDM process has been widely assessed with the decisional conflict scale (DCS). Our aim is to report participants' perspectives of each of the components of an SDM intervention (DASH-TOP) in relation to the different subscales of the DCS.

METHODS

Design: A convergent, parallel, mixed-methods design.

PARTICIPANTS

The sample consisted of 22 health care professionals, students of an Applied Clinical Research in Health Sciences (ICACS) master program.

INTERVENTION

We randomly divided the participants in three groups: Group 1 received one component (evidence -based information), Group 2 received two components (first component and value elicitation exercises), and Group 3 received all three components (the first two and a decision analysis recommendation) of the SDM intervention.

ANALYSIS

For the quantitative strand, we used a non-parametric test to analyze the differences in the DCS subscales between the three groups. For the qualitative strand, we conducted a content analysis using the decisional conflict domains to deductively categorize the responses.

RESULTS

Groups that received more intervention components experienced less conflict and better decision-making quality, although the differences between groups were not statistically significant. The decision analysis recommendation improved the efficacy with the decision-making process, however there are some challenges when implementing it in clinical practice. The uncertainty subscale showed a high decisional conflict for all three groups; contributing factors included low certainty of the evidence-based information provided and a perceived small effect of the drug to reduce the risk of a VTE event.

CONCLUSIONS

The DASH-TOP intervention reduced decisional conflict in the decision -making process, with decision analysis being the most effective component to improve the quality of the decision. There is a need for more implementation research to improve the delivery of SDM interventions in the clinical encounter.

Comparison of decision tree with common machine learning models for prediction of biguanide and sulfonylurea poisoning in the United States: an analysis of the National Poison Data System

BACKGROUND

Biguanides and sulfonylurea are two classes of anti-diabetic medications that have commonly been prescribed all around the world. Diagnosis of biguanide and sulfonylurea exposures is based on history taking and physical examination; thus, physicians might misdiagnose these two different clinical settings. We aimed to conduct a study to develop a model based on decision tree analysis to help physicians better diagnose these poisoning cases.

METHODS

The National Poison Data System was used for this six-year retrospective cohort study.The decision tree model, common machine learning models multi layers perceptron, stochastic gradient descent (SGD), Adaboosting classiefier, linear support vector machine and ensembling methods including bagging, voting and stacking methods were used. The confusion matrix, precision, recall, specificity, f1-score, and accuracy were reported to evaluate the model's performance.

RESULTS

Of 6183 participants, 3336 patients (54.0%) were identified as biguanides exposures, and the remaining were those with sulfonylureas exposures. The decision tree model showed that the most important clinical findings defining biguanide and sulfonylurea exposures were hypoglycemia, abdominal pain, acidosis, diaphoresis, tremor, vomiting, diarrhea, age, and reasons for exposure. The specificity, precision, recall, f1-score, and accuracy of all models were greater than 86%, 89%, 88%, and 88%, respectively. The lowest values belong to SGD model. The decision tree model has a sensitivity (recall) of 93.3%, specificity of 92.8%, precision of 93.4%, f1_score of 93.3%, and accuracy of 93.3%.

CONCLUSION

Our results indicated that machine learning methods including decision tree and ensembling methods provide a precise prediction model to diagnose biguanides and sulfonylureas exposure.

A Clinical Decision Tree to Support Keratoconus Patients Considering Corneal Cross-Linking Combined with Refractive Treatment

BACKGROUND

To develop a fast and frugal decision tree to identify keratoconus patients most likely to benefit visually from the combination of corneal cross-linking (CXL) with topography-guided photorefractive keratectomy ("CXL plus").

PATIENTS AND METHODS

The outcome of interest was an improvement in uncorrected distance visual acuity (UDVA) by at least two lines at the 12-month follow-up. Preoperative and 12-month follow-up data from patients who received CXL plus (n = 96) and CXL only (n = 96) were used in a recursive partitioning approach to construct a frugal tree with three variables (corneal thickness [>/< 430 um], patient interest in CXL plus [yes/no], and tomographic cylinder [</> 3 D]). In addition, we estimated the probability of the outcome from a multivariate logistic regression model for each combination of variables used in the decision tree.

RESULTS

In the complete sample, 101/192 (52.6%) patients improved by at least two lines at the 12-month follow-up. Patients affirmative in all three answers had a 75.6% (34/45) probability of gaining at least two lines of improvement in UDVA by CXL plus. The statistical model estimated a 66.0% probability for a successful outcome.

CONCLUSION

A fast and frugal tree consisting of three variables can be used to select a patient group with a high likelihood to benefit from CXL plus. The tree is useful in the preoperative counseling of keratoconus patients contemplating the CXL plus option, an intervention that is not fully covered by many health insurances.

