Machine Learning in Medicine

Machine learning reveals chronic graft-versus-host disease phenotypes and stratifies survival after stem cell transplant for hematologic malignancies

The application of machine learning in medicine has been productive in multiple fields, but has not previously been applied to analyze the complexity of organ involvement by chronic graft-versus-host disease. Chronic graft-versus-host disease is classified by an overall composite score as mild, moderate or severe, which may overlook clinically relevant patterns in organ involvement. Here we applied a novel computational approach to chronic graft-versus-host disease with the goal of identifying phenotypic groups based on the subcomponents of the National Institutes of Health Consensus Criteria. Computational analysis revealed seven distinct groups of patients with contrasting clinical risks. The high-risk group had an inferior overall survival compared to the low-risk group (hazard ratio 2.24; 95% confidence interval: 1.36-3.68), an effect that was independent of graft-versus-host disease severity as measured by the National Institutes of Health criteria. To test clinical applicability, knowledge was translated into a simplified clinical prognostic decision tree. Groups identified by the decision tree also stratified outcomes and closely matched those from the original analysis. Patients in the high- and intermediate-risk decision-tree groups had significantly shorter overall survival than those in the low-risk group (hazard ratio 2.79; 95% confidence interval: 1.58-4.91 and hazard ratio 1.78; 95% confidence interval: 1.06-3.01, respectively). Machine learning and other computational analyses may better reveal biomarkers and stratify risk than the current approach based on cumulative severity. This approach could now be explored in other disease models with complex clinical phenotypes. External validation must be completed prior to clinical application. Ultimately, this approach has the potential to reveal distinct pathophysiological mechanisms that may underlie clusters. Clinicaltrials.gov identifier: NCT00637689.

Digital pathology imaging and computer-aided diagnostics as a novel tool for standardization of evaluation of aganglionic megacolon (Hirschsprung disease) histopathology

Based on a recently introduced immunohistochemical panel (Bachmann et al. 2015) for aganglionic megacolon (AM), also known as Hirschsprung disease, histopathological diagnosis, we evaluated whether the use of digital pathology and 'machine learning' could help to obtain a reliable diagnosis. Slides were obtained from 31 specimens of 27 patients immunohistochemically stained for MAP2, calretinin, S100β and GLUT1. Slides were digitized by whole slide scanning. We used a Definiens Developer Tissue Studios as software for analysis. We configured necessary parameters in combination with 'machine learning' to identify pathological aberrations. A significant difference between AM- and non-AM-affected tissues was found for calretinin (AM 0.55% vs. non-AM 1.44%) and MAP2 (AM 0.004% vs. non-AM 0.07%) staining measurements and software-based evaluations. In contrast, S100β and GLUT1 staining measurements and software-based evaluations showed no significant differences between AM- and non-AM-affected tissues. However, no difference was found in comparison of suction biopsies with resections. Applying machine learning via an ensemble voting classifier, we achieved an accuracy of 87.5% on the test set. Automated diagnosis of AM by applying digital pathology on immunohistochemical panels was successful for calretinin and MAP2, whereas S100β and GLUT1 were not effective in diagnosis. Our method suggests that software-based approaches are capable of diagnosing AM. Our future challenge will be the improvement of efficiency by reduction of the time-consuming need for large pre-labelled training data. With increasing technical improvement, especially in unsupervised training procedures, this method could be helpful in the future.

Societal Issues Concerning the Application of Artificial Intelligence in Medicine

Background

Medicine is becoming an increasingly data-centred discipline and, beyond classical statistical approaches, artificial intelligence (AI) and, in particular, machine learning (ML) are attracting much interest for the analysis of medical data. It has been argued that AI is experiencing a fast process of commodification. This characterization correctly reflects the current process of industrialization of AI and its reach into society. Therefore, societal issues related to the use of AI and ML should not be ignored any longer and certainly not in the medical domain. These societal issues may take many forms, but they all entail the design of models from a human-centred perspective, incorporating human-relevant requirements and constraints. In this brief paper, we discuss a number of specific issues affecting the use of AI and ML in medicine, such as fairness, privacy and anonymity, explainability and interpretability, but also some broader societal issues, such as ethics and legislation. We reckon that all of these are relevant aspects to consider in order to achieve the objective of fostering acceptance of AI- and ML-based technologies, as well as to comply with an evolving legislation concerning the impact of digital technologies on ethically and privacy sensitive matters. Our specific goal here is to reflect on how all these topics affect medical applications of AI and ML. This paper includes some of the contents of the "2nd Meeting of Science and Dialysis: Artificial Intelligence," organized in the Bellvitge University Hospital, Barcelona, Spain.

Summary and Key Messages

AI and ML are attracting much interest from the medical community as key approaches to knowledge extraction from data. These approaches are increasingly colonizing ambits of social impact, such as medicine and healthcare. Issues of social relevance with an impact on medicine and healthcare include (although they are not limited to) fairness, explainability, privacy, ethics and legislation.

Deep Learning in the Medical Domain: Predicting Cardiac Arrest Using Deep Learning

With the wider adoption of electronic health records, the rapid response team initially believed that mortalities could be significantly reduced but due to low accuracy and false alarms, the healthcare system is currently fraught with many challenges. Rule-based methods (e.g., Modified Early Warning Score) and machine learning (e.g., random forest) were proposed as a solution but not effective. In this article, we introduce the DeepEWS (Deep learning based Early Warning Score), which is based on a novel deep learning algorithm. Relative to the standard of care and current solutions in the marketplace, there is high accuracy, and in the clinical setting even when we consider the number of alarms, the accuracy levels are superior.

Wearable Sensor Data to Track Subject-Specific Movement Patterns Related to Clinical Outcomes Using a Machine Learning Approach

Wearable sensors can provide detailed information on human movement but the clinical impact of this information remains limited. We propose a machine learning approach, using wearable sensor data, to identify subject-specific changes in gait patterns related to improvements in clinical outcomes. Eight patients with knee osteoarthritis (OA) completed two gait trials before and one following an exercise intervention. Wearable sensor data (e.g., 3-dimensional (3D) linear accelerations) were collected from a sensor located near the lower back, lateral thigh and lateral shank during level treadmill walking at a preferred speed. Wearable sensor data from the 2 pre-intervention gait trials were used to define each individual’s typical movement pattern using a one-class support vector machine (OCSVM). The percentage of strides defined as outliers, based on the pre-intervention gait data and the OCSVM, were used to define the overall change in an individual’s movement pattern. The correlation between the change in movement patterns following the intervention (i.e., percentage of outliers) and improvement in self-reported clinical outcomes (e.g., pain and function) was assessed using a Spearman rank correlation. The number of outliers observed post-intervention exhibited a large association (ρ = 0.78) with improvements in self-reported clinical outcomes. These findings demonstrate a proof-of-concept and a novel methodological approach for integrating machine learning and wearable sensor data. This approach provides an objective and evidence-informed way to understand clinically important changes in human movement patterns in response to exercise therapy.

