Perspectives on label-free microscopy of heterogeneous and dynamic biological systems.

Significance: Advancements in label-free microscopy could provide real-time, non-invasive imaging with unique sources of contrast and automated standardized analysis to characterize heterogeneous and dynamic biological processes. These tools would overcome challenges with widely used methods that are destructive (e.g., histology, flow cytometry) or lack cellular resolution (e.g., plate-based assays, whole animal bioluminescence imaging). Aim: This perspective aims to (1) justify the need for label-free microscopy to track heterogeneous cellular functions over time and space within unperturbed systems and (2) recommend improvements regarding instrumentation, image analysis, and image interpretation to address these needs. Approach: Three key research areas (cancer research, autoimmune disease, and tissue and cell engineering) are considered to support the need for label-free microscopy to characterize heterogeneity and dynamics within biological systems. Based on the strengths (e.g., multiple sources of molecular contrast, non-invasive monitoring) and weaknesses (e.g., imaging depth, image interpretation) of several label-free microscopy modalities, improvements for future imaging systems are recommended. Conclusion: Improvements in instrumentation including strategies that increase resolution and imaging speed, standardization and centralization of image analysis tools, and robust data validation and interpretation will expand the applications of label-free microscopy to study heterogeneous and dynamic biological systems.

AI as a Medical Device Adverse Event Reporting in Regulatory Databases: Protocol for a Systematic Review.

BACKGROUND: The reporting of adverse events (AEs) relating to medical devices is a long-standing area of concern, with suboptimal reporting due to a range of factors including a failure to recognize the association of AEs with medical devices, lack of knowledge of how to report AEs, and a general culture of nonreporting. The introduction of artificial intelligence as a medical device (AIaMD) requires a robust safety monitoring environment that recognizes both generic risks of a medical device and some of the increasingly recognized risks of AIaMD (such as algorithmic bias). There is an urgent need to understand the limitations of current AE reporting systems and explore potential mechanisms for how AEs could be detected, attributed, and reported with a view to improving the early detection of safety signals. OBJECTIVE: The systematic review outlined in this protocol aims to yield insights into the frequency and severity of AEs while characterizing the events using existing regulatory guidance. METHODS: Publicly accessible AE databases will be searched to identify AE reports for AIaMD. Scoping searches have identified 3 regulatory territories for which public access to AE reports is provided: the United States, the United Kingdom, and Australia. AEs will be included for analysis if an artificial intelligence (AI) medical device is involved. Software as a medical device without AI is not within the scope of this review. Data extraction will be conducted using a data extraction tool designed for this review and will be done independently by AUK and a second reviewer. Descriptive analysis will be conducted to identify the types of AEs being reported, and their frequency, for different types of AIaMD. AEs will be analyzed and characterized according to existing regulatory guidance. RESULTS: Scoping searches are being conducted with screening to begin in April 2024. Data extraction and synthesis will commence in May 2024, with planned completion by August 2024. The review will highlight the types of AEs being reported for different types of AI medical devices and where the gaps are. It is anticipated that there will be particularly low rates of reporting for indirect harms associated with AIaMD. CONCLUSIONS: To our knowledge, this will be the first systematic review of 3 different regulatory sources reporting AEs associated with AIaMD. The review will focus on real-world evidence, which brings certain limitations, compounded by the opacity of regulatory databases generally. The review will outline the characteristics and frequency of AEs reported for AIaMD and help regulators and policy makers to continue developing robust safety monitoring processes. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/48156.

Machine Learned Classification of Ligand Intrinsic Activities at Human µ-Opioid Receptor.

Opioids are small-molecule agonists of µ-opioid receptor (µOR), while reversal agents such as naloxone are antagonists of µOR. Here, we developed machine learning (ML) models to classify the intrinsic activities of ligands at the human µOR based on the SMILES strings and two-dimensional molecular descriptors. We first manually curated a database of 983 small molecules with measured Emax values at the human µOR. Analysis of the chemical space allowed identification of dominant scaffolds and structurally similar agonists and antagonists. Decision tree models and directed message passing neural networks (MPNNs) were then trained to classify agonistic and antagonistic ligands. The hold-out test AUCs (areas under the receiver operator curves) of the extra-tree (ET) and MPNN models are 91.5 ± 3.9% and 91.8 ± 4.4%, respectively. To overcome the challenge of a small data set, a student-teacher learning method called tritraining with disagreement was tested using an unlabeled data set comprised of 15,816 ligands of human, mouse, and rat µOR, κOR, and δOR. We found that the tritraining scheme was able to increase the hold-out AUC of MPNN models to as high as 95.7%. Our work demonstrates the feasibility of developing ML models to accurately predict the intrinsic activities of µOR ligands, even with limited data. We envisage potential applications of these models in evaluating uncharacterized substances for public safety risks and discovering new therapeutic agents to counteract opioid overdoses.

