Artificial Intelligence (AI) in medical applications holds great promise. However, the use of Machine Learning-based (ML) systems in clinical practice is still minimal. It is uniquely difficult to introduce clinician-facing ML-based systems in practice, which has been recognised in HCI and related fields. Recent publications have begun to address the sociotechnical challenges of designing, developing, and successfully deploying clinician-facing ML-based systems. We conducted a qualitative systematic review and provided answers to the question: “How can HCI researchers and practitioners contribute to the successful realisation of ML in medical practice?” We reviewed 25 eligible papers that investigated the real-world clinical implications of concrete clinician-facing ML-based systems. The main contributions of this systematic review are: (1) an overview of the technical aspects of ML innovation and their consequences for HCI researchers and practitioners; (2) a description of the different roles that ML-based systems can take in clinical settings; (3) a conceptualisation of the main activities of medical ML innovation processes; (4) identification of five sociotechnical interdependencies that emerge from medical ML innovation; and (5) implications for HCI researchers and practitioners on how to mitigate the sociotechnical challenges of medical ML innovation.

Background: Most commercial activity trackers are developed as consumer devices and not as clinical devices. The aim is to monitor and motivate sport activities, healthy living, and similar wellness purposes, and the devices are not designed to support care management in a clinical context. There are great expectations for using wearable sensor devices in health care settings, and the separate realms of wellness tracking and disease self-monitoring are increasingly becoming blurred. However, patients’ experiences with activity tracking technologies designed for use outside the clinical context have received little academic attention. Objective: This study aimed to contribute to understanding how patients with a chronic disease experience activity data from consumer self-tracking devices related to self-care and their chronic illness. Our research question was: “How do patients with heart disease experience activity data in relation to self-care and chronic illness?” Methods: We conducted a qualitative interview study with patients with chronic heart disease (n=27) who had an implanted cardioverter-defibrillator. Patients were invited to wear a FitBit Alta HR wearable activity tracker for 3-12 months and provide their perspectives on their experiences with step, sleep, and heart rate data. The average age was 57.2 years (25 men and 2 women), and patients used the tracker for 4-49 weeks (mean 26.1 weeks). Semistructured interviews (n=66) were conducted with patients 2–3 times and were analyzed iteratively in workshops using thematic analysis and abductive reasoning logic. Results: Of the 27 patients, 18 related the heart rate, sleep, and step count data directly to their heart disease. Wearable activity trackers actualized patients’ experiences across 3 dimensions with a spectrum of contrasting experiences: (1) knowing, which spanned gaining insight and evoking doubts; (2) feeling, which spanned being reassured and becoming anxious; and (3) evaluating, which spanned promoting improvements and exposing failure. Conclusions: Patients’ experiences could reside more on one end of the spectrum, could reside across all 3 dimensions, or could combine contrasting positions and even move across the spectrum over time. Activity data from wearable devices may be a resource for self-care; however, the data may simultaneously constrain and create uncertainty, fear, and anxiety. By showing how patients experience self-tracking data across dimensions of knowing, feeling, and evaluating, we point toward the richness and complexity of these data experiences in the context of chronic illness and self-care.

Electrical storm (ES) is a serious arrhythmic syndrome that is characterized by recurrent episodes of ventricular arrhythmias. Electrical storm is associated with increased mortality and morbidity despite the use of implantable cardioverter-defibrillators (ICDs). Predicting ES could be essential; however, models for predicting this event have never been developed. The goal of this study was to construct and validate machine learning models to predict ES based on daily ICD remote monitoring summaries. Daily ICD summaries from 19 935 patients were used to construct and evaluate two models [logistic regression (LR) and random forest (RF)] for predicting the short-term risk of ES. The models were evaluated on the parts of the data not used for model development. Random forest performed significantly better than LR (P < 0.01), achieving a test accuracy of 0.96 and an area under the curve (AUC) of 0.80 (vs. an accuracy of 0.96 and an AUC of 0.75). The percentage of ventricular pacing and the daytime activity were the most relevant variables in the RF model. The use of large-scale machine learning showed that daily summaries of ICD measurements in the absence of clinical information can predict the short-term risk of ES.

Background: Artificial intelligence (AI), such as machine learning (ML), shows great promise for improving clinical decision-making in cardiac diseases by outperforming statistical-based models. However, few AI-based tools have been implemented in cardiology clinics because of the sociotechnical challenges during transitioning from algorithm development to real-world implementation. Objective: This study explored how an ML-based tool for predicting ventricular tachycardia and ventricular fibrillation (VT/VF) could support clinical decision-making in the remote monitoring of patients with an implantable cardioverter defibrillator (ICD). Methods: Seven experienced electrophysiologists participated in a near-live feasibility and qualitative study, which included walkthroughs of 5 blinded retrospective patient cases, use of the prediction tool, and questionnaires and interview questions. All sessions were video recorded, and sessions evaluating the prediction tool were transcribed verbatim. Data were analyzed through an inductive qualitative approach based on grounded theory. Results: The prediction tool was found to have potential for supporting decision-making in ICD remote monitoring by providing reassurance, increasing confidence, acting as a second opinion, reducing information search time, and enabling delegation of decisions to nurses and technicians. However, the prediction tool did not lead to changes in clinical action and was found less useful in cases where the quality of data was poor or when VT/VF predictions were found to be irrelevant for evaluating the patient. Conclusions: When transitioning from AI development to testing its feasibility for clinical implementation, we need to consider the following: expectations must be aligned with the intended use of AI; trust in the prediction tool is likely to emerge from real-world use; and AI accuracy is relational and dependent on available information and local workflows. Addressing the sociotechnical gap between the development and implementation of clinical decision-support tools based on ML in cardiac care is essential for succeeding with adoption. It is suggested to include clinical end-users, clinical contexts, and workflows throughout the overall iterative approach to design, development, and implementation.