Use of deep learning to develop continuous-risk models for adverse event prediction from electronic health records

Machine learning in infectious diseases: potential applications and limitations

Infectious diseases are a major threat for human and animal health worldwide. Artificial Intelligence (AI) combined algorithms including Machine Learning and Big Data analytics have emerged as a potential solution to analyse diverse datasets and face challenges posed by infectious diseases. In this commentary we explore the potential applications and limitations of ML to management of infectious disease. It explores challenges in key areas such as outbreak prediction, pathogen identification, drug discovery, and personalized medicine. We propose potential solutions to mitigate these hurdles and applications of ML to identify biomolecules for effective treatment and prevention of infectious diseases. In addition to use of ML for management of infectious diseases, potential applications are based on catastrophic evolution events for the identification of biomolecular targets to reduce risks for infectious diseases and vaccinomics for discovery and characterization of vaccine protective antigens using intelligent Big Data analytics techniques. These considerations set a foundation for developing effective strategies for managing infectious diseases in the future.

Derivation and Validation of a Machine Learning Model for the Prevention of Unplanned Dialysis

Key Points

Background

Approximately half of all patients with advanced CKD who progress to kidney failure initiate dialysis in an unplanned fashion, which is associated with high morbidity, mortality, and health care costs. A novel prediction model designed to identify patients with advanced CKD who are at high risk for developing kidney failure over short time frames (6–12 months) may help reduce the rates of unplanned dialysis and improve the quality of transitions from CKD to kidney failure.

Methods

We performed a retrospective study using machine learning random forest algorithms incorporating routinely collected age and sex data along with time-varying trends in laboratory measurements to derive and validate 6- and 12-month kidney failure risk prediction models in the population with advanced CKD. The models were comprehensively characterized in three independent cohorts in Ontario, Canada—derived in a cohort of 1849 consecutive patients with advanced CKD (mean [SD] age 66 [15] years, eGFR 19 [7] ml/min per 1.73 m2) and validated in two external advanced CKD cohorts (n=1356; age 69 [14] years, eGFR 22 [7] ml/min per 1.73 m2).

Results

Across all cohorts, 55% of patients experienced kidney failure, of whom 35% involved unplanned dialysis. The 6- and 12-month models demonstrated excellent discrimination with area under the receiver operating characteristic curve of 0.88 (95% confidence interval [CI], 0.87 to 0.89) and 0.87 (95% CI, 0.86 to 0.87) along with high probabilistic accuracy with the Brier scores of 0.10 (95% CI, 0.09 to 0.10) and 0.14 (95% CI, 0.13 to 0.14), respectively. The models were also well calibrated and delivered timely alerts on a significant number of patients who ultimately initiated dialysis in an unplanned fashion. Similar results were found upon external validation testing.

Conclusions

These machine learning models using routinely collected patient data accurately predict near-future kidney failure risk among the population with advanced CKD and retrospectively deliver advanced warning on a substantial proportion of unplanned dialysis events. Optimal implementation strategies still need to be elucidated.

Artificial intelligence in neurology: opportunities, challenges, and policy implications

Neurological conditions are the leading cause of disability and mortality combined, demanding innovative, scalable, and sustainable solutions. Brain health has become a global priority with adoption of the World Health Organization's Intersectoral Global Action Plan in 2022. Simultaneously, rapid advancements in artificial intelligence (AI) are revolutionizing neurological research and practice. This scoping review of 66 original articles explores the value of AI in neurology and brain health, systematizing the landscape for emergent clinical opportunities and future trends across the care trajectory: prevention, risk stratification, early detection, diagnosis, management, and rehabilitation. AI's potential to advance personalized precision neurology and global brain health directives hinges on resolving core challenges across four pillars-models, data, feasibility/equity, and regulation/innovation-through concerted pursuit of targeted recommendations. Paramount actions include swift, ethical, equity-focused integration of novel technologies into clinical workflows, mitigating data-related issues, counteracting digital inequity gaps, and establishing robust governance frameworks balancing safety and innovation.