Performance Assessment of Universal Machine Learning Interatomic Potentials: Challenges and Directions for Materials' Surfaces.

Machine learning interatomic potentials (MLIPs) are one of the main techniques in the materials science toolbox, able to bridge ab initio accuracy with the computational efficiency of classical force fields. This allows simulations ranging from atoms, molecules, and biosystems, to solid and bulk materials, surfaces, nanomaterials, and their interfaces and complex interactions. A recent class of advanced MLIPs, which use equivariant representations and deep graph neural networks, is known as universal models. These models are proposed as foundation models suitable for any system, covering most elements from the periodic table. Current universal MLIPs (UIPs) have been trained with the largest consistent data set available nowadays. However, these are composed mostly of bulk materials' DFT calculations. In this article, we assess the universality of all openly available UIPs, namely MACE, CHGNet, and M3GNet, in a representative task of generalization: calculation of surface energies. We find that the out-of-the-box foundation models have significant shortcomings in this task, with errors correlated to the total energy of surface simulations, having an out-of-domain distance from the training data set. Our results show that while UIPs are an efficient starting point for fine-tuning specialized models, we envision the potential of increasing the coverage of the materials space toward universal training data sets for MLIPs.

The conversational AI "ChatGPT" outperforms medical students on a physiology university examination.

Artificial intelligence (AI) has gained massive interest with the public release of the conversational AI "ChatGPT" but it also has become a matter of concern for academia as it can easily be misused. We performed a quantitative evaluation of the performance of ChatGPT on a medical physiology university examination. Forty-one answers were obtained with ChatGPT and compared to the results of 24 students. The results of ChatGPT were significantly better than those of the students; median (IQR) score was 75 (66-84) % for the AI compared to 56 (43-65) % for students (p<0.001). The exam success rate was 100% for ChatGPT, whereas 29% (n=7) of students failed. ChatGPT could promote plagiarism and intellectual laziness among students and could represent a new and easy way to cheat, especially when evaluations are performed online. Considering that these powerful AI tools are now freely available, scholars should take great care to construct assessments that really evaluate the student reflection skills and prevent AI-assisted cheating.

From Organ-on-a-Chip to Human-on-a-Chip: A Review of Research Progress and Latest Applications.

Organ-on-a-Chip (OOC) technology, which emulates the physiological environment and functionality of human organs on a microfluidic chip, is undergoing significant technological advancements. Despite its rapid evolution, this technology is also facing notable challenges, such as the lack of vascularization, the development of multiorgan-on-a-chip systems, and the replication of the human body on a single chip. The progress of microfluidic technology has played a crucial role in steering OOC toward mimicking the human microenvironment, including vascularization, microenvironment replication, and the development of multiorgan microphysiological systems. Additionally, advancements in detection, analysis, and organoid imaging technologies have enhanced the functionality and efficiency of Organs-on-Chips (OOCs). In particular, the integration of artificial intelligence has revolutionized organoid imaging, significantly enhancing high-throughput drug screening. Consequently, this review covers the research progress of OOC toward Human-on-a-chip, the integration of sensors in OOCs, and the latest applications of organoid imaging technologies in the biomedical field.

Application of artificial intelligence in drug design: A review.

Artificial intelligence (AI) is a field of computer science that involves acquiring information, developing rule bases, and mimicking human behaviour. The fundamental concept behind AI is to create intelligent computer systems that can operate with minimal human intervention or without any intervention at all. These rule-based systems are developed using various machine learning and deep learning models, enabling them to solve complex problems. AI is integrated with these models to learn, understand, and analyse provided data. The rapid advancement of Artificial Intelligence (AI) is reshaping numerous industries, with the pharmaceutical sector experiencing a notable transformation. AI is increasingly being employed to automate, optimize, and personalize various facets of the pharmaceutical industry, particularly in pharmacological research. Traditional drug development methods areknown for being time-consuming, expensive, and less efficient, often taking around a decade and costing billions of dollars. The integration of artificial intelligence (AI) techniques addresses these challenges by enabling the examination of compounds with desired properties from a vast pool of input drugs. Furthermore, it plays a crucial role in drug screening by predicting toxicity, bioactivity, ADME properties (absorption, distribution, metabolism, and excretion), physicochemical properties, and more. AI enhances the drug design process by improving the efficiency and accuracy of predicting drug behaviour, interactions, and properties. These approaches further significantly improve the precision of drug discovery processes and decrease clinical trial costs leading to the development of more effective drugs.

