Personalized health care: From theory to practice

SwissGenVar: A Platform for Clinical-Grade Interpretation of Genetic Variants to Foster Personalized Healthcare in Switzerland

Large-scale next-generation sequencing (NGS) germline testing is technically feasible today, but variant interpretation represents a major bottleneck in analysis workflows. This includes extensive variant prioritization, annotation, and time-consuming evidence curation. The scale of the interpretation problem is massive, and variants of uncertain significance (VUSs) are a challenge to personalized medicine. This challenge is further compounded by the complexity and heterogeneity of the standards used to describe genetic variants and the associated phenotypes when searching for relevant information to support clinical decision making. To address this, all five Swiss academic institutions for Medical Genetics joined forces with the Swiss Institute of Bioinformatics (SIB) to create SwissGenVar as a user-friendly nationwide repository and sharing platform for genetic variant data generated during routine diagnostic procedures and research sequencing projects. Its aim is to provide a protected environment for expert evidence sharing about individual variants to harmonize and upscale their significance interpretation at the clinical grade according to international standards. To corroborate the clinical assessment, the variant-related data will be combined with consented high-quality clinical information. Broader visibility will be achieved by interfacing with international databases, thus supporting global initiatives in personalized healthcare.

Identifying clusters of objective functional impairment in patients with degenerative lumbar spinal disease using unsupervised learning

OBJECTIVES

The five-repetition sit-to-stand (5R-STS) test was designed to capture objective functional impairment (OFI), and thus provides an adjunctive dimension in patient assessment. It is conceivable that there are different subsets of patients with OFI and degenerative lumbar disease. We aim to identify clusters of objectively functionally impaired individuals based on 5R-STS and unsupervised machine learning (ML).

METHODS

Data from two prospective cohort studies on patients with surgery for degenerative lumbar disease and 5R-STS times of ≥ 10.5 s-indicating presence of OFI. K-means clustering-an unsupervised ML algorithm-was applied to identify clusters of OFI. Cluster hallmarks were then identified using descriptive and inferential statistical analyses.

RESULTS

We included 173 patients (mean age [standard deviation]: 46.7 [12.7] years, 45% male) and identified three types of OFI. OFI Type 1 (57 pts., 32.9%), Type 2 (81 pts., 46.8%), and Type 3 (35 pts., 20.2%) exhibited mean 5R-STS test times of 14.0 (3.2), 14.5 (3.3), and 27.1 (4.4) seconds, respectively. The grades of OFI according to the validated baseline severity stratification of the 5R-STS increased significantly with each OFI type, as did extreme anxiety and depression symptoms, issues with mobility and daily activities. Types 1 and 2 are characterized by mild to moderate OFI-with female gender, lower body mass index, and less smokers as Type I hallmarks.

CONCLUSIONS

Unsupervised learning techniques identified three distinct clusters of patients with OFI that may represent a more holistic clinical classification of patients with OFI than test-time stratifications alone, by accounting for individual patient characteristics.

Inference of social cognition in schizophrenia patients with neurocognitive domains and neurocognitive tests using automated machine learning

AIM

It has been suggested that single neurocognitive domain or neurocognitive test can be used to determine the overall cognitive function in schizophrenia using machine learning algorithms. It is unknown whether social cognition in schizophrenia patients can be estimated with machine learning based on neurocognitive domains or neurocognitive tests.

METHODS

To predict social cognition in schizophrenia, we applied an automated machine learning (AutoML) framework resulting from the analysis of predictive factors such as six neurocognitive domain scores and nine neurocognitive test scores of 380 schizophrenia patients in the Taiwanese population. Four clinical parameters (i.e., age, gender, subgroup, and education) were also used as predictive factors. We utilized an AutoML framework called Tree-based Pipeline Optimization Tool (TPOT) to generate predictive pipelines automatically.

RESULTS

The analysis revealed that all neurocognitive domains and tests except the reasoning and problem solving domain/test showed significant associations with social cognition. In addition, a TPOT-generated pipeline can best predict social cognition in schizophrenia using seven predictive factors, including five neurocognitive domains (i.e., speed of processing, sustained attention, working memory, verbal learning and memory, and visual learning and memory) and two clinical parameters (i.e., age and gender). This predictive pipeline consists of machine learning algorithms such as function transformers, an approximate feature map, independent component analysis, and linear regression.

CONCLUSION

The study indicates that an AutoML framework such as TPOT may provide a promising way to produce truly effective machine learning pipelines for predicting social cognition in schizophrenia using neurocognitive domains and/or neurocognitive tests.

Adaptation to Telehealth of Personalized Group Visits for Late Stage Diabetic Kidney Disease

Key Points

Improving late stage diabetic kidney disease care requires adapting evidence-based, self-management programs for telehealth delivery. We adapted and pilot-tested a telehealth approach and found it to be feasible. Preliminary data suggested it improved relevant health and patient-recorded outcomes.

Background

The coronavirus disease 2019 pandemic resulted in an unprecedented shift in the delivery of outpatient medical care, including the rapid transition of services from in-person to telehealth. We adapted an evidence-based personalized health planning group visit care model traditionally offered in-person to telehealth to support the care of patients with type 2 diabetes mellitus (T2D) and CKD. Despite the need to leverage telehealth technologies to better support self-management for patients with CKD, scant evidence exists on how to do so.

Methods

We conducted prospective adaptations of in-person evidence-based group visit model for telehealth delivery for patients with CKD and T2D. Intervention adaptations are reported using the Framework for Reporting Adaptations and Modifications–Expanded taxonomy. The adapted virtual group visit care model was pilot-tested among adults with T2D and stage 3b or 4 CKD. Feasibility outcomes included recruitment, attendance, satisfaction, and self-reported goal progress. Clinical outcomes were evaluated using Wilcoxon signed-rank tests and included hemoglobin A1c, diastolic and systolic BP, body mass index, and eGFR.

Results

Adaptation areas included outreach, visit format, educational materials design and access, staffing, and patient engagement strategies. 39% (43) of patients (110) contacted verbalized interest, and 58% (25) of those participated. 72% completed >6 group sessions. 68% of patients reported completing one or more health goals, with nutrition and physical activity being the most common. We observed a statistically significant improvement in hemoglobin A1c (P = 0.0176) 6 months postprogram participation.

Conclusions

Adapting evidence-based interventions for telehealth delivery is challenging because of the risk of altering an intervention's core components responsible for observed benefits. We adapted an in-person group visit model for the care of T2D and CKD for telehealth delivery. The telehealth approach was feasible, and preliminary data suggested it improved relevant health and patient-recorded outcomes up to 6 months postprogram completion. The approaches used here may be applicable to the adaptation of other clinical programs for telehealth delivery.