Quantitative methods for optimizing patient outcomes in liver transplantation

Liver transplantation (LT) is a lifesaving yet complex intervention with considerable challenges impacting graft and patient outcomes. Despite best practices, 5-year graft survival is only 70%. Sophisticated quantitative techniques offer potential solutions by assimilating multifaceted data into insights exceeding human cognition. Optimizing donor-recipient matching and graft allocation presents additional intricacies, involving the integration of clinical and laboratory data to select the ideal donor and recipient pair. Allocation must balance physiological variables with geographical and logistical constraints and timing. Quantitative methods can integrate these complex factors to optimize graft utilization. Such methods can also aid in personalizing treatment regimens, drawing on both pretransplant and posttransplant data, possibly using continuous immunological monitoring to enable early detection of graft injury or infected states. Advanced analytics is thus poised to transform management in LT, maximizing graft and patient survival. In this review, we describe quantitative methods applied to organ transplantation, with a focus on LT. These include quantitative methods for (1) utilizing and allocating donor organs equitably and optimally, (2) improving surgical planning through preoperative imaging, (3) monitoring graft and immune status, (4) determining immunosuppressant doses, and (5) establishing and maintaining the health of graft and patient after LT.

Subtle variation in sepsis-III definitions markedly influences predictive performance within and across methods

Early detection of sepsis is key to ensure timely clinical intervention. Since very few end-to-end pipelines are publicly available, fair comparisons between methodologies are difficult if not impossible. Progress is further limited by discrepancies in the reconstruction of sepsis onset time. This retrospective cohort study highlights the variation in performance of predictive models under three subtly different interpretations of sepsis onset from the sepsis-III definition and compares this against inter-model differences. The models are chosen to cover tree-based, deep learning, and survival analysis methods. Using the MIMIC-III database, between 867 and 2178 intensive care unit admissions with sepsis were identified, depending on the onset definition. We show that model performance can be more sensitive to differences in the definition of sepsis onset than to the model itself. Given a fixed sepsis definition, the best performing method had a gain of 1-5% in the area under the receiver operating characteristic (AUROC). However, the choice of onset time can cause a greater effect, with variation of 0-6% in AUROC. We illustrate that misleading conclusions can be drawn if models are compared without consideration of the sepsis definition used which emphasizes the need for a standardized definition for sepsis onset.

Private Continuous Survival Analysis with Distributed Multi-Site Data

Effective disease surveillance systems require large-scale epidemiological data to improve health outcomes and quality of care for the general population. As data may be limited within a single site, multi-site data (e.g., from a number of local/regional health systems) need to be considered. Leveraging distributed data across multiple sites for epidemiological analysis poses significant challenges. Due to the sensitive nature of epidemiological data, it is imperative to design distributed solutions that provide strong privacy protections. Current privacy solutions often assume a central site, which is responsible for aggregating the distributed data and applying privacy protection before sharing the results (e.g., aggregation via secure primitives and differential privacy for sharing aggregate results). However, identifying such a central site may be difficult in practice and relying on a central site may introduce potential vulnerabilities (e.g., single point of failure). Furthermore, to support clinical interventions and inform policy decisions in a timely manner, epidemiological analysis need to reflect dynamic changes in the data. Yet, existing distributed privacy-protecting approaches were largely designed for static data (e.g., one-time data sharing) and cannot fulfill dynamic data requirements. In this work, we propose a privacy-protecting approach that supports the sharing of dynamic epidemiological analysis and provides strong privacy protection in a decentralized manner. We apply our solution in continuous survival analysis using the Kaplan-Meier estimation model while providing differential privacy protection. Our evaluations on a real dataset containing COVID-19 cases show that our method provides highly usable results.

Development of an automated, general-purpose prediction tool for postoperative respiratory failure using machine learning: A retrospective cohort study

STUDY OBJECTIVE

Postoperative respiratory failure is a major surgical complication and key quality metric. Existing prediction tools underperform, are limited to specific populations, and necessitate manual calculation. This limits their implementation. We aimed to create an improved, machine learning powered prediction tool with ideal characteristics for automated calculation.