Deep learning of Parkinson's movement from video, without human-defined measures.

BACKGROUND: The core clinical sign of Parkinson's disease (PD) is bradykinesia, for which a standard test is finger tapping: the clinician observes a person repetitively tap finger and thumb together. That requires an expert eye, a scarce resource, and even experts show variability and inaccuracy. Existing applications of technology to finger tapping reduce the tapping signal to one-dimensional measures, with researcher-defined features derived from those measures. OBJECTIVES: (1) To apply a deep learning neural network directly to video of finger tapping, without human-defined measures/features, and determine classification accuracy for idiopathic PD versus controls. (2) To visualise the features learned by the model. METHODS: 152 smartphone videos of 10s finger tapping were collected from 40 people with PD and 37 controls. We down-sampled pixel dimensions and videos were split into 1 s clips. A 3D convolutional neural network was trained on these clips. RESULTS: For discriminating PD from controls, our model showed training accuracy 0.91, and test accuracy 0.69, with test precision 0.73, test recall 0.76 and test AUROC 0.76. We also report class activation maps for the five most predictive features. These show the spatial and temporal sections of video upon which the network focuses attention to make a prediction, including an apparent dropping thumb movement distinct for the PD group. CONCLUSIONS: A deep learning neural network can be applied directly to standard video of finger tapping, to distinguish PD from controls, without a requirement to extract a one-dimensional signal from the video, or pre-define tapping features.

Emotional and cognitive trust in artificial intelligence: A framework for identifying research opportunities.

This article briefly summarizes trust as a multi-dimensional construct, and trust in AI as a unique but related construct. It argues that because trust in AI is couched within an economic landscape, these two frameworks should be combined to understand the dynamics of trust in AI as it is currently implemented. The review focuses on healthcare and law enforcement as two industries that have adopted AI in ways that do and do not engender trust from stakeholders. The framework is applied to both industries to highlight where and why varying trust in AI is observed. Then seven research questions are posed, and researchers are encouraged to test the proposed framework in other AI-reliant contexts, like education and employment.

Development and validation of AI-derived segmentation of four-chamber cine cardiac magnetic resonance.

BACKGROUND: Cardiac magnetic resonance (CMR) in the four-chamber plane offers comprehensive insight into the volumetrics of the heart. We aimed to develop an artificial intelligence (AI) model of time-resolved segmentation using the four-chamber cine. METHODS: A fully automated deep learning algorithm was trained using retrospective multicentre and multivendor data of 814 subjects. Validation, reproducibility, and mortality prediction were evaluated on an independent cohort of 101 subjects. RESULTS: The mean age of the validation cohort was 54 years, and 66 (65%) were males. Left and right heart parameters demonstrated strong correlations between automated and manual analysis, with a ρ of 0.91-0.98 and 0.89-0.98, respectively, with minimal bias. All AI four-chamber volumetrics in repeatability analysis demonstrated high correlation (ρ = 0.99-1.00) and no bias. Automated four-chamber analysis underestimated both left ventricular (LV) and right ventricular (RV) volumes compared to ground-truth short-axis cine analysis. Two correction factors for LV and RV four-chamber analysis were proposed based on systematic bias. After applying the correction factors, a strong correlation and minimal bias for LV volumetrics were observed. During a mean follow-up period of 6.75 years, 16 patients died. On stepwise multivariable analysis, left atrial ejection fraction demonstrated an independent association with death in both manual (hazard ratio (HR) = 0.96, p = 0.003) and AI analyses (HR = 0.96, p < 0.001). CONCLUSION: Fully automated four-chamber CMR is feasible, reproducible, and has the same real-world prognostic value as manual analysis. LV volumes by four-chamber segmentation were comparable to short-axis volumetric assessment. TRIALS REGISTRATION: ClinicalTrials.gov: NCT05114785. RELEVANCE STATEMENT: Integrating fully automated AI in CMR promises to revolutionise clinical cardiac assessment, offering efficient, accurate, and prognostically valuable insights for improved patient care and outcomes. KEY POINTS: • Four-chamber cine sequences remain one of the most informative acquisitions in CMR examination. • This deep learning-based, time-resolved, fully automated four-chamber volumetric, functional, and deformation analysis solution. • LV and RV were underestimated by four-chamber analysis compared to ground truth short-axis segmentation. • Correction bias for both LV and RV volumes by four-chamber segmentation, minimises the systematic bias.