Predicting changes to INa from missense mutations in human SCN5A

Mutations in SCN5A can alter the cardiac sodium current I_Na and increase the risk of potentially lethal conditions such as Brugada and long-QT syndromes. The relation between mutations and their clinical phenotypes is complex, and systems to predict clinical severity of unclassified SCN5A variants perform poorly. We investigated if instead we could predict changes to I_Na, leaving the link from I_Na to clinical phenotype for mechanistic simulation studies. An exhaustive list of nonsynonymous missense mutations and resulting changes to I_Na was compiled. We then applied machine-learning methods to this dataset, and found that changes to I_Na could be predicted with higher sensitivity and specificity than most existing predictors of clinical significance. The substituted residues’ location on the protein correlated with channel function and strongly contributed to predictions, while conservedness and physico-chemical properties did not. However, predictions were not sufficiently accurate to form a basis for mechanistic studies. These results show that changes to I_Na, the mechanism through which SCN5A mutations create cardiac risk, are already difficult to predict using purely in-silico methods. This partly explains the limited success of systems to predict clinical significance of SCN5A variants, and underscores the need for functional studies of I_Na in risk assessment.

A Comprehensive Review of Magnetoencephalography (MEG) Studies for Brain Functionality in Healthy Aging and Alzheimer's Disease (AD)

Neural oscillations were established with their association with neurophysiological activities and the altered rhythmic patterns are believed to be linked directly to the progression of cognitive decline. Magnetoencephalography (MEG) is a non-invasive technique to record such neuronal activity due to excellent temporal and fair amount of spatial resolution. Single channel, connectivity as well as brain network analysis using MEG data in resting state and task-based experiments were analyzed from existing literature. Single channel analysis studies reported a less complex, more regular and predictable oscillations in Alzheimer's disease (AD) primarily in the left parietal, temporal and occipital regions. Investigations on both functional connectivity (FC) and effective (EC) connectivity analysis demonstrated a loss of connectivity in AD compared to healthy control (HC) subjects found in higher frequency bands. It has been reported from multiplex network of MEG study in AD in the affected regions of hippocampus, posterior default mode network (DMN) and occipital areas, however, conclusions cannot be drawn due to limited availability of clinical literature. Potential utilization of high spatial resolution in MEG likely to provide information related to in-depth brain functioning and underlying factors responsible for changes in neuronal waves in AD. This review is a comprehensive report to investigate diagnostic biomarkers for AD may be identified by from MEG data. It is also important to note that MEG data can also be utilized for the same pursuit in combination with other imaging modalities.

CASAnova: a multiclass support vector machine model for the classification of human sperm motility patterns

The ability to accurately monitor alterations in sperm motility is paramount to understanding multiple genetic and biochemical perturbations impacting normal fertilization. Computer-aided sperm analysis (CASA) of human sperm typically reports motile percentage and kinematic parameters at the population level, and uses kinematic gating methods to identify subpopulations such as progressive or hyperactivated sperm. The goal of this study was to develop an automated method that classifies all patterns of human sperm motility during in vitro capacitation following the removal of seminal plasma. We visually classified CASA tracks of 2817 sperm from 18 individuals and used a support vector machine-based decision tree to compute four hyperplanes that separate five classes based on their kinematic parameters. We then developed a web-based program, CASAnova, which applies these equations sequentially to assign a single classification to each motile sperm. Vigorous sperm are classified as progressive, intermediate, or hyperactivated, and nonvigorous sperm as slow or weakly motile. This program correctly classifies sperm motility into one of five classes with an overall accuracy of 89.9%. Application of CASAnova to capacitating sperm populations showed a shift from predominantly linear patterns of motility at initial time points to more vigorous patterns, including hyperactivated motility, as capacitation proceeds. Both intermediate and hyperactivated motility patterns were largely eliminated when sperm were incubated in noncapacitating medium, demonstrating the sensitivity of this method. The five CASAnova classifications are distinctive and reflect kinetic parameters of washed human sperm, providing an accurate, quantitative, and high-throughput method for monitoring alterations in motility.

Radiological Estimation of Intracranial Blood Volume and Occurrence of Hydrocephalus Determines Stress-Induced Hyperglycemia After Aneurysmal Subarachnoid Hemorrhage

Acute phase after aneurysmal subarachnoid hemorrhage (aSAH) is associated with several metabolic derangements including stress-induced hyperglycemia (SIH). The present study is designed to identify objective radiological determinants for SIH to better understand its contributory role in clinical outcomes after aSAH. A computer-aided detection tool was used to segment admission computed tomography (CT) images of aSAH patients to estimate intracranial blood and cerebrospinal fluid volumes. Modified Graeb score (mGS) was used as a semi-quantitative measure to estimate degree of hydrocephalus. The relationship between glycemic gap (GG) determined SIH, mGS, and estimated intracranial blood and cerebrospinal fluid volumes were evaluated using linear regression. Ninety-four [94/187 (50.3%)] among the study cohort had SIH (defined as GG > 26.7 mg/dl). Patients with SIH had 14.3 ml/1000 ml more intracranial blood volume as compared to those without SIH [39.6 ml (95% confidence interval, CI, 33.6 to 45.5) vs. 25.3 ml (95% CI 20.6 to 29.9), p = 0.0002]. Linear regression analysis of mGS with GG showed each unit increase in mGS resulted in 1.2 mg/dl increase in GG [p = 0.002]. Patients with SIH had higher mGS [median 4.0, interquartile range, IQR 2.0-7.0] as compared to those without SIH [median 2.0, IQR 0.0-6.0], p = 0.002. Patients with third ventricular blood on admission CT scan were more likely to develop SIH [67/118 (56.8%) vs. 27/69 (39.1%), p = 0.023]. Hence, the present study, using unbiased SIH definition and objective CT scan parameters, reports "dose-dependent" radiological features resulting in SIH. Such findings allude to a brain injury-stress response-neuroendocrine axis in etiopathogenesis of SIH.

Machine Learning for Outcome Prediction in Electroencephalograph (EEG)-Monitored Children in the Intensive Care Unit

The aim of this study was to evaluate the performance of models predicting in-hospital mortality in critically ill children undergoing continuous electroencephalography (cEEG) in the intensive care unit (ICU). We evaluated the performance of machine learning algorithms for predicting mortality in a database of 414 critically ill children undergoing cEEG in the ICU. The area under the receiver operating characteristic curve (AUC) in the test subset was highest for stepwise selection/elimination models (AUC = 0.82) followed by least absolute shrinkage and selection operator (LASSO) and support vector machine with linear kernel (AUC = 0.79), and random forest (AUC = 0.71). The explanatory models had the poorest discriminative performance (AUC = 0.63 for the model without considering etiology and AUC = 0.45 for the model considering etiology). Using few variables and a relatively small number of patients, machine learning techniques added information to explanatory models for prediction of in-hospital mortality.