DESIGN, SETTING, AND PATIENTS

We retrospectively reviewed 101,455 anesthetic procedures from 1/2018 to 6/2021. The primary outcome was the Standardized Endpoints in Perioperative Medicine consensus definition for postoperative respiratory failure. Secondary outcomes were respiratory quality metrics from the National Surgery Quality Improvement Sample, Society of Thoracic Surgeons, and CMS. We abstracted from the electronic health record 26 procedural and physiologic variables previously identified as respiratory failure risk factors. We randomly split the cohort and used the Random Forest method to predict the composite outcome in the training cohort. We coined this the RESPIRE model and measured its accuracy in the validation cohort using area under the receiver operating curve (AUROC) analysis, among other measures, and compared this with ARISCAT and SPORC-1, two leading prediction tools. We compared performance in a validation cohort using score cut-offs determined in a separate test cohort.

MAIN RESULTS

The RESPIRE model exhibited superior accuracy with an AUROC of 0.93 (95% CI, 0.92-0.95) compared to 0.82 for both ARISCAT and SPORC-1 (P-for-difference < 0.0001 for both). At comparable 80-90% sensitivities, RESPIRE had higher positive predictive value (11%, 95% CI: 10-12%) and lower false positive rate (12%, 95% CI: 12-13%) compared to 4% and 37% for both ARISCAT and SPORC-1. The RESPIRE model also better predicted the established quality metrics for postoperative respiratory failure.

CONCLUSIONS

We developed a general-purpose, machine learning powered prediction tool with superior performance for research and quality-based definitions of postoperative respiratory failure.

The Role of Data Science in Closing the Implementation Gap

Data science has the potential to greatly enhance efforts to translate evidence into practice in critical care. The intensive care unit is a data-rich environment enabling insight into both patient-level care patterns and clinician-level treatment patterns. By applying artificial intelligence to these novel data sources, implementation strategies can be tailored to individual patients, individual clinicians, and individual situations, revealing when evidence-based practices are missed and facilitating context-sensitive clinical decision support. To achieve these goals, technology developers should work closely with clinicians to create unbiased applications that are integrated into the clinical workflow.

Germline mechanisms of immunotherapy toxicities in the era of genome-wide association studies

Cancer immunotherapy has revolutionized the treatment of advanced cancers and is quickly becoming an option for early-stage disease. By reactivating the host immune system, immunotherapy harnesses patients' innate defenses to eradicate the tumor. By putatively similar mechanisms, immunotherapy can also substantially increase the risk of toxicities or immune-related adverse events (irAEs). Severe irAEs can lead to hospitalization, treatment discontinuation, lifelong immune complications, or even death. Many irAEs present with similar symptoms to heritable autoimmune diseases, suggesting that germline genetics may contribute to their onset. Recently, genome-wide association studies (GWAS) of irAEs have identified common germline associations and putative mechanisms, lending support to this hypothesis. A wide range of well-established GWAS methods can potentially be harnessed to understand the etiology of irAEs specifically and immunotherapy outcomes broadly. This review summarizes current findings regarding germline effects on immunotherapy outcomes and discusses opportunities and challenges for leveraging germline genetics to understand, predict, and treat irAEs.

Machine-learning-based adverse drug event prediction from observational health data: A review

Adverse drug events (ADEs) are responsible for a significant number of hospital admissions and fatalities. Machine learning models have been developed to assess the individual patient risk of having an ADE. In this article, we have reviewed studies addressing the prediction of ADEs in observational health data with machine learning. The field of individualised ADE prediction is rapidly emerging through the increasing availability of additional data modalities (e.g., genetic data, screening data, wearables data) and advanced deep learning models such as transformers. Consequently, personalised adverse drug event predictions are becoming more feasible and tangible.