Podcast

This article contains a podcast at https://dts.podtrac.com/redirect.mp3/www.asn-online.org/media/podcast/K360/2023_12_29_KID0000000000000301.mp3

ExpertNet: A Deep Learning Approach to Combined Risk Modeling and Subtyping in Intensive Care Units

Risk models play a crucial role in disease prevention, particularly in intensive care units (ICUs). Diseases often have complex manifestations with heterogeneous subpopulations, or subtypes, that exhibit distinct clinical characteristics. Risk models that explicitly model subtypes have high predictive accuracy and facilitate subtype-specific personalization. Such models combine clustering and classification methods but do not effectively utilize the inferred subtypes in risk modeling. Their limitations include tendency to obtain degenerate clusters and cluster-specific data scarcity leading to insufficient training data for the corresponding classifier. In this article, we develop a new deep learning model for simultaneous clustering and classification, ExpertNet, with novel loss terms and network training strategies that address these limitations. The performance of ExpertNet is evaluated on the tasks of predicting risk of (i) sepsis and (ii) acute respiratory distress syndrome (ARDS), using two large electronic medical records datasets from ICUs. Our extensive experiments show that, in comparison to state-of-the-art baselines for combined clustering and classification, ExpertNet achieves superior accuracy in risk prediction for both ARDS and sepsis; and comparable clustering performance. Visual analysis of the clusters further demonstrates that the clusters obtained are clinically meaningful and a knowledge-distilled model shows significant differences in risk factors across the subtypes. By addressing technical challenges in training neural networks for simultaneous clustering and classification, ExpertNet lays the algorithmic foundation for the future development of subtype-aware risk models.

"If you respect me, you are respecting my culture": methods and recommendations for personalizing a TBI transitional care intervention

OBJECTIVE

Despite research, national legislation, and clinical guidelines supporting transitional care, there is minimal benefit from existing transitional care interventions for racial/ethnic minorities with traumatic brain injury (TBI) discharged home from acute hospital care. Existing TBI transitional care interventions are not tailored to address the needs/preferences of patients from various racial/ethnic minority groups. The purpose of this study was to describe use of personalization to tailor a TBI transitional care intervention for various racial/ethnic groups.

DESIGN

Following preliminary intervention manual development, a qualitative descriptive study was conducted using eight focus groups with 40 English-and Spanish-speaking participants (12 patients, 12 caregivers, and 16 providers).

RESULTS

Three personalization-related themes emerged: 1) what is important to me, 2) finding someone to deliver the intervention who can adapt to my needs, and 3) respect over culture. Findings informed personalization strategies within our final manual.

CONCLUSIONS

We recommend researchers who wish to use personalization to tailor interventions to consider: 1) allowing stakeholders to dictate what is most important and 2) implementing an iterative intervention development process with input from diverse stakeholders. Findings have implications for informing the development of transitional care interventions to increase the likelihood that interventions are inclusive of needs and preferences of various races/ethnicities.

A feasibility Randomised Controlled Trial as a first step towards evaluating the effectiveness of a digital health dashboard in preventive child health care: a mixed methods approach

BACKGROUND

Within preventive Child Health Care (CHC), the 360°CHILD-profile has been developed. This digital tool visualises and theoretically orders holistic health data in line with the International Classification of Functioning, Disability and Health. It is anticipated that evaluating the effectiveness of the multifunctional 360°CHILD-profile within the preventive CHC-context is complex. Therefore, this study aimed at investigating the feasibility of RCT procedures and the applicability of potential outcome measures for assessing the accessibility and transfer of health information.

METHODS

During the first introduction of the 360°CHILD-profile in CHC practice, a feasibility RCT with an explanatory-sequential mixed methods design was executed. CHC professionals (n=38) recruited parents (n=30) who visited the CHC for their child (age 0-16). Parents were randomised to "care as usual" (n=15) or "care as usual with, in addition, the availability of a personalised 360°CHILD-profile during 6 months" (n=15). Quantitative data on RCT feasibility were collected on recruitment, retention, response, compliance rates and outcome data on accessibility and transfer of health information (n=26). Subsequently, thirteen semi-structured interviews (5 parents, 8 CHC professionals) and a member check focus group (6 CHC professionals) were performed to further explore and gain a deeper understanding of quantitative findings.

RESULTS

Integration of qualitative and quantitative data revealed that the recruitment of parents by CHC professionals was problematic and influenced by organisational factors. The used randomisation strategy, interventions and measurements were executable within the setting of this specific study. The outcome measures showed skewed outcome data in both groups and a low applicability to measure accessibility and transfer of health information. The study revealed points to reconsider regarding the randomisation and recruitment strategy and measures in the next steps.

CONCLUSIONS

This mixed methods feasibility study enabled us to gain a broad insight into the feasibility of executing an RCT within the CHC context. Trained research staff should recruit parents instead of CHC professionals. Measures, potentially for evaluating 360°CHILD-profile's effectiveness, need further exploration and thorough piloting before proceeding with the evaluation process. Overall findings revealed that executing an RCT within the context of evaluating 360°CHILD-profile's effectiveness in the CHC setting will be much more complex, time-consuming and costly than expected. Thereby, the CHC context requires a more complex randomisation strategy than executed during this feasibility study. Alternative designs including mixed methods research must be considered for the next phases of the downstream validation process.

TRIAL REGISTRATION

NTR6909; https://trialsearch.who.int/ .

Development and Validation of a Personalized Model With Transfer Learning for Acute Kidney Injury Risk Estimation Using Electronic Health Records

IMPORTANCE

Acute kidney injury (AKI) is a heterogeneous syndrome prevalent among hospitalized patients. Personalized risk estimation and risk factor identification may allow effective intervention and improved outcomes.

OBJECTIVE

To develop and validate personalized AKI risk estimation models using electronic health records (EHRs), examine whether personalized models were beneficial in comparison with global and subgroup models, and assess the heterogeneity of risk factors and their outcomes in different subpopulations.

DESIGN, SETTING, AND PARTICIPANTS

This diagnostic study analyzed EHR data from 1 tertiary care hospital and used machine learning and logistic regression to develop and validate global, subgroup, and personalized risk estimation models. Transfer learning was implemented to enhance the personalized model. Predictor outcomes across subpopulations were analyzed, and metaregression was used to explore predictor interactions. Adults who were hospitalized for 2 or more days from November 1, 2007, to December 31, 2016, were included in the analysis. Patients with moderate or severe kidney dysfunction at admission were excluded. Data were analyzed between August 28, 2019, and May 8, 2022.

EXPOSURES

Clinical and laboratory variables in the EHR.

MAIN OUTCOMES AND MEASURES

The main outcome was AKI of any severity, and AKI was defined using the Kidney Disease: Improving Global Outcomes serum creatinine criteria. Performance of the models was measured with area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve, and calibration.

RESULTS

The study cohort comprised 76 957 inpatient encounters. Patients had a mean (SD) age of 55.5 (17.4) years and included 42 159 men (54.8%). The personalized model with transfer learning outperformed the global model for AKI estimation in terms of AUROC among general inpatients (0.78 [95% CI, 0.77-0.79] vs 0.76 [95% CI, 0.75-0.76]; P < .001) and across the high-risk subgroups (0.79 [95% CI, 0.78-0.80] vs 0.75 [95% CI, 0.74-0.77]; P < .001) and low-risk subgroups (0.74 [95% CI, 0.73-0.75] vs 0.71 [95% CI, 0.70-0.72]; P < .001). The AUROC improvement reached 0.13 for the high-risk subgroups, such as those undergoing liver transplant and cardiac surgery. Moreover, the personalized model with transfer learning performed better than or comparably with the best published models in well-studied AKI subgroups. Predictor outcomes varied significantly between patients, and interaction analysis uncovered modifiers of the predictor outcomes.

CONCLUSIONS AND RELEVANCE

Results of this study demonstrated that a personalized modeling with transfer learning is an improved AKI risk estimation approach that can be used across diverse patient subgroups. Risk factor heterogeneity and interactions at the individual level highlighted the need for agile, personalized care.