Artificial Intelligence in Surgery: Promises and Perils

OBJECTIVE

The aim of this review was to summarize major topics in artificial intelligence (AI), including their applications and limitations in surgery. This paper reviews the key capabilities of AI to help surgeons understand and critically evaluate new AI applications and to contribute to new developments.

SUMMARY BACKGROUND DATA

AI is composed of various subfields that each provide potential solutions to clinical problems. Each of the core subfields of AI reviewed in this piece has also been used in other industries such as the autonomous car, social networks, and deep learning computers.

METHODS

A review of AI papers across computer science, statistics, and medical sources was conducted to identify key concepts and techniques within AI that are driving innovation across industries, including surgery. Limitations and challenges of working with AI were also reviewed.

RESULTS

Four main subfields of AI were defined: (1) machine learning, (2) artificial neural networks, (3) natural language processing, and (4) computer vision. Their current and future applications to surgical practice were introduced, including big data analytics and clinical decision support systems. The implications of AI for surgeons and the role of surgeons in advancing the technology to optimize clinical effectiveness were discussed.

CONCLUSIONS

Surgeons are well positioned to help integrate AI into modern practice. Surgeons should partner with data scientists to capture data across phases of care and to provide clinical context, for AI has the potential to revolutionize the way surgery is taught and practiced with the promise of a future optimized for the highest quality patient care.

Mobile technology and telemedicine for shoulder range of motion: validation of a motion-based machine-learning software development kit

BACKGROUND

Mobile technology offers the prospect of delivering high-value care with increased patient access and reduced costs. Advances in mobile health (mHealth) and telemedicine have been inhibited by the lack of interconnectivity between devices and software and inability to process consumer sensor data. The objective of this study was to preliminarily validate a motion-based machine learning software development kit (SDK) for the shoulder compared with a goniometer for 4 arcs of motion: (1) abduction, (2) forward flexion, (3) internal rotation, and (4) external rotation.

METHODS

A mobile application for the SDK was developed and "taught" 4 arcs of shoulder motion. Ten subjects without shoulder pain or prior shoulder surgery performed the arcs of motion for 5 repetitions. Each motion was measured by the SDK and compared with a physician-measured manual goniometer measurement. Angular differences between SDK and goniometer measurements were compared with univariate and power analyses.

RESULTS

The comparison between the SDK and goniometer measurement detected a mean difference of less than 5° for all arcs of motion (P > .05), with a 94% chance of detecting a large effect size from a priori power analysis. Mean differences for the arcs of motion were: abduction, -3.7° ± 3.2°; forward flexion, -4.9° ± 2.5°; internal rotation, -2.4° ± 3.7°; and external rotation -2.6° ± 3.4°.

DISCUSSION

The SDK has the potential to remotely substitute for a shoulder range of motion examination within 5° of goniometer measurements. An open-source motion-based SDK that can learn complex movements, including clinical shoulder range of motion, from consumer sensors offers promise for the future of mHealth, particularly in telemonitoring before and after orthopedic surgery.

Cardiac CT: Technological Advances in Hardware, Software, and Machine Learning Applications

Purpose of Review

Multidetector row computed tomography (CT) allows noninvasive imaging of the heart and coronary arteries. The purpose of this review is to briefly summarize recent advances in CT hardware and software technology, and machine learning applications for cardiovascular imaging.

Recent Findings

In the last decades, there have been significant improvements in CT hardware focusing on faster gantry rotation resulting in improved temporal resolution. Concurrent hardware improvements include improved spatial resolution and higher coverage of the patient, enabling faster acquisition. Advances in cardiac CT software include methods for measurement of noninvasive FFR, coronary plaque characterization, and adipose tissue characteristics around the heart. Machine learning approaches using cardiac CT have been shown to improve both risk of prognosis and lesion-specific ischemia.

Summary

Recent advances in CT hardware and software have expanded the clinical utility of CT for cardiovascular imaging. In the next decades, continued advances can be anticipated in these areas, and in machine learning applications in cardiac CT, as they are incorporated into clinical routine for image acquisition, image analysis, and prediction of patient outcomes.

Machine Learning in Orthopedics: A Literature Review

In this paper we present the findings of a systematic literature review covering the articles published in the last two decades in which the authors described the application of a machine learning technique and method to an orthopedic problem or purpose. By searching both in the Scopus and Medline databases, we retrieved, screened and analyzed the content of 70 journal articles, and coded these resources following an iterative method within a Grounded Theory approach. We report the survey findings by outlining the articles' content in terms of the main machine learning techniques mentioned therein, the orthopedic application domains, the source data and the quality of their predictive performance.

An Algorithm Based on Deep Learning for Predicting In-Hospital Cardiac Arrest

Background

In‐hospital cardiac arrest is a major burden to public health, which affects patient safety. Although traditional track‐and‐trigger systems are used to predict cardiac arrest early, they have limitations, with low sensitivity and high false‐alarm rates. We propose a deep learning–based early warning system that shows higher performance than the existing track‐and‐trigger systems.

Methods and Results

This retrospective cohort study reviewed patients who were admitted to 2 hospitals from June 2010 to July 2017. A total of 52 131 patients were included. Specifically, a recurrent neural network was trained using data from June 2010 to January 2017. The result was tested using the data from February to July 2017. The primary outcome was cardiac arrest, and the secondary outcome was death without attempted resuscitation. As comparative measures, we used the area under the receiver operating characteristic curve (AUROC), the area under the precision–recall curve (AUPRC), and the net reclassification index. Furthermore, we evaluated sensitivity while varying the number of alarms. The deep learning–based early warning system (AUROC: 0.850; AUPRC: 0.044) significantly outperformed a modified early warning score (AUROC: 0.603; AUPRC: 0.003), a random forest algorithm (AUROC: 0.780; AUPRC: 0.014), and logistic regression (AUROC: 0.613; AUPRC: 0.007). Furthermore, the deep learning–based early warning system reduced the number of alarms by 82.2%, 13.5%, and 42.1% compared with the modified early warning system, random forest, and logistic regression, respectively, at the same sensitivity.

Conclusions

An algorithm based on deep learning had high sensitivity and a low false‐alarm rate for detection of patients with cardiac arrest in the multicenter study.

Current Applications and Future Impact of Machine Learning in Radiology

Recent advances and future perspectives of machine learning techniques offer promising applications in medical imaging. Machine learning has the potential to improve different steps of the radiology workflow including order scheduling and triage, clinical decision support systems, detection and interpretation of findings, postprocessing and dose estimation, examination quality control, and radiology reporting. In this article, the authors review examples of current applications of machine learning and artificial intelligence techniques in diagnostic radiology. In addition, the future impact and natural extension of these techniques in radiology practice are discussed.