Large language models encode clinical knowledge

Large language models (LLMs) have demonstrated impressive capabilities, but the bar for clinical applications is high. Attempts to assess the clinical knowledge of models typically rely on automated evaluations based on limited benchmarks. Here, to address these limitations, we present MultiMedQA, a benchmark combining six existing medical question answering datasets spanning professional medicine, research and consumer queries and a new dataset of medical questions searched online, HealthSearchQA. We propose a human evaluation framework for model answers along multiple axes including factuality, comprehension, reasoning, possible harm and bias. In addition, we evaluate Pathways Language Model1 (PaLM, a 540-billion parameter LLM) and its instruction-tuned variant, Flan-PaLM2 on MultiMedQA. Using a combination of prompting strategies, Flan-PaLM achieves state-of-the-art accuracy on every MultiMedQA multiple-choice dataset (MedQA3, MedMCQA4, PubMedQA5 and Measuring Massive Multitask Language Understanding (MMLU) clinical topics6), including 67.6% accuracy on MedQA (US Medical Licensing Exam-style questions), surpassing the prior state of the art by more than 17%. However, human evaluation reveals key gaps. To resolve this, we introduce instruction prompt tuning, a parameter-efficient approach for aligning LLMs to new domains using a few exemplars. The resulting model, Med-PaLM, performs encouragingly, but remains inferior to clinicians. We show that comprehension, knowledge recall and reasoning improve with model scale and instruction prompt tuning, suggesting the potential utility of LLMs in medicine. Our human evaluations reveal limitations of today's models, reinforcing the importance of both evaluation frameworks and method development in creating safe, helpful LLMs for clinical applications.

Predicting in-hospital outcomes of patients with acute kidney injury

Acute kidney injury (AKI) is prevalent and a leading cause of in-hospital death worldwide. Early prediction of AKI-related clinical events and timely intervention for high-risk patients could improve outcomes. We develop a deep learning model based on a nationwide multicenter cooperative network across China that includes 7,084,339 hospitalized patients, to dynamically predict the risk of in-hospital death (primary outcome) and dialysis (secondary outcome) for patients who developed AKI during hospitalization. A total of 137,084 eligible patients with AKI constitute the analysis set. In the derivation cohort, the area under the receiver operator curve (AUROC) for 24-h, 48-h, 72-h, and 7-day death are 95·05%, 94·23%, 93·53%, and 93·09%, respectively. For dialysis outcome, the AUROC of each time span are 88·32%, 83·31%, 83·20%, and 77·99%, respectively. The predictive performance is consistent in both internal and external validation cohorts. The model can predict important outcomes of patients with AKI, which could be helpful for the early management of AKI.

Machine Learning Algorithms to Predict Breast Cancer Recurrence Using Structured and Unstructured Sources from Electronic Health Records

Recurrence is a critical aspect of breast cancer (BC) that is inexorably tied to mortality. Reuse of healthcare data through Machine Learning (ML) algorithms offers great opportunities to improve the stratification of patients at risk of cancer recurrence. We hypothesized that combining features from structured and unstructured sources would provide better prediction results for 5-year cancer recurrence than either source alone. We collected and preprocessed clinical data from a cohort of BC patients, resulting in 823 valid subjects for analysis. We derived three sets of features: structured information, features from free text, and a combination of both. We evaluated the performance of five ML algorithms to predict 5-year cancer recurrence and selected the best-performing to test our hypothesis. The XGB (eXtreme Gradient Boosting) model yielded the best performance among the five evaluated algorithms, with precision = 0.900, recall = 0.907, F1-score = 0.897, and area under the receiver operating characteristic AUROC = 0.807. The best prediction results were achieved with the structured dataset, followed by the unstructured dataset, while the combined dataset achieved the poorest performance. ML algorithms for BC recurrence prediction are valuable tools to improve patient risk stratification, help with post-cancer monitoring, and plan more effective follow-up. Structured data provides the best results when fed to ML algorithms. However, an approach based on natural language processing offers comparable results while potentially requiring less mapping effort.

