We developed and validated TRisk, a Transformer-based AI model predicting 36-month mortality in heart failure patients by analysing temporal patient journeys from UK electronic health records (EHR). Our study included 403,534 heart failure patients (ages 40-90) from 1,418 English general practices, with 1,063 practices for model derivation and 355 for external validation. TRisk was compared against the MAGGIC-EHR model across various patient subgroups. With median follow-up of 9 months, TRisk achieved a concordance index of 0.845 (95% confidence interval: [0.841, 0.849]), significantly outperforming MAGGIC-EHR's 0.728 (0.723, 0.733) for predicting 36-month all-cause mortality. TRisk showed more consistent performance across sex, age, and baseline characteristics, suggesting less bias. We successfully adapted TRisk to US hospital data through transfer learning, achieving a C-index of 0.802 (0.789, 0.816) with 21,767 patients. Explainability analyses revealed TRisk captured established risk factors while identifying underappreciated predictors like cancers and hepatic failure that were important across both cohorts. Notably, cancers maintained strong prognostic value even a decade after diagnosis. TRisk demonstrated well-calibrated mortality prediction across both healthcare systems. Our findings highlight the value of tracking longitudinal health profiles and revealed risk factors not included in previous expert-driven models.

Coronary artery calcium (CAC) is highly predictive of cardiovascular events. While millions of chest CT scans are performed annually in the United States, CAC is not routinely quantified from scans done for non-cardiac purposes. A deep learning algorithm was developed using 446 expert segmentations to automatically quantify CAC on non-contrast, non-gated CT scans (AI-CAC). Our study differs from prior works as we leverage imaging data across the Veterans Affairs national healthcare system, from 98 medical centers, capturing extensive heterogeneity in imaging protocols, scanners, and patients. AI-CAC performance on non-gated scans was compared against clinical standard ECG-gated CAC scoring. Non-gated AI-CAC differentiated zero vs. non-zero and less than 100 vs. 100 or greater Agatston scores with accuracies of 89.4% (F1 0.93) and 87.3% (F1 0.89), respectively, in 795 patients with paired gated scans within a year of a non-gated CT scan. Non-gated AI-CAC was predictive of 10-year all-cause mortality (CAC 0 vs. >400 group: 25.4% vs. 60.2%, Cox HR 3.49, p < 0.005), and composite first-time stroke, MI, or death (CAC 0 vs. >400 group: 33.5% vs. 63.8%, Cox HR 3.00, p < 0.005). In a screening dataset of 8,052 patients with low-dose lung cancer-screening CTs (LDCT), 3,091/8,052 (38.4%) individuals had AI-CAC >400. Four cardiologists qualitatively reviewed LDCT images from a random sample of >400 AI-CAC patients and verified that 527/531 (99.2%) would benefit from lipid-lowering therapy. To the best of our knowledge, this is the first non-gated CT CAC algorithm developed across a national healthcare system, on multiple imaging protocols, without filtering intra-cardiac hardware, and compared against a strong gated CT reference. We report superior performance relative to previous CAC algorithms evaluated against paired gated scans that included patients with intra-cardiac hardware.

Survival analysis is essential for studying time-to-event outcomes and providing a dynamic understanding of the probability of an event occurring over time. Various survival analysis techniques, from traditional statistical models to state-of-the-art machine learning algorithms, support healthcare intervention and policy decisions. However, there remains ongoing discussion about their comparative performance. We conducted a comparative study of several survival analysis methods, including Cox proportional hazards (CoxPH), stepwise CoxPH, elastic net penalized Cox model, Random Survival Forests (RSF), Gradient Boosting machine (GBM) learning, AutoScore-Survival, DeepSurv, time-dependent Cox model based on neural network (CoxTime), and DeepHit survival neural network. We applied the concordance index (C-index) for model goodness-of-fit, and integral Brier scores (IBS) for calibration, and considered the model interpretability. As a case study, we performed a retrospective analysis of patients admitted through the emergency department of a tertiary hospital from 2017 to 2019, predicting 90-day all-cause mortality based on patient demographics, clinicopathological features, and historical data. The results of the C-index indicate that deep learning achieved comparable performance, with DeepSurv producing the best discrimination (DeepSurv: 0.893; CoxTime: 0.892; DeepHit: 0.891). The calibration of DeepSurv (IBS: 0.041) performed the best, followed by RSF (IBS: 0.042) and GBM (IBS: 0.0421), all using the full variables. Moreover, AutoScore-Survival, using a minimal variable subset, is easy to interpret, and can achieve good discrimination and calibration (C-index: 0.867; IBS: 0.044). While all models were satisfactory, DeepSurv exhibited the best discrimination and calibration. In addition, AutoScore-Survival offers a more parsimonious model and excellent interpretability.

Worldwide, many millions of people die suddenly and unexpectedly each year, either with or without a prior history of cardiovascular disease. Such events are sparse (once in a lifetime), many victims will not have had prior investigations for cardiac disease and many different definitions of sudden death exist. Accordingly, sudden death is hard to predict. This analysis used NHS Electronic Health Records (EHRs) for people aged $\geq$50 years living in the Greater Glasgow and Clyde (GG\&C) region in 2010 (n = 380,000) to try to overcome these challenges. We investigated whether medical history, blood tests, prescription of medicines, and hospitalisations might, in combination, predict a heightened risk of sudden death. We compared the performance of models trained to predict either sudden death or all-cause mortality. We built six models for each outcome of interest: three taken from state-of-the-art research (BEHRT, Deepr and Deep Patient), and three of our own creation. We trained these using two different data representations: a language-based representation, and a sparse temporal matrix. We used global interpretability to understand the most important features of each model, and compare how much agreement there was amongst models using Rank Biased Overlap. It is challenging to account for correlated variables without increasing the complexity of the interpretability technique. We overcame this by clustering features into groups and comparing the most important groups for each model. We found the agreement between models to be much higher when accounting for correlated variables. Our analysis emphasises the challenge of predicting sudden death and emphasises the need for better understanding and interpretation of machine learning models applied to healthcare applications.