Restricted working hours in Austrian residency programs : Survey results

BACKGROUND

New regulations for working hours of medical doctors have been implemented in Austria based on the European directive 2003/88/EG, limiting on-duty working hours to 48 h per week. Clinical work is, therefore, substantially reduced compared to previous decades, and little is known on physician and students' opinions on this matter. We illustrate survey results concerning on-job training, its difficulties, and implications for restricted working hours.

METHODS

We conducted an internal survey among M.D. and Ph.D. students and medical staff members at the Medical University of Vienna using the MedCampus system (CAMPUSOnline, Graz, Austria) and SPSS (V.21, IBM Corp, Armonk, NY, USA).

RESULTS

Participants were 36.5% staff members and 63.5% students. Students rated continuous education of physicians high at 9.19 ± 1.76 and staff members at 8.90 ± 2.48 on a 1-10 (1 unimportant, 10 most important) scale. Students rated limited time resources, while staff considered financial resources as the greatest challenge for in-hospital education. Overall, 28.85% thought that restricted working hours can positively influence education, while 19.04% thought the opposite and 52.11% were undecided.

DISCUSSION

Considering the limited available time and financial resources, education of tomorrow's medical doctors remains an important but difficult task. While participants of our survey rated education as very important despite its many challenges, the opinions towards limited working hours were not as clear. Given that over 50% are still undecided whether reduced work hours may also positively influence medical education, it clearly presents an opportunity to include the next generations of physicians in this undertaking.

Machine learning for prediction of 30-day mortality after ST elevation myocardial infraction: An Acute Coronary Syndrome Israeli Survey data mining study

BACKGROUND

Risk scores for prediction of mortality 30-days following a ST-segment elevation myocardial infarction (STEMI) have been developed using a conventional statistical approach.

OBJECTIVE

To evaluate an array of machine learning (ML) algorithms for prediction of mortality at 30-days in STEMI patients and to compare these to the conventional validated risk scores.

METHODS

This was a retrospective, supervised learning, data mining study. Out of a cohort of 13,422 patients from the Acute Coronary Syndrome Israeli Survey (ACSIS) registry, 2782 patients fulfilled inclusion criteria and 54 variables were considered. Prediction models for overall mortality 30days after STEMI were developed using 6 ML algorithms. Models were compared to each other and to the Global Registry of Acute Coronary Events (GRACE) and Thrombolysis In Myocardial Infarction (TIMI) scores.

RESULTS

Depending on the algorithm, using all available variables, prediction models' performance measured in an area under the receiver operating characteristic curve (AUC) ranged from 0.64 to 0.91. The best models performed similarly to the Global Registry of Acute Coronary Events (GRACE) score (0.87 SD 0.06) and outperformed the Thrombolysis In Myocardial Infarction (TIMI) score (0.82 SD 0.06, p<0.05). Performance of most algorithms plateaued when introduced with 15 variables. Among the top predictors were creatinine, Killip class on admission, blood pressure, glucose level, and age.

CONCLUSIONS

We present a data mining approach for prediction of mortality post-ST-segment elevation myocardial infarction. The algorithms selected showed competence in prediction across an increasing number of variables. ML may be used for outcome prediction in complex cardiology settings.

Machine Learning Methods to Extract Documentation of Breast Cancer Symptoms From Electronic Health Records

CONTEXT

Clinicians document cancer patients' symptoms in free-text format within electronic health record visit notes. Although symptoms are critically important to quality of life and often herald clinical status changes, computational methods to assess the trajectory of symptoms over time are woefully underdeveloped.

OBJECTIVES

To create machine learning algorithms capable of extracting patient-reported symptoms from free-text electronic health record notes.

METHODS

The data set included 103,564 sentences obtained from the electronic clinical notes of 2695 breast cancer patients receiving paclitaxel-containing chemotherapy at two academic cancer centers between May 1996 and May 2015. We manually annotated 10,000 sentences and trained a conditional random field model to predict words indicating an active symptom (positive label), absence of a symptom (negative label), or no symptom at all (neutral label). Sentences labeled by human coder were divided into training, validation, and test data sets. Final model performance was determined on 20% test data unused in model development or tuning.

RESULTS

The final model achieved precision of 0.82, 0.86, and 0.99 and recall of 0.56, 0.69, and 1.00 for positive, negative, and neutral symptom labels, respectively. The most common positive symptoms were pain, fatigue, and nausea. Machine-based labeling of 103,564 sentences took two minutes.

CONCLUSION

We demonstrate the potential of machine learning to gather, track, and analyze symptoms experienced by cancer patients during chemotherapy. Although our initial model requires further optimization to improve the performance, further model building may yield machine learning methods suitable to be deployed in routine clinical care, quality improvement, and research applications.

Big Data and Data Science in Critical Care

The digitalization of the health-care system has resulted in a deluge of clinical big data and has prompted the rapid growth of data science in medicine. Data science, which is the field of study dedicated to the principled extraction of knowledge from complex data, is particularly relevant in the critical care setting. The availability of large amounts of data in the ICU, the need for better evidence-based care, and the complexity of critical illness makes the use of data science techniques and data-driven research particularly appealing to intensivists. Despite the increasing number of studies and publications in the field, thus far there have been few examples of data science projects that have resulted in successful implementations of data-driven systems in the ICU. However, given the expected growth in the field, intensivists should be familiar with the opportunities and challenges of big data and data science. The present article reviews the definitions, types of algorithms, applications, challenges, and future of big data and data science in critical care.

Research on Improved Depth Belief Network-Based Prediction of Cardiovascular Diseases

Quantitative analysis and prediction can help to reduce the risk of cardiovascular disease. Quantitative prediction based on traditional model has low accuracy. The variance of model prediction based on shallow neural network is larger. In this paper, cardiovascular disease prediction model based on improved deep belief network (DBN) is proposed. Using the reconstruction error, the network depth is determined independently, and unsupervised training and supervised optimization are combined. It ensures the accuracy of model prediction while guaranteeing stability. Thirty experiments were performed independently on the Statlog (Heart) and Heart Disease Database data sets in the UCI database. Experimental results showed that the mean of prediction accuracy was 91.26% and 89.78%, respectively. The variance of prediction accuracy was 5.78 and 4.46, respectively.

Machine learning-based diagnosis for disseminated intravascular coagulation (DIC): Development, external validation, and comparison to scoring systems

The major challenge in the diagnosis of disseminated intravascular coagulation (DIC) comes from the lack of specific biomarkers, leading to developing composite scoring systems. DIC scores are simple and rapidly applicable. However, optimal fibrin-related markers and their cut-off values remain to be defined, requiring optimization for use. The aim of this study is to optimize the use of DIC-related parameters through machine learning (ML)-approach. Further, we evaluated whether this approach could provide a diagnostic value in DIC diagnosis. For this, 46 DIC-related parameters were investigated for both clinical findings and laboratory results. We retrospectively reviewed 656 DIC-suspected cases at an initial order for full DIC profile and labeled their evaluation results (Set 1; DIC, n = 228; non-DIC, n = 428). Several ML algorithms were tested, and an artificial neural network (ANN) model was established via independent training and testing using 32 selected parameters. This model was externally validated from a different hospital with 217 DIC-suspected cases (Set 2; DIC, n = 80; non-DIC, n = 137). The ANN model represented higher AUC values than the three scoring systems in both set 1 (ANN 0.981; ISTH 0.945; JMHW 0.943; and JAAM 0.928) and set 2 (AUC ANN 0.968; ISTH 0.946). Additionally, the relative importance of the 32 parameters was evaluated. Most parameters had contextual importance, however, their importance in ML-approach was different from the traditional scoring system. Our study demonstrates that ML could optimize the use of clinical parameters with robustness for DIC diagnosis. We believe that this approach could play a supportive role in physicians' medical decision by integrated into electrical health record system. Further prospective validation is required to assess the clinical consequence of ML-approach and their clinical benefit.