Teaching the science of uncertainty

As we increasingly acknowledge the ubiquitous nature of uncertainty in clinical practice (Meyer AN, Giardina TD, Khawaja L, Singh H. Patient and clinician experiences of uncertainty in the diagnostic process: current understanding and future directions. Patient Educ Counsel 2021;104:2606-15; Han PK, Klein WM, Arora NK. Varieties of uncertainty in health care: a conceptual taxonomy. Med Decis Making 2011;31:828-38) and strive to better define this entity (Lee C, Hall K, Anakin M, Pinnock R. Towards a new understanding of uncertainty in medical education. J Eval Clin Pract 2020; Bhise V, Rajan SS, Sittig DF, Morgan RO, Chaudhary P, Singh H. Defining and measuring diagnostic uncertainty in medicine: a systematic review. J Gen Intern Med 2018;33:103-15), as educators we should also design, implement, and evaluate curricula addressing clinical uncertainty. Although frequently encountered, uncertainty is often implicitly referred to rather than explicitly discussed (Gärtner J, Berberat PO, Kadmon M, Harendza S. Implicit expression of uncertainty - suggestion of an empirically derived framework. BMC Med Educ 2020;20:83). Increasing explicit discussion of - and comfort with -uncertainty has the potential to improve diagnostic reasoning and accuracy and improve patient care (Dunlop M, Schwartzstein RM. Reducing diagnostic error in the intensive care unit. Engaging. Uncertainty when teaching clinical reasoning. Scholar;1:364-71). Discussion of both diagnostic and prognostic uncertainty with patients is central to shared decision-making in many contexts as well, (Simpkin AL, Armstrong KA. Communicating uncertainty: a narrative review and framework for future research. J Gen Intern Med 2019;34:2586-91) from the outpatient setting to the inpatient setting, and from undergraduate medical education (UME) trainees to graduate medical education (GME) trainees. In this article, we will explore the current status of how the science of uncertainty is taught from the UME curriculum to the GME curriculum, and describe strategies how uncertainty can be explicitly discussed for all levels of trainees.

Predictors of spinal trauma care and outcomes in a resource-constrained environment: a decision tree analysis of spinal trauma surgery and outcomes in Tanzania

OBJECTIVE

The burden of spinal trauma in low- and middle-income countries (LMICs) is immense, and its management is made complex in such resource-restricted settings. Algorithmic evidence-based management is cost-prohibitive, especially with respect to spinal implants, while perioperative care is work-intensive, making overall care dependent on multiple constraints. The objective of this study was to identify determinants of decision-making for surgical intervention, improvement in function, and in-hospital mortality among patients experiencing acute spinal trauma in resource-constrained settings.

METHODS

This study was a retrospective analysis of prospectively collected data in a cohort of patients with spinal trauma admitted to a tertiary referral hospital center in Dar es Salam, Tanzania. Data on demographic, clinical, and treatment characteristics were collected as part of a quality improvement neurotrauma registry. Outcome measures were surgical intervention, American Spinal Injury Association (ASIA) Impairment Scale (AIS) grade improvement, and in-hospital mortality, based on existing treatment protocols. Univariate analyses of demographic and clinical characteristics were performed for each outcome of interest. Using the variables associated with each outcome, a machine learning algorithm-based regression nonparametric decision tree model utilizing a bootstrapping method was created and the accuracy of the three models was estimated.

RESULTS

Two hundred eighty-four consecutively admitted patients with acute spinal trauma were included over a period of 33 months. The median age was 34 (IQR 26-43) years, 83.8% were male, and 50.7% had experienced injury in a motor vehicle accident. The median time to hospital admission after injury was 2 (IQR 1-6) days; surgery was performed after a further median delay of 22 (IQR 13-39) days. Cervical spine injury comprised 38.4% of the injuries. Admission AIS grades were A in 48.9%, B in 16.2%, C in 8.5%, D in 9.5%, and E in 16.6%. Nearly half (45.1%) of the patients underwent surgery, 12% had at least one functional improvement in AIS grade, and 11.6% died in the hospital. Determinants of surgical intervention were age ≤ 30 years, spinal injury level, admission AIS grade, delay in arrival to the referral hospital, undergoing MRI, and type of insurance; admission AIS grade, delay to arrival to the hospital, and injury level for functional improvement; and delay to arrival, injury level, delay to surgery, and admission AIS grade for in-hospital mortality. The best accuracies for the decision tree models were 0.62, 0.34, and 0.93 for surgery, AIS grade improvement, and in-hospital mortality, respectively.

CONCLUSIONS

Operative intervention and functional improvement after acute spinal trauma in this tertiary referral hospital in an LMIC environment were low and inconsistent, which suggests that nonclinical factors exist within complex resource-driven decision-making frameworks. These nonclinical factors are highlighted by the authors' results showing clinical outcomes and in-hospital mortality were determined by natural history, as evidenced by the highest accuracy of the model predicting in-hospital mortality.

