Objectives

This is a protocol for a Cochrane Review (prognosis). The objectives are as follows:

To identify and evaluate AI‐based prognostic models, in development and external validation studies, which predict impending episodes of ventricular tachycardia from continuous surface electrocardiogram (ECG) recordings in individuals at elevated risk for ventricular arrhythmias due to any relevant underlying condition.

Melanoma is the most common form of skin cancer, responsible for thousands of deaths annually. Novel therapies have been developed, but metastases are still a common problem, increasing the mortality rate and decreasing the quality of life of those who experience them. As traditional machine learning models for metastasis prediction have been limited to the use of a single modality, in this study we aim to explore and compare different unimodal and multimodal machine learning models to predict the onset of metastasis in melanoma patients to help clinicians focus their attention on patients at a higher risk of developing metastasis, increasing the likelihood of an earlier diagnosis.

We use a patient cohort derived from an Electronic Health Record, and we consider various modalities of data, including static, time series, and clinical text. We formulate the problem and propose a multimodal ML workflow for predicting the onset of metastasis in melanoma patients. We evaluate the performance of the workflow based on various classification metrics and statistical significance. The experimental findings suggest that multimodal models outperform the unimodal ones, demonstrating the potential of multimodal ML to predict the onset of metastasis.

The integration of artificial intelligence in healthcare has created a new era of advancements, reshaping patient care and revolutionizing public health interventions. Through artificial intelligence, healthcare providers and public health authorities can optimize interventions, leading to more precise and efficient responses that enhance patient outcomes and address public health challenges effectively. The past decade has witnessed a rapid digital transformation across industries, and healthcare is no exception. This evolution is evident in the widespread adoption of electronic health records and healthcare information systems and the integration of diverse technologies, including handheld, wearable, and smart devices.

A central challenge in this digital shift lies in representing data from multiple sources and modalities for downstream machine learning tasks. This complexity stems from the varied longitudinal or contextual events in patients' historical records, encompassing lab tests, vital signs, diagnoses, and drug administration. Additionally, the challenge extends to predictive modeling and constructing robust models that accurately classify future health events, taking into consideration heterogeneous health-related data. Electronic phenotyping, crucial for identifying fine-grained disease/patient clusters, is also a central problem when utilizing multisource and multimodal information effectively to create meaningful patient profiles. In the context of public health interventions, exemplified by crises like the COVID-19 pandemic, decision-making requires a delicate balance between optimizing intervention effectiveness and considering economic and societal well-being.

This Ph.D. thesis seeks to unravel the potential of multisource and multimodal health observational data in generating patient phenotypes and predictions for both individual health and public health surveillance. It addresses the following central question: How can multisource and multimodal observational health data be effectively harnessed, using machine learning, to enhance patient and public health? Comprising five studies, the thesis confronts challenges posed by diverse data sources and modalities, exploring strategies for creating comprehensive patient profiles, developing robust classification models, and employing clustering methods tailored to observational health data. The research seeks to provide valuable insights into integrating AI in healthcare, with a specific emphasis on the complexities of multisource and multimodal data integration. It underscores the importance of exploring heterogeneous health observational data to deepen our understanding of patient health and optimize machine learning applications. Emphasizing the intricate nature of health data, the thesis discusses careful data handling and innovative methodologies to maximize its potential impact on improving patient outcomes and informing public health strategies. The effective management of heterogeneous observational health data requires thoughtful consideration due to their varied sources and inherent complexities.

Sepsis refers to a potentially life-threatening situation where the immune system of the human body has an extreme response to an infection. In the presence of underlying comorbidities, the situation can become even worse and result in death. Employing unsupervised machine learning techniques, such as clustering, can assist in providing a better understanding of patient phenotypes by unveiling subgroups characterized by distinct sepsis progression and treatment patterns. More concretely, this study introduces M-ClustEHR, a clustering approach that utilizes medical data of multiple modalities by employing a multimodal autoencoder for learning comprehensive sepsis patient representations. M-ClustEHR consistently outperforms traditional clustering approaches in terms of several internal clustering performance metrics, as well as cluster stability in identifying phenotypes in the sepsis cohort. The unveiled patterns, supported by existing medical literature and clinicians, highlight the importance of multimodal clustering for advancing personalized sepsis care.

The impacts of climate change on mental health are starting to be recognized and may be exacerbated for populations at disproportionate risk of health impacts or inequalities, including some people living in low- and middle-income countries, children, indigenous populations, and people living in rural communities, among others. Here, we conduct a rapid scoping review of reviews to summarize the research to date on climate impacts on the mental health of populations at disproportionate risk. This review highlights the direct and indirect effects of climate change, the common mental health issues that have been studied related to climate events, and the populations that have been studied to date. This review outlines key gaps in the field and important research areas going forward. These include a need for more systematic methodologies, with before-and-after comparisons or exposure/non-exposure group comparisons and consistent mental health outcome measurements that are appropriately adapted for the populations being studied. Further research is also necessary in regard to the indirect effects of climate change and the climate effects on indigenous populations and populations with other protected and intersecting characteristics. This review highlights the key research areas to date and maps the critical future research necessary to develop future interventions.