Does using artificial intelligence assistance accelerate skill decay and hinder skill development without performers' awareness?

Artificial intelligence in the workplace is becoming increasingly common. These tools are sometimes used to aid users in performing their task, for example, when an artificial intelligence tool assists a radiologist in their search for abnormalities in radiographic images. The use of artificial intelligence brings a wealth of benefits, such as increasing the efficiency and efficacy of performance. However, little research has been conducted to determine how the use of artificial intelligence assistants might affect the user's cognitive skills. In this theoretical perspective, we discuss how artificial intelligence assistants might accelerate skill decay among experts and hinder skill acquisition among learners. Further, we discuss how AI assistants might also prevent experts and learners from recognizing these deleterious effects. We then discuss the types of questions: use-inspired basic cognitive researchers, applied researchers, and computer science researchers should seek to answer. We conclude that multidisciplinary research from use-inspired basic cognitive research, domain-specific applied research, and technical research (e.g., human factors research, computer science research) is needed to (a) understand these potential consequences, (b) design artificial intelligence systems to mitigate these impacts, and (c) develop training and use protocols to prevent negative impacts on users' cognitive skills. Only by answering these questions from multidisciplinary perspectives can we harness the benefits of artificial intelligence in the workplace while preventing negative impacts on users' cognitive skills.

How Artificial Intelligence Will Transform Clinical Care, Research, and Trials for Inflammatory Bowel Disease.

Artificial intelligence (AI) refers to computer-based methodologies which use data to teach a computer to solve pre-defined tasks; these methods can be applied to identify patterns in large multi-modal data sources. AI applications in inflammatory bowel disease (IBD) includes predicting response to therapy, disease activity scoring of endoscopy, drug discovery, and identifying bowel damage in images. As a complex disease with entangled relationships between genomics, metabolomics, microbiome, and the environment, IBD stands to benefit greatly from methodologies that can handle this complexity. We describe current applications, critical challenges, and propose future directions of AI in IBD.

YOLO-V5 based deep learning approach for tooth detection and segmentation on pediatric panoramic radiographs in mixed dentition.

OBJECTIVES: In the interpretation of panoramic radiographs (PRs), the identification and numbering of teeth is an important part of the correct diagnosis. This study evaluates the effectiveness of YOLO-v5 in the automatic detection, segmentation, and numbering of deciduous and permanent teeth in mixed dentition pediatric patients based on PRs. METHODS: A total of 3854 mixed pediatric patients PRs were labelled for deciduous and permanent teeth using the CranioCatch labeling program. The dataset was divided into three subsets: training (n = 3093, 80% of the total), validation (n = 387, 10% of the total) and test (n = 385, 10% of the total). An artificial intelligence (AI) algorithm using YOLO-v5 models were developed. RESULTS: The sensitivity, precision, F-1 score, and mean average precision-0.5 (mAP-0.5) values were 0.99, 0.99, 0.99, and 0.98 respectively, to teeth detection. The sensitivity, precision, F-1 score, and mAP-0.5 values were 0.98, 0.98, 0.98, and 0.98, respectively, to teeth segmentation. CONCLUSIONS: YOLO-v5 based models can have the potential to detect and enable the accurate segmentation of deciduous and permanent teeth using PRs of pediatric patients with mixed dentition.

The clinical value of artificial intelligence in assisting junior radiologists in thyroid ultrasound: a multicenter prospective study from real clinical practice.