Liquid biopsies for early diagnosis of brain tumours: in silico mathematical biomarker modelling

Brain tumours are the biggest cancer killer in those under 40 and reduce life expectancy more than any other cancer. Blood-based liquid biopsies may aid early diagnosis, prediction and prognosis for brain tumours. It remains unclear whether known blood-based biomarkers, such as glial fibrillary acidic protein (GFAP), have the required sensitivity and selectivity. We have developed a novel in silico model which can be used to assess and compare blood-based liquid biopsies. We focused on GFAP, a putative biomarker for astrocytic tumours and glioblastoma multi-formes (GBMs). In silico modelling was paired with experimental measurement of cell GFAP concentrations and used to predict the tumour volumes and identify key parameters which limit detection. The average GBM volumes of 449 patients at Leeds Teaching Hospitals NHS Trust were also measured and used as a benchmark. Our model predicts that the currently proposed GFAP threshold of 0.12 ng ml-1 may not be suitable for early detection of GBMs, but that lower thresholds may be used. We found that the levels of GFAP in the blood are related to tumour characteristics, such as vasculature damage and rate of necrosis, which are biological markers of tumour aggressiveness. We also demonstrate how these models could be used to provide clinical insight.

A machine-learning-based prediction method for easy COPD classification based on pulse oximetry clinical use

Chronic Obstructive Pulmonary Disease (COPD) is a progressive, obstructive lung disease that restricts airflow from the lungs. COPD patients are at risk of sudden and acute worsening of symptoms called exacerbations. Early identification and classification of COPD exacerbation can reduce COPD risks and improve patient’s healthcare and management. Pulse oximetry is a non-invasive technique used to assess patients with acutely worsening symptoms. As part of manual diagnosis based on pulse oximetry, clinicians examine three warning signs to classify COPD patients. This may lack high sensitivity and specificity which requires a blood test. However, laboratory tests require time, further delayed treatment and additional costs. This research proposes a prediction method for COPD patients’ classification based on pulse oximetry three manual warning signs and the resulting derived few key features that can be obtained in a short time. The model was developed on a robust physician labeled dataset with clinically diverse patient cases. Five classification algorithms were applied on the mentioned dataset and the results showed that the best algorithm is XGBoost with the accuracy of 91.04%, precision of 99.86%, recall of 82.19%, F1 measure value of 90.05% with an AUC value of 95.8%. Age, current and baseline heart rate, current and baseline pulse ox. (SPO2) were found the top most important predictors. These findings suggest the strength of XGBoost model together with the availability and the simplicity of input variables in classifying COPD daily living using a (wearable) pulse oximeter.

Cognitive Status Predicts Return to Functional Independence After Minor Stroke: A Decision Tree Analysis

About two-thirds of patients with minor strokes are discharged home. However, these patients may have difficulties returning to their usual living activities. To investigate the factors associated with successful home discharge, our aim was to provide a decision tree (based on clinical data) that could identify if a patient discharged home could return to pre-stroke activities and to perform an external validation of this decision tree on an independent cohort. Two cohorts of patients with minor strokes gathered from stroke registries at the Hôpital Pitié-Salpêtrière and University Hospital Bern were included in this study (n = 105 for the construction cohort coming from France; n = 100 for the second cohort coming from Switzerland). The decision tree was built using the classification and regression tree (CART) analysis on the construction cohort. It was then applied to the validation cohort. Accuracy, sensitivity, specificity, false positive, and false-negative rates were reported for both cohorts. In the construction cohort, 60 patients (57%) returned to their usual, pre-stroke level of independence. The CART analysis produced a decision tree with the Montreal Cognitive Assessment (MoCA) as the first decision point, followed by discharge NIHSS score or age, and then by the occupational status. The overall prediction accuracy to the favorable outcome was 80% in the construction cohort and reached 72% accuracy in the validation cohort. This decision tree highlighted the role of cognitive function as a crucial factor for patients to return to their usual activities after a minor stroke. The algorithm may help clinicians to tailor planning of patients' discharge.

Economic evaluation of Zika Contraception Access Network in Puerto Rico during the 2016-17 Zika virus outbreak

OBJECTIVE

During the 2016-2017 Zika virus (ZIKV) outbreak, the prevention of unintended pregnancies was identified as a primary strategy to prevent birth defects. This study estimated the cost-effectiveness of the Zika Contraception Access Network (Z-CAN), an emergency response intervention that provided women in Puerto Rico with access to the full range of reversible contraception at no cost and compared results with a pre-implementation hypothetical cost-effectiveness analysis (CEA).

STUDY DESIGN

We evaluated costs and outcomes of Z-CAN from a health sector perspective compared to no intervention using a decision tree model. Number of people served, contraception methods mix, and costs under Z-CAN were from actual program data and other input parameters were from the literature. Health outcome measures included the number of Zika-associated microcephaly (ZAM) cases and unintended pregnancies. The economic benefits of the Z-CAN intervention were ZIKV-associated direct costs avoided, including lifetime medical and supportive costs associated with ZAM cases, costs of monitoring ZIKV-exposed pregnancies and infants born from Zika-virus infected mothers, and the costs of unintended pregnancies prevented during the outbreak as a result of increased contraception use through the Z-CAN intervention.

RESULTS

The Z-CAN intervention cost a total of $26.1 million, including costs for the full range of reversible contraceptive methods, contraception related services, and programmatic activities. The program is estimated to have prevented 85% of cases of estimated ZAM cases and unintended pregnancies in the absence of Z-CAN. The intervention cost was projected to have been more than offset by $79.9 million in ZIKV-associated costs avoided, 96% of which were lifetime ZAM-associated costs, as well as $137.0 million from avoided unintended pregnancies, with total net savings in one year of $216.9 million. The results were consistent with the previous CEA study.