A bagging ensemble machine learning framework to predict overall cognitive function of schizophrenia patients with cognitive domains and tests

BACKGROUND

It has been indicated that the interplay between functional outcomes and cognitive functions in schizophrenia is arbitrated by clinical symptoms, where cognitive functions are evaluated by cognitive domains and cognitive tests.

METHODS

To determine which single cognitive domain or test can best predict the overall cognitive function of schizophrenia, we established a bagging ensemble framework resulting from the analysis of factors such as 7 cognitive domain scores and 11 cognitive test scores of 302 schizophrenia patients in the Taiwanese population. We compared our bagging ensemble framework with other state-of-the-art algorithms such as multilayer feedforward neural networks, linear regression, support vector machine, and random forests.

RESULTS

The analysis revealed that among the 7 cognitive domains, the speed of processing domain can best predict the overall cognitive function in schizophrenia using our bagging ensemble framework. In addition, among the 11 cognitive tests, the visual learning and memory test can best predict the overall cognitive function in schizophrenia using our bagging ensemble framework. Finally, among the 7 cognitive domains and 11 cognitive tests, the speed of processing domain can best predict the overall cognitive function in schizophrenia using our bagging ensemble framework.

CONCLUSION

The study implicates that the bagging ensemble framework may provide an applicable approach to develop tools for forecasting overall cognitive function in schizophrenia using cognitive domains and/or cognitive tests.

Proteomic Analysis of Whole Blood Using Volumetric Absorptive Microsampling for Precision Medicine Biomarker Studies

Microsampling of patient blood promises several benefits over conventional phlebotomy practices to facilitate precision medicine studies. These include at-home patient blood collection, supporting telehealth monitoring, minimal postcollection processing, and compatibility with nonrefrigerated transport and storage. However, for proteomic biomarker studies, mass spectrometry of whole blood has generally been avoided in favor of using plasma or serum obtained from venepuncture. We evaluated the use of a volumetric absorptive microsampling (VAMS) device as a sample preparation matrix to enable LC-MS proteomic analyses of dried whole blood. We demonstrated the detection and robust quantitation of up to 1600 proteins from single-shot shotgun-LC-MS analysis of dried whole blood, greatly enhancing proteome depth compared with conventional single-shot LC-MS analyses of undepleted plasma. Some proteins not previously reported in blood were detected using this approach. Various washing reagents were used to demonstrate that proteins can be preferentially removed from VAMS devices prior to downstream analyses. We provide a demonstration that archival frozen blood cell pellets housed under long-term storage (exceeding 5 years) are compatible with VAMS to enable quantitation of potential biomarker proteins from biobank repositories. These demonstrations are important steps in establishing viable analysis workflows to underpin large-scale precision medicine studies. Data are available via ProteomeXchange with the identifier PXD028605.

Physician-Customized Strategies for Reducing Outpatient Waiting Time in South Korea Using Queueing Theory and Probabilistic Metamodels

The time a patient spends waiting to be seen by a healthcare professional is an important determinant of patient satisfaction in outpatient care. Hence, it is crucial to identify parameters that affect the waiting time and optimize it accordingly. First, statistical analysis was used to validate the effective parameters. However, no parameters were found to have significant effects with respect to the entire outpatient department or to each department. Therefore, we studied the improvement of patient waiting times by analyzing and optimizing effective parameters for each physician. Queueing theory was used to calculate the probability that patients would wait for more than 30 min for a consultation session. Using this result, we built metamodels for each physician, formulated an effective method to optimize the problem, and found a solution to minimize waiting time using a non-dominated sorting genetic algorithm (NSGA-II). On average, we obtained a 30% decrease in the probability that patients would wait for a long period. This study shows the importance of customized improvement strategies for each physician.

Logistic ridge regression to predict bipolar disorder using mRNA expression levels in the N-methyl-D-aspartate receptor genes

BACKGROUND

It is hypothesized that demographic variables and mRNA expression levels in the N-methyl-D-aspartate receptor (NMDAR) genes can be employed as potential biomarkers to predict bipolar disorder using artificial intelligence and machine learning approaches.

METHODS

To determine bipolar status, we established a logistic ridge regression model resulting from the analysis of age, gender, and mRNA expression levels in 7 NMDAR genes in the blood of 51 bipolar patients and 139 unrelated healthy individuals in the Taiwanese population. The NMDAR genes encompasses COMT, GCAT, NRG1, PSAT1, SHMT2, SLC1A4, and SRR. We also compared our approach with various state-of-the-art algorithms such as support vector machine and C4.5 decision tree.

RESULTS

The analysis revealed that the mRNA expression levels of COMT, GCAT, NRG1, PSAT1, SHMT2, SLC1A4, and SRR were associated with bipolar disorder. Moreover, the logistic ridge regression model (area under the receiver operating characteristic curve = 0.922) performed maximally among predictive models to infer the complicated relationship between bipolar disorder and biomarkers. Additionally, the results for the age- and gender-matched cohort were similar to those of the unmatched cohort.

LIMITATIONS

The cross-sectional study design limited the predictive value.

CONCLUSION

This is the first study demonstrating that the mRNA expression levels in the NMDAR genes may be altered in patients with bipolar disorder, thereby supporting the NMDAR hypothesis of bipolar disorder. The study also indicates that the mRNA expression levels in the NMDAR genes could serve as potential biomarkers to distinguish bipolar patients from healthy controls using artificial intelligence and machine learning approaches.

Prospects and Challenges of MXenes as Emerging Sensing Materials for Flexible and Wearable Breath-Based Biomarker Diagnosis

A fully integrated, flexible, and functional sensing device for exhaled breath analysis drastically transforms conventional medical diagnosis to non-invasive, low-cost, real-time, and personalized health care. 2D materials based on MXenes offer multiple advantages for accurately detecting various breath biomarkers compared to conventional semiconducting oxides. High surface sensitivity, large surface-to-weight ratio, room temperature detection, and easy-to-assemble structures are vital parameters for such sensing devices in which MXenes have demonstrated all these properties both experimentally and theoretically. So far, MXenes-based flexible sensor is successfully fabricated at a lab-scale and is predicted to be translated into clinical practice within the next few years. This review presents a potential application of MXenes as emerging materials for flexible and wearable sensor devices. The biomarkers from exhaled breath are described first, with emphasis on metabolic processes and diseases indicated by abnormal biomarkers. Then, biomarkers sensing performances provided by MXenes families and the enhancement strategies are discussed. The method of fabrications toward MXenes integration into various flexible substrates is summarized. Finally, the fundamental challenges and prospects, including portable integration with Internet-of-Thing (IoT) and Artificial Intelligence (AI), are addressed to realize marketization.