Effective learning from electronic health records (EHR) data for prediction of clinical outcomes is often challenging because of features recorded at irregular timesteps and loss to follow-up as well as competing events such as death or disease progression. To that end, we propose a generative time-to-event model, SurvLatent ODE, which adopts an Ordinary Differential Equation-based Recurrent Neural Networks (ODE-RNN) as an encoder to effectively parameterize dynamics of latent states under irregularly sampled input data. Our model then utilizes the resulting latent embedding to flexibly estimate survival times for multiple competing events without specifying shapes of event-specific hazard function. We demonstrate competitive performance of our model on MIMIC-III, a freely-available longitudinal dataset collected from critical care units, on predicting hospital mortality as well as the data from the Dana-Farber Cancer Institute (DFCI) on predicting onset of Venous Thromboembolism (VTE), a life-threatening complication for patients with cancer, with death as a competing event. SurvLatent ODE outperforms the current clinical standard Khorana Risk scores for stratifying VTE risk groups, while providing clinically meaningful and interpretable latent representations.

Summary: A new machine-learning algorithm which videos of echocardiograms is able to accurately predict patients who will die within a year. Researchers at Geisinger have found that a computer algorithm developed using echocardiogram videos of the heart can predict mortality within a year. The algorithm–an example of what is known as machine learning, or artificial intelligence (AI)–outperformed other clinically used predictors, including pooled cohort equations and the Seattle Heart Failure score. The results of the study were published in Nature Biomedical Engineering. "We were excited to find that machine learning can leverage unstructured datasets such as medical images and videos to improve on a wide range of clinical prediction models," said Chris Haggerty, Ph.D., co-senior author and assistant professor in the Department of Translational Data Science and Informatics at Geisinger.

Currently, the diagnosis of sleep disorders relies on polysomnographic recordings with a time-consuming manual analysis with low reliability between different manual scorers. Throughout the night, sleep stages are identified manually in non-overlapping 30-second epochs starting from the onset of the recording based on electroencephalography (EEG), electro-oculography (EOG), and chin electromyography (EMG) signals which require meticulous placement of electrodes. Moreover, the diagnosis of many sleep disorders relies on outdated guidelines. When assessing the severity of obstructive sleep apnea (OSA), the patients are classified based on thresholds of the apnea-hypopnea index (AHI), i.e. the number of respiratory disruptions during sleep. These thresholds are not fully based on solid scientific evidence and remain the same across different measurement techniques.

Semisupervised machine-learning methods are able to learn from fewer labeled patient data. We illustrate the potential use of a semisupervised automated machine-learning (AutoML) pipeline for phenotyping patients who underwent transcatheter aortic valve implantation and identifying patient groups with similar clinical outcome. Using the Transcatheter Valve Therapy registry data, we divided 344 patients into 2 sequential cohorts (cohort 1, n = 211, cohort 2, n = 143). We investigated patient similarity analysis to identify unique phenogroups of patients in the first cohort. We subsequently applied the semisupervised AutoML to the second cohort for developing automatic phenogroup labels.

Machine learning was found to be superior to logistic risk scores in predicting intrahospital all-cause mortality after transcatheter aortic valve implantation (TAVI), according to study results published in Clinical Research in Cardiology. Current strategies for identifying patients eligible for TAVI rely on risk assessment tools such as the Society of Thoracic Surgeon's Risk Score (STS score). The predictive power of these tools is poor, and improved options for risk stratification of TAVI patients are needed. In this retrospective analysis of data from 451 patients, investigators aimed to evaluate whether machine learning models could be used to predict clinical outcomes for patients after TAVI. A total of 83 features, including patient demographics, comorbidities, laboratory data, electro- and echocardiogram findings, and computed tomography (CT) results, were used to train and test the predictive models.

Question Is a convolutional neural network able to extract prognostic information from chest radiographs? Findings In this prognostic study of data from 2 randomized clinical trials (Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial [n 10 464] and National Lung Screening Trial [n 5493]), a convolutional neural network identified persons at high risk of long-term mortality based on their chest radiographs, even with adjustment for the radiologists' diagnostic findings and standard risk factors. Meaning Individuals at high risk of mortality based on chest radiography may benefit from prevention, screening, and lifestyle interventions. Importance Chest radiography is the most common diagnostic imaging test in medicine and may also provide information about longevity and prognosis. Objective To develop and test a convolutional neural network (CNN) (named CXR-risk) to predict long-term mortality, including noncancer death, from chest radiographs. Design, Setting, and Participants In this prognostic study, CXR-risk CNN development (n 41 856) and testing (n 10 464) used data from the screening radiography arm of the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial (PLCO) (n 52 320), a community cohort of asymptomatic nonsmokers and smokers (aged 55-74 years) enrolled at 10 US sites from November 8, 1993, through July 2, 2001. External testing used data from the screening radiography arm of the National Lung Screening Trial (NLST) (n 5493), a community cohort of heavy smokers (aged 55-74 years) enrolled at 21 US sites from August 2002, through April 2004. Data analysis was performed from January 1, 2018, to May 23, 2019. Exposure Deep learning CXR-risk score (very low, low, moderate, high, and very high) based on CNN analysis of the enrollment radiograph.