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.

An Artificial Neural Network for Nasogastric Tube Position Decision Support.

Purpose: To develop and validate a deep learning model for detection of nasogastric tube (NGT) malposition on chest radiographs and assess model impact as a clinical decision support tool for junior physicians to help determine whether feeding can be safely performed in patients (feed/do not feed). Materials and Methods: A neural network ensemble was pretrained on 1 132 142 retrospectively collected (June 2007-August 2019) frontal chest radiographs and further fine-tuned on 7081 chest radiographs labeled by three radiologists. Clinical relevance was assessed on an independent set of 335 images. Five junior emergency medicine physicians assessed chest radiographs and made feed/do not feed decisions without and with artificial intelligence (AI)-generated NGT malposition probabilities placed above chest radiographs. Decisions from the radiologists served as ground truths. Model performance was evaluated using receiver operating characteristic analysis. Agreement between junior physician and radiologist decision was determined using the Cohen κ coefficient. Results: In the testing set, the ensemble achieved area under the receiver operating characteristic curve values of 0.82 (95% CI: 0.78, 0.86), 0.77 (95% CI: 0.71, 0.83), and 0.98 (95% CI: 0.96, 1.00) for satisfactory, malpositioned, and bronchial positions, respectively. In the clinical evaluation set, mean interreader agreement for feed/do not feed decisions among junior physicians was 0.65 ± 0.03 (SD) and 0.77 ± 0.13 without and with AI support, respectively. Mean agreement between junior physicians and radiologists was 0.53 ± 0.05 (unaided) and 0.65 ± 0.09 (AI-aided). Conclusion: A simple classifier for NGT malposition may help junior physicians determine the safety of feeding in patients with NGTs.Keywords: Neural Networks, Feature Detection, Supervised Learning, Machine Learning Supplemental material is available for this article. Published under a CC BY 4.0 license.

Development and prospective validation of COVID-19 chest X-ray screening model for patients attending emergency departments.

Chest X-rays (CXRs) are the first-line investigation in patients presenting to emergency departments (EDs) with dyspnoea and are a valuable adjunct to clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to facilitate rapid triage of CXRs for further patient testing and/or isolation. In this work we develop an AI algorithm, CovIx, to differentiate normal, abnormal, non-COVID-19 pneumonia, and COVID-19 CXRs using a multicentre cohort of 293,143 CXRs. The algorithm is prospectively validated in 3289 CXRs acquired from patients presenting to ED with symptoms of COVID-19 across four sites in NHS Greater Glasgow and Clyde. CovIx achieves area under receiver operating characteristic curve for COVID-19 of 0.86, with sensitivity and F1-score up to 0.83 and 0.71 respectively, and performs on-par with four board-certified radiologists. AI-based algorithms can identify CXRs with COVID-19 associated pneumonia, as well as distinguish non-COVID pneumonias in symptomatic patients presenting to ED. Pre-trained models and inference scripts are freely available at https://github.com/beringresearch/bravecx-covid .

Supervised and unsupervised language modelling in Chest X-Ray radiological reports.

Chest radiography (CXR) is the most commonly used imaging modality and deep neural network (DNN) algorithms have shown promise in effective triage of normal and abnormal radiograms. Typically, DNNs require large quantities of expertly labelled training exemplars, which in clinical contexts is a major bottleneck to effective modelling, as both considerable clinical skill and time is required to produce high-quality ground truths. In this work we evaluate thirteen supervised classifiers using two large free-text corpora and demonstrate that bi-directional long short-term memory (BiLSTM) networks with attention mechanism effectively identify Normal, Abnormal, and Unclear CXR reports in internal (n = 965 manually-labelled reports, f1-score = 0.94) and external (n = 465 manually-labelled reports, f1-score = 0.90) testing sets using a relatively small number of expert-labelled training observations (n = 3,856 annotated reports). Furthermore, we introduce a general unsupervised approach that accurately distinguishes Normal and Abnormal CXR reports in a large unlabelled corpus. We anticipate that the results presented in this work can be used to automatically extract standardized clinical information from free-text CXR radiological reports, facilitating the training of clinical decision support systems for CXR triage.

Structure-preserving visualisation of high dimensional single-cell datasets.

Single-cell technologies offer an unprecedented opportunity to effectively characterize cellular heterogeneity in health and disease. Nevertheless, visualisation and interpretation of these multi-dimensional datasets remains a challenge. We present a novel framework, ivis, for dimensionality reduction of single-cell expression data. ivis utilizes a siamese neural network architecture that is trained using a novel triplet loss function. Results on simulated and real datasets demonstrate that ivis preserves global data structures in a low-dimensional space, adds new data points to existing embeddings using a parametric mapping function, and scales linearly to hundreds of thousands of cells. ivis is made publicly available through Python and R interfaces on https://github.com/beringresearch/ivis .