Application of the inverted classroom model in the teaching module "new classification of periodontal and peri-implant diseases and conditions" during the COVID-19 pandemic

Background: Due to the need for patient-free dental education during the COVID-19 pandemic, Hannover Medical School (MHH) implemented a new periodontology module. Its didactic structure was based on the "inverted classroom model" (ICM) in combination with elements of case-based learning. The educational objective was to increase the diagnostic confidence of dental students in the classification of periodontal patients (staging & grading), based on 33 digitized patient cases. To assess the suitability of the module for future dental curricula, this study aimed to evaluate student satisfaction and skills acquisition. Methods: The periodontology module, which was attended by final year dental students of MHH (n=55, mean age: 26.5±3.9 years, male/female ratio: 24.1%/75.9%) was evaluated in a two-tiered way. Student satisfaction was recorded using a questionnaire. Learning success was assessed by comparing error rates in patient case classifications before (T₀) and after (T₁) participation in the periodontology module. Results: The study found a high level of student satisfaction with the ICM format and a significant reduction in error rates (T₀ error rate=28.3%; MV±SD=3.12±1.67 vs. T₁ error rate=18.7%; MV±SD=2.06±1.81; Δ=9.6%). However, of the 11 diagnostic decisions required, only four parameters (extent, grading, percentage of bone loss per age, phenotype) showed significant improvements, with effect sizes ranging from small to medium. Conclusions: The ICM-based teaching concept is definitely not an alternative to patient-based learning. However, in regard to student satisfaction and learning success, it might be superior to conventional classroom-based lectures, especially when complex topics are covered. In summary, the newly developed periodontology module may be a useful addition to traditional dental education in future curricula, even for the time after the COVID-19 pandemic.

The evolution of personalized healthcare and the pivotal role of European regions in its implementation

Personalized medicine (PM) moves at the same pace of data and technology and calls for important changes in healthcare. New players are participating, providing impulse to PM. We review the conceptual foundations for PM and personalized healthcare and their evolution through scientific publications where a clear definition and the features of the different formulations are identifiable. We then examined PM policy documents of the International Consortium for Personalised Medicine and related initiatives to understand how PM stakeholders have been changing. Regional authorities and stakeholders have joined the race to deliver personalized care and are driving toward what could be termed as the next personalized healthcare. Their role as a key stakeholder in PM is expected to be pivotal.

Applying a bagging ensemble machine learning approach to predict functional outcome of schizophrenia with clinical symptoms and cognitive functions

It has been suggested that the relationship between cognitive function and functional outcome in schizophrenia is mediated by clinical symptoms, while functional outcome is assessed by the Quality of Life Scale (QLS) and the Global Assessment of Functioning (GAF) Scale. To determine the outcome assessed by QLS and GAF, we established a bagging ensemble framework with a feature selection algorithm resulting from the analysis of factors such as 3 clinical symptom scales and 11 cognitive function scores of 302 patients with schizophrenia in the Taiwanese population. We compared our bagging ensemble framework with other state-of-the-art algorithms such as multilayer feedforward neural networks, support vector machine, linear regression, and random forests. The analysis revealed that the bagging ensemble model with feature selection performed best among predictive models in predicting the QLS functional outcome by using 20-item Scale for the Assessment of Negative Symptoms (SANS20) and 17-item Hamilton Depression Rating Scale (HAMD17). Moreover, to predict the GAF outcome, the bagging ensemble model with feature selection performed best among predictive models by using SANS20 and the Positive and Negative Syndrome Scale-Positive (PANSS-Positive) subscale. The study indicates that there are synergistic effects between negative (SANS20) and depressive (HAMD17) symptoms as well as between negative and positive (PANSS-Positive) symptoms in influencing functional outcome of schizophrenia using the bagging ensemble framework with feature selection.

Evaluation of a New Personalized Health Dashboard in Preventive Child Health Care: Protocol for a Mixed Methods Feasibility Randomized Controlled Trial

BACKGROUND

A new dashboard, the 360ºCHILD-profile, was developed to adopt personalized health care within preventive child health care. On this profile, holistic health data are visualized in a single image to provide parents, adolescents, and caregivers direct access to a manageable résumé of a child's medical record. Theoretical ordering, conforming to "International Classification of Functioning, Disability and Health for Children and Youth", guides clinical reasoning toward the biopsychosocial concept of health. It is yet unknown if and how this promising tool functions in practice, and a variety of feasibility questions must be addressed.

OBJECTIVE

This paper describes the design and methods of a feasibility randomized controlled trial (RCT), with the aim of evaluating the RCT's feasibility (recruitment, response, measure completion, and intervention allocation) and 360ºCHILD-profile's feasibility (usability and potential effectiveness).

METHODS

A pragmatic mixed methods study design was chosen, starting with an RCT to measure feasibility and health literacy in 2 parallel groups (1:1). Qualitative research will then be used to understand and explain quantitative findings and to explore the stakeholders' perspectives on the potential of the 360ºCHILD-profile. Participants will include child health care professionals (n≥30), parents (n≥30), and caregivers (n≥10) of children who experience developmental problems (age 0-16 years). Children will only be able to participate if they are older than 11 years (adolescents, n≥10). The 2 groups included in the study will receive standard care. The experimental group will additionally receive personalized 360ºCHILD-profiles.

RESULTS

After an intervention period of 6 months, quantitative outcomes will be measured, analyzed (descriptive feasibility statistics and preliminary between-group differences) and used to purposively sample for semistructured interviews.

CONCLUSIONS

Study results will provide knowledge for building theory on the 360ºCHILD-profile and designing future (effect) studies.

TRIAL REGISTRATION

Netherlands Trial Register NTR6909; https://www.trialregister.nl/trial/6731.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/21942.

Deep learning for the prediction of treatment response in depression

BACKGROUND

Mood disorders are characterized by heterogeneity in severity, symptoms and treatment response. The possibility of selecting the correct therapy on the basis of patient-specific biomarker may be a considerable step towards personalized psychiatry. Machine learning methods are gaining increasing popularity in the medical field. Once trained, the possibility to consider single patients in the analyses instead of whole groups makes them particularly appealing to investigate treatment response. Deep learning, a branch of machine learning, lately gained attention, due to its effectiveness in dealing with large neuroimaging data and to integrate them with clinical, molecular or -omics biomarkers.

METHODS

In this mini-review, we summarize studies that use deep learning methods to predict response to treatment in depression. We performed a bibliographic search on PUBMED, Google Scholar and Web of Science using the terms "psychiatry", "mood disorder", "depression", "treatment", "deep learning", "neural networks". Only studies considering patients' datasets are considered.

RESULTS

Eight studies met the inclusion criteria. Accuracies in prediction of response to therapy were considerably high in all studies, but results may be not easy to interpret.

LIMITATIONS

The major limitation for the current studies is the small sample size, which constitutes an issue for machine learning methods.

CONCLUSIONS

Deep learning shows promising results in terms of prediction of treatment response, often outperforming regression methods and reaching accuracies of around 80%. This could be of great help towards personalized medicine. However, more efforts are needed in terms of increasing datasets size and improved interpretability of results.

Designing a Personalized Health Dashboard: Interdisciplinary and Participatory Approach

Background

Within the Dutch Child Health Care (CHC), an online tool (360° CHILD-profile) is designed to enhance prevention and transformation toward personalized health care. From a personalized preventive perspective, it is of fundamental importance to timely identify children with emerging health problems interrelated to multiple health determinants. While digitalization of children’s health data is now realized, the accessibility of data remains a major challenge for CHC professionals, let alone for parents/youth. Therefore, the idea was initiated from CHC practice to develop a novel approach to make relevant information accessible at a glance.

Objective

This paper describes the stepwise development of a dashboard, as an example of using a design model to achieve visualization of a comprehensive overview of theoretically structured health data.

Methods

Developmental process is based on the nested design model with involvement of relevant stakeholders in a real-life context. This model considers immediate upstream validation within 4 cascading design levels: Domain Problem and Data Characterization, Operation and Data Type Abstraction, Visual Encoding and Interaction Design, and Algorithm Design. This model also includes impact-oriented downstream validation, which can be initiated after delivering the prototype.