A universal AutoScore framework to develop interpretable scoring systems for predicting common types of clinical outcomes

The AutoScore framework can automatically generate data-driven clinical scores in various clinical applications. Here, we present a protocol for developing clinical scoring systems for binary, survival, and ordinal outcomes using the open-source AutoScore package. We describe steps for package installation, detailed data processing and checking, and variable ranking. We then explain how to iterate through steps for variable selection, score generation, fine-tuning, and evaluation to generate understandable and explainable scoring systems using data-driven evidence and clinical knowledge. For complete details on the use and execution of this protocol, please refer to Xie et al. (2020),¹ Xie et al. (2022)², Saffari et al. (2022)³ and the online tutorial https://nliulab.github.io/AutoScore/.

AI-assisted prediction of differential response to antidepressant classes using electronic health records

Antidepressant selection is largely a trial-and-error process. We used electronic health record (EHR) data and artificial intelligence (AI) to predict response to four antidepressants classes (SSRI, SNRI, bupropion, and mirtazapine) 4 to 12 weeks after antidepressant initiation. The final data set comprised 17,556 patients. Predictors were derived from both structured and unstructured EHR data and models accounted for features predictive of treatment selection to minimize confounding by indication. Outcome labels were derived through expert chart review and AI-automated imputation. Regularized generalized linear model (GLM), random forest, gradient boosting machine (GBM), and deep neural network (DNN) models were trained and their performance compared. Predictor importance scores were derived using SHapley Additive exPlanations (SHAP). All models demonstrated similarly good prediction performance (AUROCs ≥ 0.70, AUPRCs ≥ 0.68). The models can estimate differential treatment response probabilities both between patients and between antidepressant classes for the same patient. In addition, patient-specific factors driving response probabilities for each antidepressant class can be generated. We show that antidepressant response can be accurately predicted from real-world EHR data with AI modeling, and our approach could inform further development of clinical decision support systems for more effective treatment selection.

Culture intelligent workflow, structure, and steps

Introduction

Technologies abstract intelligence and provide predictor and precision insight in workflows that manage disorders, similar to cardiology and hematological disease. Positive perceptions of Artificial Intelligence (AI) that support Machine Learning (ML) and Deep Learning (DL) manage transformations with a safe system that improves wellbeing. In sections, workflow introduces an eXamination (X = AI) as an end-to-end structure to culture workstreams in a step-by-step design to manage populace health in a governed system.

Method

To better healthcare outcomes, communities and personnel benefit from an explanation and an interpretive that elucidates workflow for citizens or practitioners to comprehend personalized platforms. Therefore, the author undertook structure and practice reviews and appraised perspectives that impact the management of AI in public health and medicine.

Results

Figures for the management of AI workflow illustrate and inform on the model, structure, culture, assurance, process steps, values, and governance required for abstract insights in public health and medicine. The papers' end-to-end structure with explanans in a work culture interprets the step-by-step designs that manage the success of AI. Personalized care graphics offer an explanandum in the management of biological analytic value.

Discussion

Healthcare leadership collaboratives plan population health with an upstream, workplace and workstream format. Secure workflow and safety wellbeing system requirements prove that genomics and AI improve medicine. Therefore, the paper discusses group understanding of current practice, ethics, policy, and legality.

Conclusion

"Culture, intelligent workflow, structure, and steps" improve wellbeing with personalized care and align a percept for national opportunities, regional control, and local needs. Personalized practice cultures support analytic systems to describe, predict, precision, and prescript medicine in population health management eXaminations.

Machine learning applied to electronic health record data in home healthcare: A scoping review

OBJECTIVE

Despite recent calls for home healthcare (HHC) to integrate informatics, the application of machine learning in HHC is relatively unknown. Thus, this study aimed to synthesize and appraise the literature describing the application of machine learning to predict adverse outcomes (e.g., hospitalization, mortality) using electronic health record (EHR) data in the HHC setting. Our secondary aim was to evaluate the comprehensiveness of predictors used in the machine learning algorithms guided by the Biopsychosocial Model.