Using a Guided Machine Learning Ensemble Model to Predict Discharge Disposition following Meningioma Resection

Objective  Machine learning (ML) algorithms are powerful tools for predicting patient outcomes. This study pilots a novel approach to algorithm selection and model creation using prediction of discharge disposition following meningioma resection as a proof of concept. Materials and Methods  A diversity of ML algorithms were trained on a single-institution database of meningioma patients to predict discharge disposition. Algorithms were ranked by predictive power and top performers were combined to create an ensemble model. The final ensemble was internally validated on never-before-seen data to demonstrate generalizability. The predictive power of the ensemble was compared with a logistic regression. Further analyses were performed to identify how important variables impact the ensemble. Results  Our ensemble model predicted disposition significantly better than a logistic regression (area under the curve of 0.78 and 0.71, respectively, p  = 0.01). Tumor size, presentation at the emergency department, body mass index, convexity location, and preoperative motor deficit most strongly influence the model, though the independent impact of individual variables is nuanced. Conclusion  Using a novel ML technique, we built a guided ML ensemble model that predicts discharge destination following meningioma resection with greater predictive power than a logistic regression, and that provides greater clinical insight than a univariate analysis. These techniques can be extended to predict many other patient outcomes of interest.

Machine learning methods for locating re-entrant drivers from electrograms in a model of atrial fibrillation

Mapping resolution has recently been identified as a key limitation in successfully locating the drivers of atrial fibrillation (AF). Using a simple cellular automata model of AF, we demonstrate a method by which re-entrant drivers can be located quickly and accurately using a collection of indirect electrogram measurements. The method proposed employs simple, out-of-the-box machine learning algorithms to correlate characteristic electrogram gradients with the displacement of an electrogram recording from a re-entrant driver. Such a method is less sensitive to local fluctuations in electrical activity. As a result, the method successfully locates 95.4% of drivers in tissues containing a single driver, and 95.1% (92.6%) for the first (second) driver in tissues containing two drivers of AF. Additionally, we demonstrate how the technique can be applied to tissues with an arbitrary number of drivers. In its current form, the techniques presented are not refined enough for a clinical setting. However, the methods proposed offer a promising path for future investigations aimed at improving targeted ablation for AF.

Exercise Therapy and Cardiovascular Toxicity in Cancer

Cardio-oncology is an emerging discipline focused predominantly on the detection and management of cancer treatment-induced cardiac dysfunction (cardiotoxicity), which predisposes to development of overt heart failure or coronary artery disease. The direct adverse consequences, as well as those secondary to anticancer therapeutics, extend beyond the heart, however, to affect the entire cardiovascular-skeletal muscle axis (ie, whole-organism cardiovascular toxicity). The global nature of impairment creates a strong rationale for treatment strategies that augment or preserve global cardiovascular reserve capacity. In noncancer clinical populations, exercise training is an established therapy to improve cardiovascular reserve capacity, leading to concomitant reductions in cardiovascular morbidity and its attendant symptoms. Here, we overview the tolerability and efficacy of exercise on cardiovascular toxicity in adult patients with cancer. We also propose a conceptual research framework to facilitate personalized risk assessment and the development of targeted exercise prescriptions to optimally prevent or manage cardiovascular toxicity after a cancer diagnosis.

CarDiac MagnEtic Resonance for Primary Prevention Implantable CardioVerter DebrillAtor ThErapy international registry: Design and rationale of the DERIVATE study

BACKGROUND

Implantable cardioverter defibrillator (ICD) represents the most valuable sudden cardiac death (SCD) prophylactic strategy in patients with heart failure and severely reduced left ventricular ejection fraction (LVEF). To date, it is still unknown how to integrate the information given by cardiac magnetic resonance (CMR) into clinical and transthoracic echocardiography (TTE) work-up of non-ischemic cardiomyopathy (NICM) and ischemic cardiomyopathy (ICM) patients for accurate risk stratification.

METHODS AND RESULTS

DERIVATE is a prospective, international, multicenter, observational registry of NICM and ICM patients with chronic heart failure and reduced LVEF who will undergo clinical evaluation, TTE and CMR. The registry will enrol cohorts from 34 sites. Complete risk factor, clinical presentation, TTE and CMR data will be collected and each patient will be followed-up for outcomes. Primary end point of the study is all-cause mortality. Secondary end points are: cardiovascular death, SCD, aborted SCD, sustained ventricular tachycardia (VT), and major adverse cardiac events (MACE) defined as a composite endpoint of SCD, aborted SCD, and sustained VT. Specifically, we will determine CMR findings that predict outcomes, with incremental value over LVEF and NYHA classification. Secondary aims consist in providing a comprehensive clinical and imaging score and testing the contribution of machine learning to determine prognostic CMR parameters.

CONCLUSIONS

The final objective of the study consists in the identification of prognostic CMR parameters in a large prospective cohort for a better selection of patients with heart failure being worthy of primary prevention ICD therapy. (clinicaltrials.gov registration: RTT# NCT03352648).

Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis

Aims

Traditional prognostic risk assessment in patients undergoing non-invasive imaging is based upon a limited selection of clinical and imaging findings. Machine learning (ML) can consider a greater number and complexity of variables. Therefore, we investigated the feasibility and accuracy of ML to predict 5-year all-cause mortality (ACM) in patients undergoing coronary computed tomographic angiography (CCTA), and compared the performance to existing clinical or CCTA metrics.

Methods and results

The analysis included 10 030 patients with suspected coronary artery disease and 5-year follow-up from the COronary CT Angiography EvaluatioN For Clinical Outcomes: An InteRnational Multicenter registry. All patients underwent CCTA as their standard of care. Twenty-five clinical and 44 CCTA parameters were evaluated, including segment stenosis score (SSS), segment involvement score (SIS), modified Duke index (DI), number of segments with non-calcified, mixed or calcified plaques, age, sex, gender, standard cardiovascular risk factors, and Framingham risk score (FRS). Machine learning involved automated feature selection by information gain ranking, model building with a boosted ensemble algorithm, and 10-fold stratified cross-validation. Seven hundred and forty-five patients died during 5-year follow-up. Machine learning exhibited a higher area-under-curve compared with the FRS or CCTA severity scores alone (SSS, SIS, DI) for predicting all-cause mortality (ML: 0.79 vs. FRS: 0.61, SSS: 0.64, SIS: 0.64, DI: 0.62; P< 0.001).