Lung transplantation is a critical procedure performed in end-stage pulmonary patients. The number of lung transplantations performed in the USA in the last decade has been rising, but the survival rate is still lower than that of other solid organ transplantations. First, this study aims to employ machine learning models to predict patient survival after lung transplantation. Additionally, the aim is to generate counterfactual explanations based on these predictions to help clinicians and patients understand the changes needed to increase the probability of survival after the transplantation and better comply with normative requirements. We use data derived from the UNOS database, particularly the lung transplantations performed in the USA between 2019 and 2021. We formulate the problem and define two data representations, with the first being a representation that describes only the lung recipients and the second the recipients and donors. We propose an explainable ML workflow for predicting patient survival after lung transplantation. We evaluate the workflow based on various performance metrics, using five classification models and two counterfactual generation methods. Finally, we demonstrate the potential of explainable ML for resource allocation, predicting patient mortality, and generating explainable predictions for lung transplantation.

Background and Objective: Novel advances in machine learning (ML) and its subfield, deep learning (DL), as well as the recent release of large-scale electrocardiogram (ECG) databases, have driven a sharp increase in research related to automated ECG interpretation. This review aims to summarize the recent ML approaches for automatically interpreting standard 12-lead ECG signals.

Methods: We searched 10 indexing databases, for original research in English, referring to the application of ML/DL techniques in 12-lead, raw ECG signal analysis. The retrieved titles were filtered based on their relevance. The results were summarized and reported.

Key Content and Findings: More than 80% of studies integrated a DL approach, while fewer attempts applied a feature extraction method to obtain inputs for training a simple ML classifier. The average diagnostic accuracy was as high as 90%, while several other performance metrics, such as the area under the curve (AUC), F1-score, sensitivity and specificity, were also employed. DL models generally demanded 10-time more samples for training but were capable of better handling multi-class problems. The most frequently involved disease (49% of studies) was myocardial infarction (MI), while atrial fibrillation (AF) was encountered in more than one-third of studies. Various datasets were used for training and testing, constituting either private collections or publicly available databanks [such as the “Physikalisch-Technische Bundesanstalt” (PTB) dataset and datasets derived from the “China Physiological Signal Challenge” and the “Computing in Cardiology Challenge”]. Overall, DL and simpler ML approaches for automated ECG interpretation display unprecedented growth, reaching remarkably high performances.

Conclusions: While such novel tools can support clinicians in reaching reliable diagnoses for life-threatening conditions on the spot, concerns regarding their accountability do exist. Generalizability of the developed approaches is still an issue, possibly mitigable with the extensive deployment of developed models, so as to become massively accessible and validatable. Finally, the observed heterogeneity of the various attempts underlines the need for transparency and reproducibility in the development processes.

Epidemics of infectious diseases can pose a serious threat to public health and the global economy. Despite scientific advances, containment and mitigation of infectious diseases remain a challenging task. In this paper, we investigate the potential of reinforcement learning as a decision making tool for epidemic control by constructing a deep Reinforcement Learning simulator, called EpidRLearn, composed of a contact-based, age-structured extension of the SEIR compartmental model, referred to as C-SEIR. We evaluate EpidRLearn by comparing the learned policies to two deterministic policy baselines. We further assess our reward function by integrating an alternative reward into our deep RL model. The experimental evaluation indicates that deep reinforcement learning has the potential of learning useful policies under complex epidemiological models and large state spaces for the mitigation of infectious diseases, with a focus on COVID-19.

We present a clustering framework for identifying patient groups with Adverse Drug Reactions from Electronic Health Records (EHRs). The increased adoption of EHRs has brought changes in the way drug safety surveillance is carried out and plays an important role in effective drug regulation. Unsupervised machine learning methods using EHRs as their input can identify patients that share common meaningful information, without the need for expert input. In this work, we propose a generalized framework that exploits the strengths of different clustering algorithms and via clustering aggregation identifies consensus patient cluster profiles. Moreover, the inherent hierarchical structure of diagnoses and medication codes is exploited. We assess the statistical significance of the produced clusterings by applying a randomization technique that keeps the data distribution margins fixed, as we are interested in evaluating information that is not conveyed by the marginal distributions. The experimental findings suggest that the framework produces medically meaningful patient groups with regard to adverse drug events by investigating two use-cases, i.e., aplastic anaemia and drug-induced skin eruption.

Electronic Health Records are a valuable source of patient information which can be leveraged to detect Adverse Drug Events (ADEs) and aid post-mark drug-surveillance. The overall aim of this study is to scrutinize text written by clinicians in the EHRs and build a model for ADE detection that produces medically relevant predictions. Natural Language Processing techniques will be exploited to create important predictors and incorporate them into the learning process. The study focuses on the 5 most frequent ADE cases found ina Swedish electronic patient record corpus. The results indicate that considering textual features, rather than the structured, can improve the classification performance by 15{\%} in some ADE cases. Additionally, variable patient history lengths are incorporated in the models, demonstrating the importance of the above decision rather than using an arbitrary number for a history length. The experimental findings suggest that the clinical text in EHRs includes information that can capture data beyond the ones that are found in a structured format.