Results

A comprehensible 360° CHILD-profile is developed: an online accessible visualization of CHC data based on the theoretical concept of the International Classification of Functioning, Disability and Health. This dashboard provides caregivers and parents/youth with a holistic view on children’s health and “entry points” for preventive, individualized health plans.

Conclusions

Describing this developmental process offers guidance on how to utilize the nested design model within a health care context.

Preschool Communication: Early Identification of Concerns About Preschool Language Development and Social Participation

Background: Adverse communication development in preschool children is a risk factor influencing child health and well-being with a negative impact on social participation. Language and social skills develop and maintain human adaptability over the life course. However, the accuracy of detecting language problems in asymptomatic children in primary care needs to be improved. Therefore, it is important to identify concerns about language development as a risk factor for child health. The association between parental and professional caregivers' concerns about language development and the level of preschool social participation was assessed, as well as the possible mediating/moderating effect of the perception of social competence. In addition, validity and predictive value of parental and professional caregivers' concerns about language development were tested. Methods: To identify emerging concerns about development and social participation, a community sample of 341 preschool children was systematically assessed with a comprehensive preventive child health care "toolkit" of instruments, including parent-completed tools like the Parents' Evaluation of Developmental Status (PEDS) and child competence Visual Analog Scales (VAS). At baseline, children were aged 3 years and at follow-up ~4 years. Results: There was a statistically significant association between parental and professional caregivers' concerns about language development and the level of preschool social participation, with a mediating effect of child social competence at the age of 3 years as well as 4 years. Negative predictive value of parental and professional caregiver language concerns at the age of 3 and 4 years were 99 and 97%, respectively. Furthermore, this article showed that while some preschool children grow out of language problems, others may develop them. Conclusion: Short but valid pediatric primary care tools like the PEDS and child competence VAS can support monitoring and early identification of concerns about language development and social competence as a risk factor for preschool social participation. Personalized health care requires continued communication between parents, professional caregivers and preventive child health care about parental and professional caregiver perceptions concerning preschool language development as well as the perception of a child's social competence.

Digital Twins, Internet of Things and Mobile Medicine: A Review of Current Platforms to Support Smart Healthcare

As the population grows, the need for higher-quality medical services increases, as well as the demand for information technology in medicine. The Smart Healthcare concept brings various approaches to address the acute problems encountered in modern healthcare. In this paper, we review the main problems of modern healthcare and analyze existing approaches and technologies in digital twins, the Internet of Things, and mobile medicine. We will also analyze the key features of modern platforms that support Mobile Health Applications. Finally, based on our analysis, we will propose the concept of Smart Healthcare Platform, focused on solving tasks related to supporting the development of Mobile Health Applications, including organizing access, management, and sharing of user data.

Advancing human health in the decade ahead: pregnancy as a key window for discovery: A Burroughs Wellcome Fund Pregnancy Think Tank

Recent revolutionary advances at the intersection of medicine, omics, data sciences, computing, epidemiology, and related technologies inspire us to ponder their impact on health. Their potential impact is particularly germane to the biology of pregnancy and perinatal medicine, where limited improvement in health outcomes for women and children has remained a global challenge. We assembled a group of experts to establish a Pregnancy Think Tank to discuss a broad spectrum of major gestational disorders and adverse pregnancy outcomes that affect maternal-infant lifelong health and should serve as targets for leveraging the many recent advances. This report reflects avenues for future effects that hold great potential in 3 major areas: developmental genomics, including the application of methodologies designed to bridge genotypes, physiology, and diseases, addressing vexing questions in early human development; gestational physiology, from immune tolerance to growth and the timing of parturition; and personalized and population medicine, focusing on amalgamating health record data and deep phenotypes to create broad knowledge that can be integrated into healthcare systems and drive discovery to address pregnancy-related disease and promote general health. We propose a series of questions reflecting development, systems biology, diseases, clinical approaches and tools, and population health, and a call for scientific action. Clearly, transdisciplinary science must advance and accelerate to address adverse pregnancy outcomes. Disciplines not traditionally involved in the reproductive sciences, such as computer science, engineering, mathematics, and pharmacology, should be engaged at the study design phase to optimize the information gathered and to identify and further evaluate potentially actionable therapeutic targets. Information sources should include noninvasive personalized sensors and monitors, alongside instructive "liquid biopsies" for noninvasive pregnancy assessment. Future research should also address the diversity of human cohorts in terms of geography, racial and ethnic distributions, and social and health disparities. Modern technologies, for both data-gathering and data-analyzing, make this possible at a scale that was previously unachievable. Finally, the psychosocial and economic environment in which pregnancy takes place must be considered to promote the health and wellness of communities worldwide.

Impedimetric Aptamer-Based Biosensors: Applications

Impedimetric aptamer-based biosensors show high potential for handheld devices and point-of-care tests. In this review, we report on recent advances in aptamer-based impedimetric biosensors for applications in biotechnology. We detail on analytes relevant in medical and environmental biotechnology as well as food control, for which aptamer-based impedimetric biosensors were developed. The reviewed biosensors are examined for their performance, including sensitivity, selectivity, response time, and real sample validation. Additionally, the benefits and challenges of impedimetric aptasensors are summarized.

An evaluation of the facilitator training to implement 'Taking charge of my life and health', a peer-led group program to promote self-care and patient empowerment in Veteran participants

OBJECTIVE

We developed a peer-led group program for Veterans called Taking Charge of My Life and Health (TCMLH) that emphasizes patient education, goal setting, shared decision making, and whole person care. Our aim was to conduct an evaluation of a facilitator training course to deliver TCMLH in VA sites.

METHODS

Repeated measures ANOVA models were used to examine change over three timepoints (pre-test, post-test, and two-month follow-up) in outcomes of attitudes, knowledge, skills, and self-efficacy related to patient empowerment, skills acquisition, self-care strategies, and curriculum facilitation. Qualitative data analysis of participant feedback was used to identify potential training adaptations and barriers to TCMLH delivery.

RESULTS

Our sample comprised 70 trainees who completed all three assessments. Participants reported high levels of training satisfaction, quality, and utility, and sustained improvements in knowledge of Whole Health, self-efficacy for group facilitation, and self-efficacy for using Whole Health concepts and tools. Implementation barriers included challenges related to group management and site logistics.

CONCLUSION

The facilitator training course improved knowledge and self-efficacy associated with successful peer-led program delivery and identified opportunities to improve the training course and TCMLH dissemination.

PRACTICE IMPLICATIONS

Findings provide insights on the design and implementation of training models to support peer-led programs.