METHODS

During March 2022 we conducted a literature search in four databases: PubMed, Embase, CINAHL, and Scopus. Inclusion criteria were 1) describing services provided in the HHC setting, 2) applying machine learning algorithms to predict adverse outcomes, defined as outcomes related to patient deterioration, 3) using EHR data and 4) focusing on the adult population. Predictors were mapped to the Biopsychosocial Model. A risk of bias analysis was conducted using the Prediction Model Risk Of Bias Assessment Tool.

RESULTS

The final sample included 20 studies. Eighteen studies used predictors from standardized assessments integrated in the EHR. The most common outcome of interest was hospitalization (55%), followed by mortality (25%). Psychological predictors were frequently excluded (35%). Tree based algorithms were most frequently applied (75%). Most studies demonstrated high or unclear risk of bias (75%).

CONCLUSION

Future studies in HHC should consider incorporating machine learning algorithms into clinical decision support systems to identify patients at risk. Based on the Biopsychosocial model, psychological and interpersonal characteristics should be used along with biological characteristics to enhance risk prediction. To facilitate the widespread adoption of machine learning, stakeholders should encourage standardization in the HHC setting.

Integration of artificial intelligence and multi-omics in kidney diseases

Kidney disease is a leading cause of death worldwide. Currently, the diagnosis of kidney diseases and the grading of their severity are mainly based on clinical features, which do not reveal the underlying molecular pathways. More recent surge of ∼omics studies has greatly catalyzed disease research. The advent of artificial intelligence (AI) has opened the avenue for the efficient integration and interpretation of big datasets for discovering clinically actionable knowledge. This review discusses how AI and multi-omics can be applied and integrated, to offer opportunities to develop novel diagnostic and therapeutic means in kidney diseases. The combination of new technology and novel analysis pipelines can lead to breakthroughs in expanding our understanding of disease pathogenesis, shedding new light on biomarkers and disease classification, as well as providing possibilities of precise treatment.

Malpractice Claims and Incident Reporting: Two Faces of the Same Coin?

Incident reporting is an important method to identify risks because learning from the reports is crucial in developing and implementing effective improvements. A medical malpractice claims analysis is an important tool in any case. Both incident reports and claims show cases of damage caused to patients, despite incident reporting comprising near misses, cases where no event occurred and no-harm events. We therefore compare the two worlds to assess whether they are similar or definitively different. From 1 January 2014 to 31 December 2021, the claims database of Policlinico Universitario A. Gemelli IRCCS collected 843 claims. From 1 January 2020 to 31 December 2021, the incident-reporting database collected 1919 events. In order to compare the two, we used IBNR calculation, usually adopted by the insurance industry to determine loss to a company and to evaluate the real number of adverse events that occurred. Indeed, the number of reported adverse events almost overlapped with the total number of events, which is indicative that incurred-but-not-reported events are practically irrelevant. The distribution of damage events reported as claims in the period from 1 January 2020 to 31 December 2021 and related to incidents that occurred in the months of the same period, grouped by quarter, was then compared with the distribution of damage events reported as adverse events and sentinel events in the same period, grouped by quarter. The analysis of the claims database showed that the claims trend is slightly decreasing. However, the analysis of the reports database showed that, in the period 2020-2021, the reports trend was increasing. In our study, the comparison of the two, malpractice claims and incident reporting, documented many differences and weak areas of overlap. Nevertheless, this contribution represents the first attempt to compare the two and new studies focusing on single types of adverse events are, therefore, desirable.