CONCLUSION

Z-CAN was likely cost-saving in the context of a public health emergency response setting.

Opportunities and Challenges for Machine Learning in Rare Diseases

Rare diseases (RDs) are complicated health conditions that are difficult to be managed at several levels. The scarcity of available data chiefly determines an intricate scenario even for experts and specialized clinicians, which in turn leads to the so called “diagnostic odyssey” for the patient. This situation calls for innovative solutions to support the decision process via quantitative and automated tools. Machine learning brings to the stage a wealth of powerful inference methods; however, matching the health conditions with advanced statistical techniques raises methodological, technological, and even ethical issues. In this contribution, we critically point to the specificities of the dialog of rare diseases with machine learning techniques concentrating on the key steps and challenges that may hamper or create actionable knowledge and value for the patient together with some on-field methodological suggestions and considerations.

Towards a new understanding of uncertainty in medical education

RATIONALE, AIMS, AND OBJECTIVES

Uncertainty is a complex and constant phenomenon in clinical practice. How medical students recognize and respond to uncertainty impacts on their well-being, career choices, and attitudes towards patients. It has been suggested that curricula should do more to prepare medical students for an uncertain world. In order to teach medical students about uncertainty, we need to understand how uncertainty has been conceptualized in the literature to date. The aim of this article is to explore existing models of uncertainty and to develop a framework of clinical uncertainty to aid medical education.

METHOD

A scoping literature review was performed to identify conceptual models of uncertainty in healthcare. Content and inductive analyses were performed to explore three dimensions of clinical uncertainty: sources of uncertainty, subjective influencers and responses to uncertainty.

RESULTS

Nine hundred one references were identified using our search strategy, of which, 24 met our inclusion criteria. It was possible to classify these conceptual models using one or more of three dimensions of uncertainty; sources, subjective influencers, and responses. Exploration and further classification of these dimensions led to the development of a framework of uncertainty for medical education.

CONCLUSION

The developed framework of clinical uncertainty highlights sources, subjective influencers, responses to uncertainty, and the dynamic relationship among these elements. Our framework illustrates the different aspects of knowledge as a source of uncertainty and how to distinguish between those aspects. Our framework highlights the complexity of sources of uncertainty, especially when including uncertainty arising from relationships and systems. These sources can occur in combination. Our framework is also novel in how it describes the impact of influencers such as personal characteristics, experience, and affect on perceptions of and responses to uncertainty. This framework can be used by educators and curricula developers to help understand and teach about clinical uncertainty.

Dose Adjustment Model of Paliperidone in Patients With Acute Schizophrenia: A post hoc Analysis of an Open-Label, Single-Arm Multicenter Study

This study aimed to investigate the factors that influenced the clinicians to adjust the paliperidone dose in the acute phase of schizophrenia. This was a post hoc study of an 8-week, open-label, single-arm multicenter trial which evaluated the efficacy, safety, and tolerability of flexible doses of paliperidone ER (3-12 mg/day) in patients with acutely exacerbated schizophrenia. Patients were divided into groups according to the dose at week 8 (3, 6, and 9-12 mg). The responder was defined as the reduction percentage in the Positive and Negative Syndrome Scale (PANSS) total score of ≥30%. According to the chi-squared automatic interaction detection algorithm, decision tree models predicting an increase in the dose of paliperidone ER were established. A decision tree, based on 4-week Marder positive factor, Clinical Global Impression (CGI), and BMI, was established to guide the dose adjustments of paliperidone ER in the acute phase of schizophrenia. The multivariable logistic regression analysis showed that lower age at onset, higher baseline PANSS positive subscale score, and lower baseline Personal and Social Performance Scale (PSP) score were significant predictors of increased dose in responders. Patients with young-onset age, severe baseline symptoms, and poor function are more likely to benefit from high dosage.

Decision Making in Psychiatric Patients: A Qualitative Study with Focus Groups

INTRODUCTION

It has been said that mental illnesses are characterised by poor decision making; there is some neuroscientific evidence of specific alterations in performance in decision making tests, but little is known about how patients make choices about their own treatments.

METHODS

Focus groups with patients from two psychiatric clinics, with discourse analysis.

RESULTS

Five deductive categories (tools, capacity, therapeutic relationship, method and family and network), plus one additional category from the analysis (stigma), and 35 inductive (posterior) categories were considered. The categories are analysed and the findings presented.

CONCLUSIONS

Patients express a need for greater participation in decisions about their treatment, and a more symmetrical psychiatrist-patient relationship, involving families. Decisions may be changed due to stigma, barriers to treatment access, and previous experiences.

Estimating assistive product need in Cameroon and India: results of population-based surveys and comparison of self-report and clinical impairment assessment approaches

OBJECTIVES

To estimate population need and coverage for distance glasses, hearing aids and wheelchairs in India and Cameroon, and to explore the relationship between assistive product (AP) need measured through self-report and clinical impairment assessment.