Conclusions

Machine learning combining clinical and CCTA data was found to predict 5-year ACM significantly better than existing clinical or CCTA metrics alone.

Simulation and Synthesis in Medical Imaging

This editorial introduces the Special Issue on Simulation and Synthesis in Medical Imaging. In this editorial, we define so-far ambiguous terms of simulation and synthesis in medical imaging. We also briefly discuss the synergistic importance of mechanistic (hypothesis-driven) and phenomenological (data-driven) models of medical image generation. Finally, we introduce the twelve papers published in this issue covering both mechanistic (5) and phenomenological (7) medical image generation. This rich selection of papers covers applications in cardiology, retinopathy, histopathology, neurosciences, and oncology. It also covers all mainstream diagnostic medical imaging modalities. We conclude the editorial with a personal view on the field and highlight some existing challenges and future research opportunities.

Association of Pathological Fibrosis With Renal Survival Using Deep Neural Networks

INTRODUCTION

Chronic kidney damage is routinely assessed semiquantitatively by scoring the amount of fibrosis and tubular atrophy in a renal biopsy sample. Although image digitization and morphometric techniques can better quantify the extent of histologic damage, we need more widely applicable ways to stratify kidney disease severity.

METHODS

We leveraged a deep learning architecture to better associate patient-specific histologic images with clinical phenotypes (training classes) including chronic kidney disease (CKD) stage, serum creatinine, and nephrotic-range proteinuria at the time of biopsy, and 1-, 3-, and 5-year renal survival. Trichrome-stained images processed from renal biopsy samples were collected on 171 patients treated at the Boston Medical Center from 2009 to 2012. Six convolutional neural network (CNN) models were trained using these images as inputs and the training classes as outputs, respectively. For comparison, we also trained separate classifiers using the pathologist-estimated fibrosis score (PEFS) as input and the training classes as outputs, respectively.

RESULTS

CNN models outperformed PEFS across the classification tasks. Specifically, the CNN model predicted the CKD stage more accurately than the PEFS model (κ = 0.519 vs. 0.051). For creatinine models, the area under curve (AUC) was 0.912 (CNN) versus 0.840 (PEFS). For proteinuria models, AUC was 0.867 (CNN) versus 0.702 (PEFS). AUC values for the CNN models for 1-, 3-, and 5-year renal survival were 0.878, 0.875, and 0.904, respectively, whereas the AUC values for PEFS model were 0.811, 0.800, and 0.786, respectively.

CONCLUSION

The study demonstrates a proof of principle that deep learning can be applied to routine renal biopsy images.

Predicting central line-associated bloodstream infections and mortality using supervised machine learning

PURPOSE

The purpose of this study was to compare machine learning techniques for predicting central line-associated bloodstream infection (CLABSI).

MATERIALS AND METHODS

The Multiparameter Intelligent Monitoring in Intensive Care III database was queried for all ICU admissions. The variables included six different severities of illness scores calculated on the first day of ICU admission with their components and comorbidities. The outcomes of interest were in-hospital mortality, central line placement, and CLABSI. Predictive models were created for these outcomes using classifiers with different algorithms: logistic regression, gradient boosted trees, and deep learning.

RESULTS

There were 57,786 total hospital admissions and the mortality rate was 10.1%. There were 38.4% patients with a central line and the rate of CLABSI was 1.5%. The classifiers using deep learning performed with the highest AUC for mortality, 0.885±0.010 (p<0.01) and central line placement, 0.816±0.006 (p<0.01). The classifier using logistic regression for predicting CLABSI performed with an AUC of 0.722±0.048 (p<0.01).

CONCLUSIONS

This study demonstrates models for identifying patients who will develop CLABSI. Early identification of these patients has implications for quality, cost, and outcome improvements.

Artificial Intelligence in Medical Practice: The Question to the Answer?

Computer science advances and ultra-fast computing speeds find artificial intelligence (AI) broadly benefitting modern society-forecasting weather, recognizing faces, detecting fraud, and deciphering genomics. AI's future role in medical practice remains an unanswered question. Machines (computers) learn to detect patterns not decipherable using biostatistics by processing massive datasets (big data) through layered mathematical models (algorithms). Correcting algorithm mistakes (training) adds to AI predictive model confidence. AI is being successfully applied for image analysis in radiology, pathology, and dermatology, with diagnostic speed exceeding, and accuracy paralleling, medical experts. While diagnostic confidence never reaches 100%, combining machines plus physicians reliably enhances system performance. Cognitive programs are impacting medical practice by applying natural language processing to read the rapidly expanding scientific literature and collate years of diverse electronic medical records. In this and other ways, AI may optimize the care trajectory of chronic disease patients, suggest precision therapies for complex illnesses, reduce medical errors, and improve subject enrollment into clinical trials.

Machine learning and medicine: book review and commentary

This article is a review of the book "Master machine learning algorithms, discover how they work and implement them from scratch" (ISBN: not available, 37 USD, 163 pages) edited by Jason Brownlee published by the Author, edition, v1.10 http://MachineLearningMastery.com . An accompanying commentary discusses some of the issues that are involved with use of machine learning and data mining techniques to develop predictive models for diagnosis or prognosis of disease, and to call attention to additional requirements for developing diagnostic and prognostic algorithms that are generally useful in medicine. Appendix provides examples that illustrate potential problems with machine learning that are not addressed in the reviewed book.

Integrated prediction of lesion-specific ischaemia from quantitative coronary CT angiography using machine learning: a multicentre study

OBJECTIVES

We aimed to investigate if lesion-specific ischaemia by invasive fractional flow reserve (FFR) can be predicted by an integrated machine learning (ML) ischaemia risk score from quantitative plaque measures from coronary computed tomography angiography (CTA).

METHODS

In a multicentre trial of 254 patients, CTA and invasive coronary angiography were performed, with FFR in 484 vessels. CTA data sets were analysed by semi-automated software to quantify stenosis and non-calcified (NCP), low-density NCP (LD-NCP, < 30 HU), calcified and total plaque volumes, contrast density difference (CDD, maximum difference in luminal attenuation per unit area) and plaque length. ML integration included automated feature selection and model building from quantitative CTA with a boosted ensemble algorithm, and tenfold stratified cross-validation.

RESULTS

Eighty patients had ischaemia by FFR (FFR ≤ 0.80) in 100 vessels. Information gain for predicting ischaemia was highest for CDD (0.172), followed by LD-NCP (0.125), NCP (0.097), and total plaque volumes (0.092). ML exhibited higher area-under-the-curve (0.84) than individual CTA measures, including stenosis (0.76), LD-NCP volume (0.77), total plaque volume (0.74) and pre-test likelihood of coronary artery disease (CAD) (0.63); p < 0.006.