An Ensemble Approach to Predict Schizophrenia Using Protein Data in the N-methyl-D-Aspartate Receptor (NMDAR) and Tryptophan Catabolic Pathways

In the wake of recent advances in artificial intelligence research, precision psychiatry using machine learning techniques represents a new paradigm. The D-amino acid oxidase (DAO) protein and its interaction partner, the D-amino acid oxidase activator (DAOA, also known as G72) protein, have been implicated as two key proteins in the N-methyl-D-aspartate receptor (NMDAR) pathway for schizophrenia. Another potential biomarker in regard to the etiology of schizophrenia is melatonin in the tryptophan catabolic pathway. To develop an ensemble boosting framework with random undersampling for determining disease status of schizophrenia, we established a prediction approach resulting from the analysis of genomic and demographic variables such as DAO levels, G72 levels, melatonin levels, age, and gender of 355 schizophrenia patients and 86 unrelated healthy individuals in the Taiwanese population. We compared our ensemble boosting framework with other state-of-the-art algorithms such as support vector machine, multilayer feedforward neural networks, logistic regression, random forests, naive Bayes, and C4.5 decision tree. The analysis revealed that the ensemble boosting model with random undersampling [area under the receiver operating characteristic curve (AUC) = 0.9242 ± 0.0652; sensitivity = 0.8580 ± 0.0770; specificity = 0.8594 ± 0.0760] performed maximally among predictive models to infer the complicated relationship between schizophrenia disease status and biomarkers. In addition, we identified a causal link between DAO and G72 protein levels in influencing schizophrenia disease status. The study indicates that the ensemble boosting framework with random undersampling may provide a suitable method to establish a tool for distinguishing schizophrenia patients from healthy controls using molecules in the NMDAR and tryptophan catabolic pathways.

Two Threats to Precision Medicine Equity

In January 2015, President Barack Obama unveiled the "Precision Medicine Initiative," a nationwide research effort to help bring an effective, preventive, and therapeutic approach to medicine. The purpose of the initiative is to bring a precise understanding of the genetic and environmental determinants of disease into clinical settings across the United States.¹ The announcement was coupled with $216 million provided in the President's proposed budget for a million-person national research cohort including public and private partnerships with academic medical centers, researchers, foundations, privacy experts, medical ethicists, and medical product innovators. The Initiative promises to expand the use of precision medicine in cancer research and modernize regulatory approval processes for genome sequencing technologies. In response, Congress passed the 21st Century Cures Act in December 2016, authorizing a total of $1.5 billion over 10 years for the program.² Although the Precision Medicine Initiative heralds great promise for the future of disease treatment and eradication, its implementation and development must be carefully guided to ensure that the millions of federal dollars expended will be spent equitably. This commentary discusses two key threats to the Precision Medicine Initiative's ability to proceed in a manner consistent with the United States Constitutional requirement that the federal government shall not "deny to any person . . . the equal protection of the laws."³ In short, this commentary sounds two cautionary notes, in order to advance precision medicine equity. First, achieving precision medicine equity will require scientists and clinicians to fulfill their intellectual, moral, and indeed legal duty to work against abusive uses of precision medicine science to advance distorted views of racial group variation. Precision medicine scientists must decisively denounce and distinguish this Initiative from the pseudo-science of eugenics - the immoral and deadly pseudo-science that gave racist and nationalist ideologies what Troy Duster called a "halo of legitimacy" during the first half of the 20th century.⁴ Second, to combat the social threat to precision medicine, scientists must incorporate a comprehensive, ecological understanding of the fundamental social and environmental determinants of health outcomes in all research. Only then will the Precision Medicine Initiative live up to its potential to improve and indeed transform health care delivery for all patients, regardless of race, color, or national origin.

Deep learning-based preoperative predictive analytics for patient-reported outcomes following lumbar discectomy: feasibility of center-specific modeling

BACKGROUND CONTEXT

There is considerable variability in patient-reported outcome measures following surgery for lumbar disc herniation. Individualized prediction tools that are derived from center- or even surgeon-specific data could provide valuable insights for shared decision-making.

PURPOSE

To evaluate the feasibility of deriving robust deep learning-based predictive analytics from single-center, single-surgeon data.

STUDY DESIGN

Derivation of predictive models from a prospective registry.

PATIENT SAMPLE

Patients who underwent single-level tubular microdiscectomy for lumbar disc herniation.

OUTCOME MEASURES

Numeric rating scales for leg and back pain severity and Oswestry Disability Index scores at 12 months postoperatively.

METHODS

Data were derived from a prospective registry. We trained deep neural network-based and logistic regression-based prediction models for patient-reported outcome measures. The primary endpoint was achievement of the minimum clinically important difference (MCID) in numeric rating scales and Oswestry Disability Index, defined as a 30% or greater improvement from baseline. Univariate predictors of MCID were also identified using conventional statistics.

RESULTS

A total of 422 patients were included (mean [SD] age: 48.5 [11.5] years; 207 [49%] female). After 1 year, 337 (80%), 219 (52%), and 337 (80%) patients reported a clinically relevant improvement in leg pain, back pain, and functional disability, respectively. The deep learning models predicted MCID with high area-under-the-curve of 0.87, 0.90, and 0.84, as well as accuracy of 85%, 87%, and 75%. The regression models provided inferior performance measures for each of the outcomes.

CONCLUSIONS

Our study demonstrates that generating personalized and robust deep learning-based analytics for outcome prediction is feasible even with limited amounts of center-specific data. With prospective validation, the ability to preoperatively and reliably inform patients about the likelihood of symptom improvement could prove useful in patient counselling and shared decision-making.

The Uncanny of the Illness Experience: Can Phenomenology Help?

The illness experience encompasses not only several changes in bodily processes but also the very feeling of becoming ill. This seemingly non-scientific aspect of being sick is characterized by forms of uncanny body experiences and an unhomelike being-in-the-world. Both include disconcerting phenomena, feelings of fear, restlessness, and inexplicability. In this paper we discuss some contributions aiming to understand the illness experience, focusing on the concept of the uncanny. This life event brings changes in the familiarity of our world, revelation of what previously was and should have remained hidden, loss of control, and the certainty of mortality. The experience of uncanniness is here conceptualized as a psychopathological phenomenon that should be regarded as a general symptom of diseases and should be identified and approached. We discuss the impact of these considerations on medical practice, focusing on the role of physicians and ultimately on the purpose of medicine.

Integration of Personalized Health Planning and Shared Medical Appointments for Patients with Type 2 Diabetes Mellitus

OBJECTIVES

This study describes the feasibility of implementing personalized health planning (PHP) within shared medical appointments (SMAs) for patients with type 2 diabetes mellitus. The PHP-SMA approach was designed to synergize the benefits of SMAs with those of PHP, enabling greater patient engagement focused on meeting individualized therapeutic goals in a group setting.

METHODS

Patients were assigned randomly to a PHP-SMA or a standard eight-session SMA series. Standard SMAs included an interactive educational curriculum delivered in group medical encounters. The PHP-SMA included the addition of a patient self-assessment, health risk assessment, shared patient-provider goal setting, creation of a personal health plan, and follow-up on clinical progress. Clinical and patient-reported outcomes and qualitative data from focus groups with patients, providers, and administrative staff were used for evaluation. Qualitative data explored facilitators and barriers to implementation of the PHP-SMA. The Consolidated Framework for Implementation Research was used to provide insight into implementation factors.

RESULTS

PHP was successfully integrated into SMAs in a primary care setting. Patients in the PHP-SMA (n = 12) were more likely to attend ≥5 sessions than patients assigned to the standard SMA (n = 7; 58% PHP, 28.5% control). Qualitative data evaluation described the advantages and barriers to PHP, the team-based approach to care, and patient participation. The PHP-SMA group experienced reductions in hemoglobin A1c, low-density lipoprotein, blood pressure, and body mass index, as well as successful attainment of health goals.

CONCLUSIONS

The PHP-SMA is a proactive and participatory approach to chronic care delivery that synergizes the benefits of PHP within SMAs. This study describes the components of this intervention; collects evidence on feasibility, acceptability, and clinical outcomes; and identifies implementation barriers and facilitators. The PHP-SMA warrants further evaluation as an approach to improve health outcomes in patients with common chronic conditions.