METHODS

Population-based surveys of approximately 4000 people each were conducted in Mahabubnagar district, India and Fundong district, Cameroon. Participants underwent standardised vision, hearing and musculoskeletal impairment assessment to assess need for distance glasses, hearing aids, wheelchairs. Participants with moderate or worse impairment and/or self-reported difficulties in functioning were also asked about their self-reported AP need.

RESULTS

6.5% (95% CI 5.4-7.9) in India and 1.9% (95% CI 1.5-2.4) in Cameroon of the population needed at least one of the three APs based on moderate or worse impairments. Total need was highest for distance glasses [3.7% (95% CI 2.8-4.7) India; 0.8% (95% CI 0.5-1.1), Cameroon] and lowest for wheelchairs (0.1% both settings; 95% CI 0.03-0.3 India, 95% CI 0.04-0.3 Cameroon). Coverage for each AP was below 40%, except for distance glasses in India, where it was 87% (95% CI 77.1-93.0). The agreement between self-report and clinical impairment assessment of AP need was poor. For instance, in India, 60% of people identified through clinical assessment as needing distance glasses did not self-report a need. Conversely, in India, 75% of people who self-reported needing distance glasses did not require one based on clinical impairment assessment.

CONCLUSIONS

There is high need and low coverage of three APs in two low-and middle-income settings. Methodological shortcomings highlight the need for improved survey methods compatible with the international classification of functioning, disability and health to estimate population-level need for AP and related services to inform advocacy and planning.

Shared Decision Making in Endodontics

Engaging patients in shared decision making (SDM) is a professional requirement since the Montgomery ruling in 2015. Endodontic treatments present a specific challenge to achieving SDM, both for the clinician and the patient. The treatments are often perceived as more challenging to complete by the clinician, and the assessment of risk and likely outcome requires a deep understanding of the (limited) evidence base. For the patient, decisions can be required at a time of acute symptoms and prolonged treatments. There are health literacy demands in comparison to some less complex dental treatments. Treatment decisions may be based more on inherent biases and prior experiences than objective probabilities. This article discusses options and supports effective shared decision making in endodontic treatment.

Decision Tree Learning Algorithm for Classifying Knee Injury Status Using Return-to-Activity Criteria

Anterior cruciate ligament (ACL) injury rates in female adolescents are increasing. Irrespective of treatment options, approximately 1/3 will suffer secondary ACL injuries following their return to activity (RTA). Despite this, there are no evidence-informed RTA guidelines to aid clinicians in deciding when this should occur. The first step towards these guidelines is to identify relevant and feasible measures to assess the functional status of these patients. The purpose of this study was therefore to evaluate tests frequently used to assess functional capacity following surgery using a Reduced Error Pruning Tree (REPT). Thirty-six healthy and forty-two ACLinjured adolescent females performed a series of functional tasks. Motion analysis along with spatiotemporal measures were used to extract thirty clinically relevant variables. The REPT reduced these variables down to two limb symmetry measures (maximum anterior hop and maximum lateral hop), capable of classifying injury status between the healthy and ACL injured participants with a 69% sensitivity, 78% specificity and kappa statistic of 0.464. We, therefore, conclude that the REPT model was able to evaluate functional capacity as it relates to injury status in adolescent females. We also recommend considering these variables when developing RTA assessments and guidelines.Clinical Relevance- Our results indicate that spatiotemporal measures may differentiate ACL-injured and healthy female adolescents with moderate confidence using a REPT. The identified tests may reasonably be added to the clinical evaluation process when evaluating functional capacity and readiness to return to activity.

A novel and simple machine learning algorithm for preoperative diagnosis of acute appendicitis in children

INTRODUCTION

There is a tendency toward nonoperative management of appendicitis resulting in an increasing need for preoperative diagnosis and classification. For medical purposes, simple conceptual decision-making models that can learn are widely used. Decision trees are reliable and effective techniques which provide high classification accuracy. We tested if we could detect appendicitis and differentiate uncomplicated from complicated cases using machine learning algorithms.

MATERIALS AND METHODS

We analyzed all cases admitted between 2010 and 2016 that fell into the following categories: healthy controls (Group 1); sham controls (Group 2); sham disease (Group 3), and acute abdomen (Group 4). The latter group was further divided into four groups: false laparotomy; uncomplicated appendicitis; complicated appendicitis without abscess, and complicated appendicitis with abscess. Patients with comorbidities and whose complete blood count and/or pathology results were lacking were excluded. Data were collected for demographics, preoperative blood analysis, and postoperative diagnosis. Various machine learning algorithms were applied to detect appendicitis patients.

RESULTS

There were 7244 patients with a mean age of 6.84 ± 5.31 years, of whom 82.3% (5960/7244) were male. Most algorithms tested, especially linear methods, provided similar performance measures. We preferred the decision tree model due to its easier interpretability. With this algorithm, we detected appendicitis patients with 93.97% area under the curve (AUC), 94.69% accuracy, 93.55% sensitivity, and 96.55% specificity, and uncomplicated appendicitis with 79.47% AUC, 70.83% accuracy, 66.81% sensitivity, and 81.88% specificity.