CONCLUSIONS

Integrated ML ischaemia risk score improved the prediction of lesion-specific ischaemia by invasive FFR, over stenosis, plaque measures and pre-test likelihood of CAD.

KEY POINTS

• Integrated ischaemia risk score improved prediction of ischaemia over quantitative plaque measures • Integrated ischaemia risk score showed higher prediction of ischaemia than standard approach • Contrast density difference had the highest information gain to identify lesion-specific ischaemia.

Support Vector Machine Based Monitoring of Cardio-Cerebrovascular Reserve during Simulated Hemorrhage

Introduction: In the initial phase of hypovolemic shock, mean blood pressure (BP) is maintained by sympathetically mediated vasoconstriction rendering BP monitoring insensitive to detect blood loss early. Late detection can result in reduced tissue oxygenation and eventually cellular death. We hypothesized that a machine learning algorithm that interprets currently used and new hemodynamic parameters could facilitate in the detection of impending hypovolemic shock.

Method: In 42 (27 female) young [mean (sd): 24 (4) years], healthy subjects central blood volume (CBV) was progressively reduced by application of −50 mmHg lower body negative pressure until the onset of pre-syncope. A support vector machine was trained to classify samples into normovolemia (class 0), initial phase of CBV reduction (class 1) or advanced CBV reduction (class 2). Nine models making use of different features were computed to compare sensitivity and specificity of different non-invasive hemodynamic derived signals. Model features included: volumetric hemodynamic parameters (stroke volume and cardiac output), BP curve dynamics, near-infrared spectroscopy determined cortical brain oxygenation, end-tidal carbon dioxide pressure, thoracic bio-impedance, and middle cerebral artery transcranial Doppler (TCD) blood flow velocity. Model performance was tested by quantifying the predictions with three methods: sensitivity and specificity, absolute error, and quantification of the log odds ratio of class 2 vs. class 0 probability estimates.

Results: The combination with maximal sensitivity and specificity for classes 1 and 2 was found for the model comprising volumetric features (class 1: 0.73–0.98 and class 2: 0.56–0.96). Overall lowest model error was found for the models comprising TCD curve hemodynamics. Using probability estimates the best combination of sensitivity for class 1 (0.67) and specificity (0.87) was found for the model that contained the TCD cerebral blood flow velocity derived pulse height. The highest combination for class 2 was found for the model with the volumetric features (0.72 and 0.91).

Conclusion: The most sensitive models for the detection of advanced CBV reduction comprised data that describe features from volumetric parameters and from cerebral blood flow velocity hemodynamics. In a validated model of hemorrhage in humans these parameters provide the best indication of the progression of central hypovolemia.

Is It Possible to Predict the Future in First-Episode Psychosis?

The outcome of first-episode psychosis (FEP) is highly variable, ranging from early sustained recovery to antipsychotic treatment resistance from the onset of illness. For clinicians, a possibility to predict patient outcomes would be highly valuable for the selection of antipsychotic treatment and in tailoring psychosocial treatments and psychoeducation. This selective review summarizes current knowledge of prognostic markers in FEP. We sought potential outcome predictors from clinical and sociodemographic factors, cognition, brain imaging, genetics, and blood-based biomarkers, and we considered different outcomes, like remission, recovery, physical comorbidities, and suicide risk. Based on the review, it is currently possible to predict the future for FEP patients to some extent. Some clinical features-like the longer duration of untreated psychosis (DUP), poor premorbid adjustment, the insidious mode of onset, the greater severity of negative symptoms, comorbid substance use disorders (SUDs), a history of suicide attempts and suicidal ideation and having non-affective psychosis-are associated with a worse outcome. Of the social and demographic factors, male gender, social disadvantage, neighborhood deprivation, dysfunctional family environment, and ethnicity may be relevant. Treatment non-adherence is a substantial risk factor for relapse, but a small minority of patients with acute onset of FEP and early remission may benefit from antipsychotic discontinuation. Cognitive functioning is associated with functional outcomes. Brain imaging currently has limited utility as an outcome predictor, but this may change with methodological advancements. Polygenic risk scores (PRSs) might be useful as one component of a predictive tool, and pharmacogenetic testing is already available and valuable for patients who have problems in treatment response or with side effects. Most blood-based biomarkers need further validation. None of the currently available predictive markers has adequate sensitivity or specificity used alone. However, personalized treatment of FEP will need predictive tools. We discuss some methodologies, such as machine learning (ML), and tools that could lead to the improved prediction and clinical utility of different prognostic markers in FEP. Combination of different markers in ML models with a user friendly interface, or novel findings from e.g., molecular genetics or neuroimaging, may result in computer-assisted clinical applications in the near future.

An introduction and overview of machine learning in neurosurgical care

BACKGROUND

Machine learning (ML) is a branch of artificial intelligence that allows computers to learn from large complex datasets without being explicitly programmed. Although ML is already widely manifest in our daily lives in various forms, the considerable potential of ML has yet to find its way into mainstream medical research and day-to-day clinical care. The complex diagnostic and therapeutic modalities used in neurosurgery provide a vast amount of data that is ideally suited for ML models. This systematic review explores ML's potential to assist and improve neurosurgical care.

METHOD

A systematic literature search was performed in the PubMed and Embase databases to identify all potentially relevant studies up to January 1, 2017. All studies were included that evaluated ML models assisting neurosurgical treatment.

RESULTS

Of the 6,402 citations identified, 221 studies were selected after subsequent title/abstract and full-text screening. In these studies, ML was used to assist surgical treatment of patients with epilepsy, brain tumors, spinal lesions, neurovascular pathology, Parkinson's disease, traumatic brain injury, and hydrocephalus. Across multiple paradigms, ML was found to be a valuable tool for presurgical planning, intraoperative guidance, neurophysiological monitoring, and neurosurgical outcome prediction.

CONCLUSIONS

ML has started to find applications aimed at improving neurosurgical care by increasing the efficiency and precision of perioperative decision-making. A thorough validation of specific ML models is essential before implementation in clinical neurosurgical care. To bridge the gap between research and clinical care, practical and ethical issues should be considered parallel to the development of these techniques.

Machine Learning Algorithm Predicts Cardiac Resynchronization Therapy Outcomes: Lessons From the COMPANION Trial

BACKGROUND

Cardiac resynchronization therapy (CRT) reduces morbidity and mortality in heart failure patients with reduced left ventricular function and intraventricular conduction delay. However, individual outcomes vary significantly. This study sought to use a machine learning algorithm to develop a model to predict outcomes after CRT.