BACKGROUND: This study is to propose a clinically applicable 2-echelon (2e) diagnostic criteria for the analysis of thyroid nodules such that low-risk nodules are screened off while only suspicious or indeterminate ones are further examined by histopathology, and to explore whether artificial intelligence (AI) can provide precise assistance for clinical decision-making in the real-world prospective scenario. METHODS: In this prospective study, we enrolled 1036 patients with a total of 2296 thyroid nodules from three medical centers. The diagnostic performance of the AI system, radiologists with different levels of experience, and AI-assisted radiologists with different levels of experience in diagnosing thyroid nodules were evaluated against our proposed 2e diagnostic criteria, with the first being an arbitration committee consisting of 3 senior specialists and the second being cyto- or histopathology. RESULTS: According to the 2e diagnostic criteria, 1543 nodules were classified by the arbitration committee, and the benign and malignant nature of 753 nodules was determined by pathological examinations. Taking pathological results as the evaluation standard, the sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) of the AI systems were 0.826, 0.815, 0.821, and 0.821. For those cases where diagnosis by the Arbitration Committee were taken as the evaluation standard, the sensitivity, specificity, accuracy, and AUC of the AI system were 0.946, 0.966, 0.964, and 0.956. Taking the global 2e diagnostic criteria as the gold standard, the sensitivity, specificity, accuracy, and AUC of the AI system were 0.868, 0.934, 0.917, and 0.901, respectively. Under different criteria, AI was comparable to the diagnostic performance of senior radiologists and outperformed junior radiologists (all P < 0.05). Furthermore, AI assistance significantly improved the performance of junior radiologists in the diagnosis of thyroid nodules, and their diagnostic performance was comparable to that of senior radiologists when pathological results were taken as the gold standard (all p > 0.05). CONCLUSIONS: The proposed 2e diagnostic criteria are consistent with real-world clinical evaluations and affirm the applicability of the AI system. Under the 2e criteria, the diagnostic performance of the AI system is comparable to that of senior radiologists and significantly improves the diagnostic capabilities of junior radiologists. This has the potential to reduce unnecessary invasive diagnostic procedures in real-world clinical practice.

BART, the new robotic assistant: big data, artificial intelligence, robotics, and telemedicine integration for an ICU 4.0.

We are in the era of Health 4.0 when novel technologies are providing tools capable of improving the quality and safety of the services provided. Our project involves the integration of different technologies (AI, big data, robotics, and telemedicine) to create a unique system for patients admitted to intensive care units suffering from infectious diseases capable of both increasing the personalization of care and ensuring a safer environment for caregivers.

Current technological advancement in asthma care.

INTRODUCTION: Asthma is a common chronic respiratory disease affecting 262 million people globally, causing half a million deaths each year. Poor asthma outcomes are frequently due to non-adherence to medication, poor engagement with asthma services, and a lack of objective diagnostic tests. In recent years, technologies have been developed to improve diagnosis, monitoring, and care. AREAS COVERED: Technology has impacted asthma care with the potential to improve patient outcomes, reduce healthcare costs, and provide personalized management. We focus on current evidence on home diagnostics and monitoring, remote asthma reviews, and digital smart inhalers. PubMed, Ovid/Embase, Cochrane Library, Scopus and Google Scholar were searched in November 2023 with no limit by year of publication. EXPERT OPINION: Advanced diagnostic technologies have enabled early asthma detection and personalized treatment plans. Mobile applications and digital therapeutics empower patients to manage their condition and improve adherence to treatments. Telemedicine platforms and remote monitoring devices have the potential to streamline asthma care. AI algorithms can analyze patient data and predict exacerbations in proof-of-concept studies. Technology can potentially provide precision medicine to a wider patient group in the future, but further development is essential for implementation into routine care which in itself will be a major challenge.

Creating virtual patients using large language models: scalable, global, and low cost.

Virtual patients (VPs) have long been used to teach and assess clinical reasoning. VPs can be programmed to simulate authentic patient-clinician interactions and to reflect a variety of contextual permutations. However, their use has historically been limited by the high cost and logistical challenges of large-scale implementation. We describe a novel globally-accessible approach to develop low-cost VPs at scale using artificial intelligence (AI) large language models (LLMs). We leveraged OpenAI Generative Pretrained Transformer (GPT) to create and implement two interactive VPs, and created permutations that differed in contextual features. We used systematic prompt engineering to refine a prompt instructing ChatGPT to emulate the patient for a given case scenario, and then provide feedback on clinician performance. We implemented the prompts using GPT-3.5-turbo and GPT-4.0, and created a simple text-only interface using the OpenAI API. GPT-4.0 was far superior. We also conducted limited testing using another LLM (Anthropic Claude), with promising results. We provide the final prompt, case scenarios, and Python code. LLM-VPs represent a 'disruptive innovation' - an innovation that is unmistakably inferior to existing products but substantially more accessible (due to low cost, global reach, or ease of implementation) and thereby able to reach a previously underserved market. LLM-VPs will lay the foundation for global democratization via low-cost-low-risk scalable development of educational and clinical simulations. These powerful tools could revolutionize the teaching, assessment, and research of management reasoning, shared decision-making, and AI evaluation (e.g. 'software as a medical device' evaluations).