CONCLUSIONS

Machine learning is a novel approach to prevent unnecessary operations and decrease the burden of appendicitis both for patients and health systems.

LEVELS OF EVIDENCE

III.

Use of Decision Analysis and Economic Evaluation in Breast Reconstruction: A Systematic Review

Background:

Decision analysis allows clinicians to compare different strategies in the context of uncertainty, through explicit and quantitative measures such as quality of life outcomes and costing data. This is especially important in breast reconstruction, where multiple strategies can be offered to patients. This systematic review aims to appraise and review the different decision analytic models used in breast reconstruction.

Methods:

A search of English articles in PubMed, Ovid, and Embase databases was performed. All articles regardless of date of publishing were considered. Two reviewers independently assessed each article, based on strict inclusion criteria.

Results:

Out of 442 articles identified, 27 fit within the inclusion criteria. These were then grouped according to aspects of breast reconstruction, with implant-based reconstruction (n = 13) being the most commonly reported. Decision analysis (n = 19) and/or economic analyses (n = 27) were employed to discuss reconstructive options. The most common outcome was cost (n = 27). The decision analysis models compared and contrasted surgical strategies, management options, and novel adjuncts.

Conclusions:

Decision analysis in breast reconstruction is growing exponentially.The most common model used was a simple decision tree. Models published were of high quality but could be improved with a more in-depth sensitivity analysis. It is essential for surgeons to familiarize themselves with the concept of decision analysis to better tackle complicated decisions, due to its intrinsic advantage of being able to weigh risks and benefits of multiple strategies while using probabilistic models.

Artificial intelligence with multi-functional machine learning platform development for better healthcare and precision medicine

Precision medicine is one of the recent and powerful developments in medical care, which has the potential to improve the traditional symptom-driven practice of medicine, allowing earlier interventions using advanced diagnostics and tailoring better and economically personalized treatments. Identifying the best pathway to personalized and population medicine involves the ability to analyze comprehensive patient information together with broader aspects to monitor and distinguish between sick and relatively healthy people, which will lead to a better understanding of biological indicators that can signal shifts in health. While the complexities of disease at the individual level have made it difficult to utilize healthcare information in clinical decision-making, some of the existing constraints have been greatly minimized by technological advancements. To implement effective precision medicine with enhanced ability to positively impact patient outcomes and provide real-time decision support, it is important to harness the power of electronic health records by integrating disparate data sources and discovering patient-specific patterns of disease progression. Useful analytic tools, technologies, databases, and approaches are required to augment networking and interoperability of clinical, laboratory and public health systems, as well as addressing ethical and social issues related to the privacy and protection of healthcare data with effective balance. Developing multifunctional machine learning platforms for clinical data extraction, aggregation, management and analysis can support clinicians by efficiently stratifying subjects to understand specific scenarios and optimize decision-making. Implementation of artificial intelligence in healthcare is a compelling vision that has the potential in leading to the significant improvements for achieving the goals of providing real-time, better personalized and population medicine at lower costs. In this study, we focused on analyzing and discussing various published artificial intelligence and machine learning solutions, approaches and perspectives, aiming to advance academic solutions in paving the way for a new data-centric era of discovery in healthcare.

Assessing the Impact of Ozone and Particulate Matter on Mortality Rate from Respiratory Disease in Seoul, Korea

The evidence linking ozone and particulate matter with adverse health impacts is increasing. The goal of this study was to assess the impact of air pollution on the mortality rate from respiratory disease in Seoul, Korea, between 2008 and 2017. The analysis was conducted using a decision tree model in two ways: using 24-hour average concentrations and using 1-hour maximum values to compare any health impacts from the different times of exposure to pollution. Results show that in spring an elevated level of ozone is one of the most important factors, but in summer temperature has a greater impact than air pollution. Nitrogen dioxide is one of the most important factors in fall, while high levels of particles less than 2.5 μm (PM2.5) and 10 μm in size (PM10) and cooler temperatures are key factors in winter. We checked the accuracy of our results through a 10-fold cross validation method. Error rates using 24-hour average and 1-hour maximum concentrations were in the ranges of 24.9%–42% and 27.6%–42%, respectively, indicating that 24-hour average concentrations are slightly more directly related with mortality rate. These results could be useful for policy makers in determining the temporal scale of predicted pollutant concentrations for an air quality warning system to help minimize the adverse impacts of air pollution.

Use of Decision Analysis and Economic Evaluation in Upper Extremity Surgery: A Systematic Review

BACKGROUND

Decision analysis allows clinicians to apply evidence-based medicine to guide objective decisions in uncertain scenarios. There is no comprehensive review summarizing the various decision analysis tools used. The authors aimed to appraise and review the decision analytic models used in hand surgery.

METHODS

A search of English articles on the PubMed, Ovid, and Embase databases was performed. All articles, regardless of date of publishing, were considered. Two reviewers, based on strict inclusion criteria, independently assessed each article.