METHODS AND RESULTS

Models were developed with machine learning algorithms to predict all-cause mortality or heart failure hospitalization at 12 months post-CRT in the COMPANION trial (Comparison of Medical Therapy, Pacing, and Defibrillation in Heart Failure). The best performing model was developed with the random forest algorithm. The ability of this model to predict all-cause mortality or heart failure hospitalization and all-cause mortality alone was compared with discrimination obtained using a combination of bundle branch block morphology and QRS duration. In the 595 patients with CRT-defibrillator in the COMPANION trial, 105 deaths occurred (median follow-up, 15.7 months). The survival difference across subgroups differentiated by bundle branch block morphology and QRS duration did not reach significance (P=0.08). The random forest model produced quartiles of patients with an 8-fold difference in survival between those with the highest and lowest predicted probability for events (hazard ratio, 7.96; P<0.0001). The model also discriminated the risk of the composite end point of all-cause mortality or heart failure hospitalization better than subgroups based on bundle branch block morphology and QRS duration.

CONCLUSIONS

In the COMPANION trial, a machine learning algorithm produced a model that predicted clinical outcomes after CRT. Applied before device implant, this model may better differentiate outcomes over current clinical discriminators and improve shared decision-making with patients.

Big-Data Analysis, Cluster Analysis, and Machine-Learning Approaches

Medicine will experience many changes in the coming years because the so-called "medicine of the future" will be increasingly proactive, featuring four basic elements: predictive, personalized, preventive, and participatory. Drivers for these changes include the digitization of data in medicine and the availability of computational tools that deal with massive volumes of data. Thus, the need to apply machine-learning methods to medicine has increased dramatically in recent years while facing challenges related to an unprecedented large number of clinically relevant features and highly specific diagnostic tests. Advances regarding data-storage technology and the progress concerning genome studies have enabled collecting vast amounts of patient clinical details, thus permitting the extraction of valuable information. In consequence, big-data analytics is becoming a mandatory technology to be used in the clinical domain.Machine learning and big-data analytics can be used in the field of cardiology, for example, for the prediction of individual risk factors for cardiovascular disease, for clinical decision support, and for practicing precision medicine using genomic information. Several projects employ machine-learning techniques to address the problem of classification and prediction of heart failure (HF) subtypes and unbiased clustering analysis using dense phenomapping to identify phenotypically distinct HF categories. In this chapter, these ideas are further presented, and a computerized model allowing the distinction between two major HF phenotypes on the basis of ventricular-volume data analysis is discussed in detail.

e-Addictology: An Overview of New Technologies for Assessing and Intervening in Addictive Behaviors

BACKGROUND

New technologies can profoundly change the way we understand psychiatric pathologies and addictive disorders. New concepts are emerging with the development of more accurate means of collecting live data, computerized questionnaires, and the use of passive data. Digital phenotyping, a paradigmatic example, refers to the use of computerized measurement tools to capture the characteristics of different psychiatric disorders. Similarly, machine learning-a form of artificial intelligence-can improve the classification of patients based on patterns that clinicians have not always considered in the past. Remote or automated interventions (web-based or smartphone-based apps), as well as virtual reality and neurofeedback, are already available or under development.

OBJECTIVE

These recent changes have the potential to disrupt practices, as well as practitioners' beliefs, ethics and representations, and may even call into question their professional culture. However, the impact of new technologies on health professionals' practice in addictive disorder care has yet to be determined. In the present paper, we therefore present an overview of new technology in the field of addiction medicine.

METHOD

Using the keywords [e-health], [m-health], [computer], [mobile], [smartphone], [wearable], [digital], [machine learning], [ecological momentary assessment], [biofeedback] and [virtual reality], we searched the PubMed database for the most representative articles in the field of assessment and interventions in substance use disorders.

RESULTS

We screened 595 abstracts and analyzed 92 articles, dividing them into seven categories: e-health program and web-based interventions, machine learning, computerized adaptive testing, wearable devices and digital phenotyping, ecological momentary assessment, biofeedback, and virtual reality.

CONCLUSION

This overview shows that new technologies can improve assessment and interventions in the field of addictive disorders. The precise role of connected devices, artificial intelligence and remote monitoring remains to be defined. If they are to be used effectively, these tools must be explained and adapted to the different profiles of physicians and patients. The involvement of patients, caregivers and other health professionals is essential to their design and assessment.

Real-Time Monitoring and Analysis of Zebrafish Electrocardiogram with Anomaly Detection

Heart disease is the leading cause of mortality in the U.S. with approximately 610,000 people dying every year. Effective therapies for many cardiac diseases are lacking, largely due to an incomplete understanding of their genetic basis and underlying molecular mechanisms. Zebrafish (Danio rerio) are an excellent model system for studying heart disease as they enable a forward genetic approach to tackle this unmet medical need. In recent years, our team has been employing electrocardiogram (ECG) as an efficient tool to study the zebrafish heart along with conventional approaches, such as immunohistochemistry, DNA and protein analyses. We have overcome various challenges in the small size and aquatic environment of zebrafish in order to obtain ECG signals with favorable signal-to-noise ratio (SNR), and high spatial and temporal resolution. In this paper, we highlight our recent efforts in zebrafish ECG acquisition with a cost-effective simplified microelectrode array (MEA) membrane providing multi-channel recording, a novel multi-chamber apparatus for simultaneous screening, and a LabVIEW program to facilitate recording and processing. We also demonstrate the use of machine learning-based programs to recognize specific ECG patterns, yielding promising results with our current limited amount of zebrafish data. Our solutions hold promise to carry out numerous studies of heart diseases, drug screening, stem cell-based therapy validation, and regenerative medicine.

Molecular Epidemiology of Heart Failure: Translational Challenges and Opportunities

Heart failure (HF) is the end-stage of all heart disease and arguably constitutes the greatest unmet therapeutic need in cardiovascular medicine today. Classic epidemiological studies have established clinical risk factors for HF, but the cause remains poorly understood in many cases. Biochemical analyses of small case-control series and animal models have described a plethora of molecular characteristics of HF, but a single unifying pathogenic theory is lacking. Heart failure appears to result not only from cardiac overload or injury but also from a complex interplay among genetic, neurohormonal, metabolic, inflammatory, and other biochemical factors acting on the heart. Recent development of robust, high-throughput tools in molecular biology provides opportunity for deep molecular characterization of population-representative cohorts and HF cases (molecular epidemiology), including genome sequencing, profiling of myocardial gene expression and chromatin modifications, plasma composition of proteins and metabolites, and microbiomes. The integration of such detailed information holds promise for improving understanding of HF pathophysiology in humans, identification of therapeutic targets, and definition of disease subgroups beyond the current classification based on ejection fraction which may benefit from improved individual tailoring of therapy. Challenges include: 1) the need for large cohorts with deep, uniform phenotyping; 2) access to the relevant tissues, ideally with repeated sampling to capture dynamic processes; and 3) analytical issues related to integration and analysis of complex datasets. International research consortia have formed to address these challenges and combine datasets, and cohorts with up to 1 million participants are being collected. This paper describes the molecular epidemiology of HF and provides an overview of methods and tissue types and examples of published and ongoing efforts to systematically evaluate molecular determinants of HF in human populations.