Reduced dose helical CT scout imaging on next generation wide volume CT system decreases scan length and overall radiation exposure.

Purpose: Traditional CT acquisition planning is based on scout projection images from planar anterior-posterior and lateral projections where the radiographer estimates organ locations. Alternatively, a new scout method utilizing ultra-low dose helical CT (3D Landmark Scan) offers cross-sectional imaging to identify anatomic structures in conjunction with artificial intelligence based Anatomic Landmark Detection (ALD) for automatic CT acquisition planning. The purpose of this study is to quantify changes in scan length and radiation dose of CT examinations planned using 3D Landmark Scan and ALD and performed on next generation wide volume CT versus examinations planned using traditional scout methods. We additionally aim to quantify changes in radiation dose reduction of scans planned with 3D Landmark Scan and performed on next generation wide volume CT. Methods: Single-center retrospective analysis of consecutive patients with prior CT scan of the same organ who underwent clinical CT using 3D Landmark Scan and automatic scan planning. Acquisition length and dose-length-product (DLP) were collected. Data was analyzed by paired t-tests. Results: 104 total CT examinations (48.1 % chest, 15.4 % abdomen, 36.5 % chest/abdomen/pelvis) on 61 individual consecutive patients at a single center were retrospectively analyzed. 79.8 % of scans using 3D Landmark Scan had reduction in acquisition length compared to the respective prior acquisition. Median acquisition length using 3D Landmark Scan was 26.7 mm shorter than that using traditional scout methods (p < 0.001) with a 23.3 % median total radiation dose reduction (245.6 (IQR 150.0-400.8) mGy cm vs 320.3 (IQR 184.1-547.9) mGy cm). CT dose index similarly was overall decreased for scans planned with 3D Landmark and ALD and performed on next generation CT versus traditional methods (4.85 (IQR 3.8-7) mGy vs. 6.70 (IQR 4.43-9.18) mGy, respectively, p < 0.001). Conclusion: Scout imaging using reduced dose 3D Landmark Scan images and Anatomic Landmark Detection reduces acquisition range in chest, abdomen, and chest/abdomen/pelvis CT scans. This technology, in combination with next generation wide volume CT reduces total radiation dose.

Accurate prediction of all-cause mortality in patients with metabolic dysfunction-associated steatotic liver disease using electronic health records.

INTRODUCTION AND OBJECTIVES: Despite the huge clinical burden of MASLD, validated tools for early risk stratification are lacking, and heterogeneous disease expression and a highly variable rate of progression to clinical outcomes result in prognostic uncertainty. We aimed to investigate longitudinal electronic health record-based outcome prediction in MASLD using a state-of-the-art machine learning model. PATIENTS AND METHODS: n = 940 patients with histologically-defined MASLD were used to develop a deep-learning model for all-cause mortality prediction. Patient timelines, spanning 12 years, were fully-annotated with demographic/clinical characteristics, ICD-9 and -10 codes, blood test results, prescribing data, and secondary care activity. A Transformer neural network (TNN) was trained to output concomitant probabilities of 12-, 24-, and 36-month all-cause mortality. In-sample performance was assessed using 5-fold cross-validation. Out-of-sample performance was assessed in an independent set of n = 528 MASLD patients. RESULTS: In-sample model performance achieved AUROC curve 0.74-0.90 (95 % CI: 0.72-0.94), sensitivity 64 %-82 %, specificity 75 %-92 % and Positive Predictive Value (PPV) 94 %-98 %. Out-of-sample model validation had AUROC 0.70-0.86 (95 % CI: 0.67-0.90), sensitivity 69 %-70 %, specificity 96 %-97 % and PPV 75 %-77 %. Key predictive factors, identified using coefficients of determination, were age, presence of type 2 diabetes, and history of hospital admissions with length of stay >14 days. CONCLUSIONS: A TNN, applied to routinely-collected longitudinal electronic health records, achieved good performance in prediction of 12-, 24-, and 36-month all-cause mortality in patients with MASLD. Extrapolation of our technique to population-level data will enable scalable and accurate risk stratification to identify people most likely to benefit from anticipatory health care and personalized interventions.