RESULTS

The search resulted in 5525 abstracts, which yielded 30 studies that met inclusion criteria. Included studies were grouped according to medical indications, with scaphoid fractures (n = 6) and carpal tunnel syndrome (n = 5) being the most commonly reported. Included articles used decision analysis (n = 15) and/or economic analyses (n = 23) to discuss diagnostic strategies or compare treatments. The three most common outcomes reported were utility (n = 12), cost per quality-adjusted life-year (n = 16), and quality-adjusted life-years (n = 16). The decision analysis models compared diagnostic strategies, management options, and novel treatments.

CONCLUSIONS

Decision analysis is increasingly popular in hand surgery. It is useful for comparing surgical strategies through evaluation of quality-of-life outcomes and costing data. The most common model was a simple decision tree. The quality of decision analysis models can be improved with the addition of sensitivity analysis. Surgeons should be familiar with the principles of decision analysis, so that complex decisions can be evaluated using rigorous probabilistic models that combine risks and benefits of multiple strategies.

Morphometric MRI profiles of multiple system atrophy variants and implications for differential diagnosis

Background

Manual width measurements of the middle cerebellar peduncle on MRI were shown to improve the accuracy of an imaging‐guided diagnosis of multiple system atrophy (MSA). Recently, automated volume segmentation algorithms were able to reliably differentiate patients with Parkinson's disease (PD) and the parkinsonian variant of MSA. The objective of the current study was to integrate probabilistic information of the middle cerebellar peduncle into an existing MRI atlas for automated subcortical segmentation and to evaluate the diagnostic properties of the novel atlas for the differential diagnosis of MSA (parkinsonian and cerebellar variant) versus PD.

Methods

Three Tesla MRI scans of 48 healthy individuals were used to establish an automated whole‐brain segmentation procedure that includes the volumes of the putamen, cerebellar gray and white matter, and the middle cerebellar peduncles. Classification accuracy of segmented volumes were tested in early‐stage MSA patients (18 MSA‐parkinsonism, 13 MSA‐cerebellar) and 19 PD patients using a C4.5 classifier.

Results

Putaminal and infratentorial atrophy were present in 77.8% and 61.1% of MSA‐parkinsonian patients, respectively. Four of 18 MSA‐parkinsonian patients (22.2%) had infratentorial atrophy without evidence of putaminal atrophy. Infratentorial atrophy was present in all MSA‐cerebellar patients, with concomitant putaminal atrophy in 46.2% of these cases. The diagnostic algorithm using putaminal and infratentorial volumetric information correctly classified all PD patients and 96.8% of MSA patients.

Conclusions

The middle cerebellar peduncle was successfully integrated into a subcortical segmentation atlas, and its excellent diagnostic accuracy outperformed existing volumetric MRI processing strategies in differentiating MSA patients with variable atrophy patterns from PD patients. © 2019 The Authors. Movement Disorders published by Wiley Periodicals, Inc. on behalf of International Parkinson and Movement Disorder Society.

Systematic scoping review protocol for clinical prediction rules (CPRs) in the management of patients with spinal cord injuries

INTRODUCTION

The upsurge in the use of clinical prediction models in general medical practice is a result of evidence-based practice. However, the total number of clinical prediction rules (CPRs) currently being used or undergoing impact analysis in the management of patients who have sustained spinal cord injuries (SCIs) is unknown. This scoping review protocol will describe the current CPRs being used and highlight their possible strengths and weaknesses in SCI management.

METHODS AND ANALYSIS

Arksey and O'Malley's scoping review framework will be used. The following databases will be searched to identify relevant literature relating to the use of CPRs in the management of patients who have sustained an SCI: PubMed, Cumulative Index of Nursing and Allied Health Literature (CINAHL), ScienceDirect, EBSCOhost, Medline, OvidMedline and Google Scholar. Grey literature as well as reference lists of included studies will be searched. All studies relating to the use of CPRs in the management of patients with SCIs will be included. Literature searches and data extraction will be performed independently by two groups of reviewers.

ETHICS AND DISSEMINATION

Ethical clearance is not required for this scoping review study since only secondary data sources will be used. The findings of this review will be disseminated by means of peer-reviewed publication and conference proceedings. The final paper will be submitted for publication. Results of this review will also be presented at relevant conferences and disseminated to important stakeholders such as practicing physicians within specialised spinal care facilities within South Africa.

The impact of improved detection and treatment of isoniazid resistant tuberculosis on prevalence of multi-drug resistant tuberculosis: A modelling study

Introduction

Isoniazid-resistant, rifampin susceptible tuberculosis (INHR-TB) is the most common form of drug resistant TB globally. Treatment of INHR-TB with standard first-line therapy is associated with high rates of multidrug resistant TB (MDR-TB). We modelled the potential impact of INHR-TB detection and appropriate treatment on MDR-TB prevalence.