Generalizability of an acute kidney injury prediction model across health systems

Delays in the identification of acute kidney injury (AKI) in hospitalized patients are a major barrier to the development of effective interventions to treat AKI. A recent study by Tomasev and colleagues at DeepMind described a model that achieved a state-of-the-art performance in predicting AKI up to 48 hours in advance.1 Because this model was trained in a population of US Veterans that was 94% male, questions have arisen about its reproducibility and generalizability. In this study, we aimed to reproduce key aspects of this model, trained and evaluated it in a similar population of US Veterans, and evaluated its generalizability in a large academic hospital setting. We found that the model performed worse in predicting AKI in females in both populations, with miscalibration in lower stages of AKI and worse discrimination (a lower area under the curve) in higher stages of AKI. We demonstrate that while this discrepancy in performance can be largely corrected in non-Veterans by updating the original model using data from a sex-balanced academic hospital cohort, the worse model performance persists in Veterans. Our study sheds light on the importance of reproducing artificial intelligence studies, and on the complexity of discrepancies in model performance in subgroups that cannot be explained simply on the basis of sample size.

Understanding the risk factors for adverse events during exchange transfusion in neonatal hyperbilirubinemia using explainable artificial intelligence

Objective

To understand the risk factors associated with adverse events during exchange transfusion (ET) in severe neonatal hyperbilirubinemia.

Study design

We conducted a retrospective study of infants with hyperbilirubinemia who underwent ET within 30 days of birth from 2015 to 2020 in a children’s hospital. Both traditional statistical analysis and state-of-the-art explainable artificial intelligence (XAI) were used to identify the risk factors.

Results

A total of 188 ET cases were included; 7 major adverse events, including hyperglycemia (86.2%), top-up transfusion after ET (50.5%), hypocalcemia (42.6%), hyponatremia (42.6%), thrombocytopenia (38.3%), metabolic acidosis (25.5%), and hypokalemia (25.5%), and their risk factors were identified. Some novel and interesting findings were identified by XAI.

Conclusions

XAI not only achieved better performance in predicting adverse events during ET but also helped clinicians to more deeply understand nonlinear relationships and generate actionable knowledge for practice.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12887-022-03615-5.

A deep learning approach for detection of shallow anterior chamber depth based on the hidden features of fundus photographs

BACKGROUND AND OBJECTIVES

Patients with angle-closure glaucoma (ACG) are asymptomatic until they experience a painful attack. Shallow anterior chamber depth (ACD) is considered a significant risk factor for ACG. We propose a deep learning approach to detect shallow ACD using fundus photographs and to identify the hidden features of shallow ACD.

METHODS

This retrospective study assigned healthy subjects to the training (n = 1188 eyes) and test (n = 594) datasets (prospective validation design). We used a deep learning approach to estimate ACD and build a classification model to identify eyes with a shallow ACD. The proposed method, including subtraction of the input and output images of CycleGAN and a thresholding algorithm, was adopted to visualize the characteristic features of fundus photographs with a shallow ACD.

RESULTS

The deep learning model integrating fundus photographs and clinical variables achieved areas under the receiver operating characteristic curve of 0.978 (95% confidence interval [CI], 0.963-0.988) for an ACD ≤ 2.60 mm and 0.895 (95% CI, 0.868-0.919) for an ACD ≤ 2.80 mm, and outperformed the regression model using only clinical variables. However, the difference between shallow and deep ACD classes on fundus photographs was difficult to be detected with the naked eye. We were unable to identify the features of shallow ACD using the Grad-CAM. The CycleGAN-based feature images showed that area around the macula and optic disk significantly contributed to the classification of fundus photographs with a shallow ACD.

CONCLUSIONS

We demonstrated the feasibility of a novel deep learning model to detect a shallow ACD as a screening tool for ACG using fundus photographs. The CycleGAN-based feature map showed the hidden characteristic features of shallow ACD that were previously undetectable by conventional techniques and ophthalmologists. This framework will facilitate the early detection of shallow ACD to prevent overlooking the risks associated with ACG.