Personalized medicine and chronic obstructive pulmonary disease

PURPOSE OF REVIEW

The current review summarizes ongoing developments in personalized medicine and precision medicine in chronic obstructive pulmonary disease (COPD). Our current approach is far away of personalized management algorithms as current recommendations for COPD are largely based on a reductionist disease description, operationally defined by results of spirometry.

RECENT FINDINGS

Besides precision medicine developments, a personalized medicine approach in COPD is described based on a holistic approach of the patient and considering illness as the consequence of dynamic interactions within and between multiple interacting and self-adjusting systems. Pulmonary rehabilitation is described as a model of personalized medicine. Largely based on current understanding of inflammatory processes in COPD, targeted interventions in COPD are reviewed. Augmentation therapy for α-1-antitrypsine deficiency is described as model of precision medicine in COPD based in profound understanding of the related genetic endotype.

SUMMARY

Future developments of precision medicine in COPD require identification of relevant endotypes combined with proper identification of phenotypes involved in the complex and heterogeneous manifestations of COPD.

Fundamentals and commercial aspects of nanobiosensors in point-of-care clinical diagnostics

Among various problems faced by mankind, health-related concerns are prevailing since long which are commonly found in the form of infectious diseases and different metabolic disorders. The clinical cure and management of such abnormalities are greatly dependent on the availability of their diagnoses. The conventional diagnostics used for such purposes are extremely powerful; however, most of these are limited by time-consuming protocols and require higher volume of test sample, etc. A new evolving technology called "biosensor" in this context shows an enormous potential for an alternative diagnostic device, which constantly compliments the conventional diagnoses. In this review, we have summarized different kinds of biosensors and their fundamental understanding with various state-of-the-art examples. A critical examination of different types of biosensing mechanisms is also reported highlighting the advantages of electrochemical biosensors for its great potentials in next-generation commercially viable modules. In recent years, a number of nanomaterials are extensively used to enhance not only the performance of biosensing mechanism, but also obtain robust, cheap, and fabrication-friendly durable mechanism. Herein, we have summarized the importance of nanomaterials in biosensing mechanism, their syntheses as well as characterization techniques. Subsequently, we have discussed the probe fabrication processes along with various techniques for assessing its analytical performances and potentials for commercial viability.

A Deep Learning Approach for Predicting Antidepressant Response in Major Depression Using Clinical and Genetic Biomarkers

In the wake of recent advances in scientific research, personalized medicine using deep learning techniques represents a new paradigm. In this work, our goal was to establish deep learning models which distinguish responders from non-responders, and also to predict possible antidepressant treatment outcomes in major depressive disorder (MDD). To uncover relationships between the responsiveness of antidepressant treatment and biomarkers, we developed a deep learning prediction approach resulting from the analysis of genetic and clinical factors such as single nucleotide polymorphisms (SNPs), age, sex, baseline Hamilton Rating Scale for Depression score, depressive episodes, marital status, and suicide attempt status of MDD patients. The cohort consisted of 455 patients who were treated with selective serotonin reuptake inhibitors (treatment-response rate = 61.0%; remission rate = 33.0%). By using the SNP dataset that was original to a genome-wide association study, we selected 10 SNPs (including ABCA13 rs4917029, BNIP3 rs9419139, CACNA1E rs704329, EXOC4 rs6978272, GRIN2B rs7954376, LHFPL3 rs4352778, NELL1 rs2139423, NUAK1 rs2956406, PREX1 rs4810894, and SLIT3 rs139863958) which were associated with antidepressant treatment response. Furthermore, we pinpointed 10 SNPs (including ARNTL rs11022778, CAMK1D rs2724812, GABRB3 rs12904459, GRM8 rs35864549, NAALADL2 rs9878985, NCALD rs483986, PLA2G4A rs12046378, PROK2 rs73103153, RBFOX1 rs17134927, and ZNF536 rs77554113) in relation to remission. Then, we employed multilayer feedforward neural networks (MFNNs) containing 1-3 hidden layers and compared MFNN models with logistic regression models. Our analysis results revealed that the MFNN model with 2 hidden layers (area under the receiver operating characteristic curve (AUC) = 0.8228 ± 0.0571; sensitivity = 0.7546 ± 0.0619; specificity = 0.6922 ± 0.0765) performed maximally among predictive models to infer the complex relationship between antidepressant treatment response and biomarkers. In addition, the MFNN model with 3 hidden layers (AUC = 0.8060 ± 0.0722; sensitivity = 0.7732 ± 0.0583; specificity = 0.6623 ± 0.0853) achieved best among predictive models to predict remission. Our study indicates that the deep MFNN framework may provide a suitable method to establish a tool for distinguishing treatment responders from non-responders prior to antidepressant therapy.

Precision Medicine and Personalized Medicine in Cardiovascular Disease

Precision medicine aims to offer "the right treatment to the right patient at the right time." In cardiovascular medicine the potential of precision medicine applies to all stages of the disease development and includes risk prediction, preventative measures, and targeted therapeutic approaches. Precision medicine will benefit from new developments in the area of genomics and other omics but equally heavily depends on established biomarkers, functional tests, and imaging. Cardiovascular medicine often relies on noninvasive diagnostic procedures and symptom-based disease management. In contrast, other clinical disciplines including oncology and immunology have already moved to molecular diagnostics that lend themselves to precision medicine approaches. There are opportunities to implement precision medicine approaches by focusing on common diseases such as hypertension, conditions with diagnostic and prognostic uncertainty such as angina, and conditions that are associated with high mortality and involve costly and potentially harmful interventions such as dilated cardiomyopathy and cardiac resynchronization therapy. Sex and gender issues have not yet been fully explored in precision medicine although the opportunity to use molecular data to more accurately manage men and women with cardiovascular disease has been acknowledged. A mindshift is required in order to fully exploit the potential of precision medicine to tackle the global burden of cardiovascular diseases.

Research and Discovery Science and the Future of Dental Education and Practice

Dental graduates of 2040 will face new and complex challenges. If they are to meet these challenges, dental schools must develop a research and discovery mission that will equip graduates with the new knowledge required to function in a modern health care environment. The dental practitioner of 2040 will place greater emphasis on risk assessment, disease prevention, and health maintenance; and the emerging discipline of precision medicine and systems biology will revolutionize disease diagnosis and reveal new targeted therapies. The dental graduate of 2040 will be expected to function effectively in a collaborative, learning health care system and to understand the impact of health care policy on local, national, and global communities. Emerging scientific fields such as big data analytics, stem cell biology, tissue engineering, and advanced biomimetics will impact dental practice. Despite all the warning signs indicating how the changing scientific and heath care landscape will dramatically alter dental education and dental practice, dental schools have yet to reconsider their research and educational priorities and clinical practice objectives. Until dental schools and the practicing community come to grips with these challenges, this persistent attitude of complacency will likely be at the dental profession's peril. This article was written as part of the project "Advancing Dental Education in the 21^st Century."