Methods

A decision analysis model was developed to compare three different strategies for the detection of TB (AFB smear, Xpert MTB/RIF, and Line-Probe Assays (LPA)), combined with appropriate treatment. The population evaluated were patients with a globally representative prevalence of newly diagnosed, drug-susceptible (88.6%), isoniazid-resistant (7.3%), and multidrug resistant (4.1%) pulmonary TB. Our primary outcome was the proportion of patients with MDR-TB after initial attempt at diagnosis and treatment within a 2-year period. Secondary outcomes were the proportion of i) individuals with detected TB who acquired MDR-TB ii) individuals who died after initial attempt at diagnosis and treatment.

Results

After initial attempt at diagnosis and treatment, LPA combined with appropriate INHR-TB therapy resulted in a lower proportion of prevalent MDR-TB (1.61%; 95% Uncertainty Range (UR: 2.5^th and 97.5^th percentiles generated from 10 000 Monte Carlo simulation trials) 1.61–1.65), when compared to Xpert (1.84%; 95% UR 1.82–1.85) and AFB smear (3.21%; 95% UR 3.19–3.26). LPA also resulted in fewer cases of acquired MDR-TB in those with detected TB (0.35%; 95% UR 0.34–0.35), when compared to Xpert (0.67%; 95% UR 0.65–0.67) and AFB smear (0.68%; 95% UR 0.67–0.69). The majority of acquired MDR-TB arose from the treatment of INHR-TB in all strategies. Xpert-based strategies resulted in a lower proportion of death (2.89%; 95% UR 2.87–2.90) compared to LPA (2.93%; 95% UR 2.91–2.94) and AFB smear (3.21%; 95% UR 3.19–3.23).

Conclusion

Accurate diagnosis and tailored treatment of INHR-TB with LPA led to an almost 50% relative decrease in acquired MDR-TB when compared with an Xpert MTB/RIF strategy. Continued reliance on diagnostic and treatment protocols that ignore INHR-TB will likely result in further generation of MDR-TB.

A Hybrid Computer-aided-diagnosis System for Prediction of Breast Cancer Recurrence (HPBCR) Using Optimized Ensemble Learning

Cancer is a collection of diseases that involves growing abnormal cells with the potential to invade or spread to the body. Breast cancer is the second leading cause of cancer death among women. A method for 5-year breast cancer recurrence prediction is presented in this manuscript. Clinicopathologic characteristics of 579 breast cancer patients (recurrence prevalence of 19.3%) were analyzed and discriminative features were selected using statistical feature selection methods. They were further refined by Particle Swarm Optimization (PSO) as the inputs of the classification system with ensemble learning (Bagged Decision Tree: BDT). The proper combination of selected categorical features and also the weight (importance) of the selected interval-measurement-scale features were identified by the PSO algorithm. The performance of HPBCR (hybrid predictor of breast cancer recurrence) was assessed using the holdout and 4-fold cross-validation. Three other classifiers namely as supported vector machines, DT, and multilayer perceptron neural network were used for comparison. The selected features were diagnosis age, tumor size, lymph node involvement ratio, number of involved axillary lymph nodes, progesterone receptor expression, having hormone therapy and type of surgery. The minimum sensitivity, specificity, precision and accuracy of HPBCR were 77%, 93%, 95% and 85%, respectively in the entire cross-validation folds and the hold-out test fold. HPBCR outperformed the other tested classifiers. It showed excellent agreement with the gold standard (i.e. the oncologist opinion after blood tumor marker and imaging tests, and tissue biopsy). This algorithm is thus a promising online tool for the prediction of breast cancer recurrence.

The value of decision tree analysis in planning anaesthetic care in obstetrics

The use of decision tree analysis is discussed in the context of the anaesthetic and obstetric management of a young pregnant woman with joint hypermobility syndrome with a history of insensitivity to local anaesthesia and a previous difficult intubation due to a tongue tumour. The multidisciplinary clinical decision process resulted in the woman being delivered without complication by elective caesarean section under general anaesthesia after an awake fibreoptic intubation. The decision process used is reviewed and compared retrospectively to a decision tree analytical approach. The benefits and limitations of using decision tree analysis are reviewed and its application in obstetric anaesthesia is discussed.

Development and application of patient decision aids

With the current overdiagnosis of thyroid cancer resulting from routine screening in Korea, it is necessary to educate the public that not all cancers are malignant. The exposure to patient decision aids (PtDAs) compared to usual care reduced the number of people choosing to undergo prostate-specific antigen screening. This article introduces the definition, usefulness, and developmental processes of PtDAs and suggests the urgent need for a Korean PtDA related to thyroid cancer screening.

Value-based medicine: concepts and application

Global healthcare in the 21st century is characterized by evidence-based medicine (EBM), patient-centered care, and cost effectiveness. EBM involves clinical decisions being made by integrating patient preference with medical treatment evidence and physician experiences. The Center for Value-Based Medicine suggested value-based medicine (VBM) as the practice of medicine based upon the patient-perceived value conferred by an intervention. VBM starts with the best evidence-based data and converts it to patient value-based data, so that it allows clinicians to deliver higher quality patient care than EBM alone. The final goals of VBM are improving quality of healthcare and using healthcare resources efficiently. This paper introduces the concepts and application of VBM and suggests some strategies for promoting related research.