Can Robots Do Epidemiology? Machine Learning, Causal Inference, and Predicting the Outcomes of Public Health Interventions

This paper argues that machine learning (ML) and epidemiology are on collision course over causation. The discipline of epidemiology lays great emphasis on causation, while ML research does not. Some epidemiologists have proposed imposing what amounts to a causal constraint on ML in epidemiology, requiring it either to engage in causal inference or restrict itself to mere projection. We whittle down the issues to the question of whether causal knowledge is necessary for underwriting predictions about the outcomes of public health interventions. While there is great plausibility to the idea that it is, conviction that something is impossible does not by itself motivate a constraint to forbid trying. We disambiguate the possible motivations for such a constraint into definitional, metaphysical, epistemological, and pragmatic considerations and argue that “Proceed with caution” (rather than “Stop!”) is the outcome of each. We then argue that there are positive reasons to proceed, albeit cautiously. Causal inference enforces existing classification schema prior to the testing of associational claims (causal or otherwise), but associations and classification schema are more plausibly discovered (rather than tested or justified) in a back-and-forth process of gaining reflective equilibrium. ML instantiates this kind of process, we argue, and thus offers the welcome prospect of uncovering meaningful new concepts in epidemiology and public health—provided it is not causally constrained.

An overview of machine learning methods for monotherapy drug response prediction

For an increasing number of preclinical samples, both detailed molecular profiles and their responses to various drugs are becoming available. Efforts to understand, and predict, drug responses in a data-driven manner have led to a proliferation of machine learning (ML) methods, with the longer term ambition of predicting clinical drug responses. Here, we provide a uniquely wide and deep systematic review of the rapidly evolving literature on monotherapy drug response prediction, with a systematic characterization and classification that comprises more than 70 ML methods in 13 subclasses, their input and output data types, modes of evaluation, and code and software availability. ML experts are provided with a fundamental understanding of the biological problem, and how ML methods are configured for it. Biologists and biomedical researchers are introduced to the basic principles of applicable ML methods, and their application to the problem of drug response prediction. We also provide systematic overviews of commonly used data sources used for training and evaluation methods.

Machine-Learning-Aided Self-Powered Assistive Physical Therapy Devices

An expanding elderly population and people with disabilities pose considerable challenges to the current healthcare system. As a practical technology that integrates systems and services, assistive physical therapy devices are essential to maintain or to improve an individual's functioning and independence, thus promoting their well-being. Given technological advancements, core components of self-powered sensors and optimized machine-learning algorithms will play innovative roles in providing assistive services for unmet global needs. In this Perspective, we provide an overview of the latest developments in machine-learning-aided assistive physical therapy devices based on emerging self-powered sensing systems and a discussion of the challenges and opportunities in this field.

Analyzing Patient Trajectories With Artificial Intelligence

In digital medicine, patient data typically record health events over time (eg, through electronic health records, wearables, or other sensing technologies) and thus form unique patient trajectories. Patient trajectories are highly predictive of the future course of diseases and therefore facilitate effective care. However, digital medicine often uses only limited patient data, consisting of health events from only a single or small number of time points while ignoring additional information encoded in patient trajectories. To analyze such rich longitudinal data, new artificial intelligence (AI) solutions are needed. In this paper, we provide an overview of the recent efforts to develop trajectory-aware AI solutions and provide suggestions for future directions. Specifically, we examine the implications for developing disease models from patient trajectories along the typical workflow in AI: problem definition, data processing, modeling, evaluation, and interpretation. We conclude with a discussion of how such AI solutions will allow the field to build robust models for personalized risk scoring, subtyping, and disease pathway discovery.

Adapting skills from genetic counseling to wearables technology research during the COVID-19 pandemic: Poised for the pivot

Genetic counselors have shown themselves to be adaptable in an evolving profession, with expansion into new sub-specialties, various non-clinical settings, and research roles. The COVID-19 pandemic caused a sudden and drastic shift in healthcare priorities. In an effort to contribute meaningfully to the COVID-19 crisis, and to adapt to a remote- and essential-only research environment, our workplace and thus our roles pivoted from genomics research to remote COVID-19 research using wearables technologies. With a deep understanding of genomic data, we were quickly able to apply similar concepts to wearables data including considering privacy implications, managing uncertain findings, and acknowledging the lack of ethnic diversity in many datasets. By sharing our own experience as an example, we hope individuals trained in genetic counseling may see opportunities for adaptation of their skills into expanding roles.