Oral Health Research and Scholarship in 2040: Executive Summary

This executive summary for Section 6 of the "Advancing Dental Education in the 21^st Century" project provides an overview of five background articles that address the role of research and scholarship in dental education in the year 2040. Beginning with a historical account of research and discovery science in dentistry's evolution as a profession, the article then reviews the role of early thought leaders and organized dentistry in establishing research as a cornerstone of dental education and dental practice. The dental research workforce faces an uncertain future fueled by a volatile funding environment and inadequate mentoring and training of research faculty. Dental schools must forge stronger academic and scientific ties to their university and academic health centers and will be challenged to develop sustainable research and patient care collaborations with other health professions. The changing health care environment will create new opportunities for oral health care providers to expand their scope of practice and focus on prevention and screening for non-communicable chronic diseases. Dental practitioners in the future are likely to place greater emphasis on managing the overall health of their patients while promoting closer integration with other health professionals. All dental schools must develop a sustainable research mission if they hope to graduate dentists who function effectively in a collaborative health care environment. The changing scientific and health care landscape will dramatically alter dental education and dental practice. Dental schools need to reconsider their research and educational priorities and clinical practice objectives. Until dental schools and the practicing community come to grips with these challenges, a persistent attitude of complacency will likely be at the dental profession's peril.

Paper based diagnostics for personalized health care: Emerging technologies and commercial aspects

Personalized health care (PHC) is being appreciated globally to combat clinical complexities underlying various metabolic or infectious disorders including diabetes, cardiovascular, communicable diseases etc. Effective diagnoses majorly depend on initial identification of the causes which are nowadays being practiced in disease-oriented approach, where personal health profile is often overlooked. The adoption of PHC has shown significantly improved diagnoses in various conditions including emergency, ambulatory, and remote area. PHC includes personalized health monitoring (PHM), which is its integral part and may provide valuable information's on various clinical conditions. In PHC, bio-fluids are analyzed using various diagnostic devices including lab based equipment and biosensors. Among all types of biosensing systems, paper based biosensors are commercially attracted due to its portability, easy availability, cheaper manufacturing cost, and transportability. Not only these, various intrinsic properties of paper has facilitated the development of paper based miniaturized sensors, which has recently gained ASSURED (Affordable, Sensitive, Specific, User-friendly, Rapid and Robust, Equipment free, Deliverable to all end-users) status for point of care diagnosis in miniaturized settings. In this review, importance of paper based biosensors and their compatibility for affordable and low cost diagnostics has been elaborated with various examples. Limitations and strategies to overcome the challenges of paper biosensor have also been discussed. We have provided elaborated tables which describe the types, model specifications, sensing mechanisms, target biomarkers, and analytical performance of the paper biosensors with their respective applications in real sample matrices. Different commercial aspects of paper biosensor have also been explained using SWOT (Strength, Weakness, Opportunities, Threats) analysis.

Patient Similarity in Prediction Models Based on Health Data: A Scoping Review

Background

Physicians and health policy makers are required to make predictions during their decision making in various medical problems. Many advances have been made in predictive modeling toward outcome prediction, but these innovations target an average patient and are insufficiently adjustable for individual patients. One developing idea in this field is individualized predictive analytics based on patient similarity. The goal of this approach is to identify patients who are similar to an index patient and derive insights from the records of similar patients to provide personalized predictions..

Objective

The aim is to summarize and review published studies describing computer-based approaches for predicting patients’ future health status based on health data and patient similarity, identify gaps, and provide a starting point for related future research.

Methods

The method involved (1) conducting the review by performing automated searches in Scopus, PubMed, and ISI Web of Science, selecting relevant studies by first screening titles and abstracts then analyzing full-texts, and (2) documenting by extracting publication details and information on context, predictors, missing data, modeling algorithm, outcome, and evaluation methods into a matrix table, synthesizing data, and reporting results.

Results

After duplicate removal, 1339 articles were screened in abstracts and titles and 67 were selected for full-text review. In total, 22 articles met the inclusion criteria. Within included articles, hospitals were the main source of data (n=10). Cardiovascular disease (n=7) and diabetes (n=4) were the dominant patient diseases. Most studies (n=18) used neighborhood-based approaches in devising prediction models. Two studies showed that patient similarity-based modeling outperformed population-based predictive methods.

Conclusions

Interest in patient similarity-based predictive modeling for diagnosis and prognosis has been growing. In addition to raw/coded health data, wavelet transform and term frequency-inverse document frequency methods were employed to extract predictors. Selecting predictors with potential to highlight special cases and defining new patient similarity metrics were among the gaps identified in the existing literature that provide starting points for future work. Patient status prediction models based on patient similarity and health data offer exciting potential for personalizing and ultimately improving health care, leading to better patient outcomes.

Machine learning and systems genomics approaches for multi-omics data

In light of recent advances in biomedical computing, big data science, and precision medicine, there is a mammoth demand for establishing algorithms in machine learning and systems genomics (MLSG), together with multi-omics data, to weigh probable phenotype-genotype relationships. Software frameworks in MLSG are extensively employed to analyze hundreds of thousands of multi-omics data by high-throughput technologies. In this study, we reviewed the MLSG software frameworks and future directions with respect to multi-omics data analysis and integration. Our review was targeted at researching recent approaches and technical solutions for the MLSG software frameworks using multi-omics platforms.

Crossing the Boundaries of Our Current Healthcare System by Integrating Ultra-Weak Photon Emissions with Metabolomics

The current healthcare system is hampered by a reductionist approach in which diagnostics and interventions focus on a specific target, resulting in medicines that center on generic, static phenomena while excluding inherent dynamic nature of biological processes, let alone psychosocial parameters. In this essay, we present some limitations of the current healthcare system and introduce the novel and potential approach of combining ultra-weak photon emission (UPE) with metabolomics technology in order to provide a dynamic readout of higher organizational systems. We argue that the combination of metabolomics and UPE can bring a new, broader, view of health state and can potentially help to shift healthcare toward more personalized approach that improves patient well-being.

Other side of the coin for personalised medicine and healthcare: content analysis of 'personalised' practices in the literature

OBJECTIVES

Various terms and definitions are used to describe personalised approaches to medicine and healthcare, but in ambiguous and inconsistent ways. They mostly have been defined in a top-down manner. However, actual practices might take different paths. Here, we aimed to provide a 'practice-based' perspective on the debate by analysing the content of 'personalised' practices published in the literature.

METHODS

The search in PubMed and EMBASE (April 2014) using the terms frequently used for personalised approaches resulted in 5333 records. 2 independent researchers used different strategies for screening, resulting in 157 articles describing 88 'personalised' practices that were implemented/presented on at least 1 individual/patient case. The content analysis was grounded on these data and did not have a priori analytical frameworks.

RESULTS

'Personalised medicine/healthcare' can be a commodity in the healthcare market, a way how health services are provided, or a keyword for emerging applications. It can help individuals/patients to gain control of their health, health professionals to provide better services, healthcare organisations to increase effectiveness and efficiency, or national health systems to increase performance. Country examples indicated that for integration of practices into health services, attitude towards innovations and health system and policy context is important. Categorisation based on the terms or the technologies used, if any, was not possible.

CONCLUSIONS

This study is the first to provide a comprehensive content analysis of the 'personalised' practices in the literature. Unlike the top-down definitions, our findings highlighted not the technologies but real-life issues faced by the practices. 'Personalised medicine' and 'personalised healthcare' can be differentiated by using the former for specific tools available and the latter for health services with a holistic approach, implemented in certain contexts. To realise integration of 'personalised medicine/healthcare' into real life, science, technology, health policy and practice, and society domains must work together.