Derivation, External Validation and Clinical Implications of a deep learning approach for intracranial pressure estimation using non-cranial waveform measurements.

Importance: Increased intracranial pressure (ICP) is associated with adverse neurological outcomes, but needs invasive monitoring. Objective: Development and validation of an AI approach for detecting increased ICP (aICP) using only non-invasive extracranial physiological waveform data. Design: Retrospective diagnostic study of AI-assisted detection of increased ICP. We developed an AI model using exclusively extracranial waveforms, externally validated it and assessed associations with clinical outcomes. Setting: MIMIC-III Waveform Database (2000-2013), a database derived from patients admitted to an ICU in an academic Boston hospital, was used for development of the aICP model, and to report association with neurologic outcomes. Data from Mount Sinai Hospital (2020-2022) in New York City was used for external validation. Participants: Patients were included if they were older than 18 years, and were monitored with electrocardiograms, arterial blood pressure, respiratory impedance plethysmography and pulse oximetry. Patients who additionally had intracranial pressure monitoring were used for development (N=157) and external validation (N=56). Patients without intracranial monitors were used for association with outcomes (N=1694). Exposures: Extracranial waveforms including electrocardiogram, arterial blood pressure, plethysmography and SpO2. Main Outcomes and Measures: Intracranial pressure > 15 mmHg. Measures were Area under receiver operating characteristic curves (AUROCs), sensitivity, specificity, and accuracy at threshold of 0.5. We calculated odds ratios and p-values for phenotype association. Results: The AUROC was 0.91 (95% CI, 0.90-0.91) on testing and 0.80 (95% CI, 0.80-0.80) on external validation. aICP had accuracy, sensitivity, and specificity of 73.8% (95% CI, 72.0%-75.6%), 99.5% (95% CI 99.3%-99.6%), and 76.9% (95% CI, 74.0-79.8%) on external validation. A ten-percentile increment was associated with stroke (OR=2.12; 95% CI, 1.27-3.13), brain malignancy (OR=1.68; 95% CI, 1.09-2.60), subdural hemorrhage (OR=1.66; 95% CI, 1.07-2.57), intracerebral hemorrhage (OR=1.18; 95% CI, 1.07-1.32), and procedures like percutaneous brain biopsy (OR=1.58; 95% CI, 1.15-2.18) and craniotomy (OR = 1.43; 95% CI, 1.12-1.84; P < 0.05 for all). Conclusions and Relevance: aICP provides accurate, non-invasive estimation of increased ICP, and is associated with neurological outcomes and neurosurgical procedures in patients without intracranial monitoring.

Factors associated with resistance to SARS-CoV-2 infection discovered using large-scale medical record data and machine learning.

There have been over 621 million cases of COVID-19 worldwide with over 6.5 million deaths. Despite the high secondary attack rate of COVID-19 in shared households, some exposed individuals do not contract the virus. In addition, little is known about whether the occurrence of COVID-19 resistance differs among people by health characteristics as stored in the electronic health records (EHR). In this retrospective analysis, we develop a statistical model to predict COVID-19 resistance in 8,536 individuals with prior COVID-19 exposure using demographics, diagnostic codes, outpatient medication orders, and count of Elixhauser comorbidities in EHR data from the COVID-19 Precision Medicine Platform Registry. Cluster analyses identified 5 patterns of diagnostic codes that distinguished resistant from non-resistant patients in our study population. In addition, our models showed modest performance in predicting COVID-19 resistance (best performing model AUROC = 0.61). Monte Carlo simulations conducted indicated that the AUROC results are statistically significant (p < 0.001) for the testing set. We hope to validate the features found to be associated with resistance/non-resistance through more advanced association studies.

A pilot study to predict cardiac arrest in the pediatric intensive care unit.

BACKGROUND: Cardiac arrest is a leading cause of mortality prior to discharge for children admitted to the pediatric intensive care unit. To address this problem, we used machine learning to predict cardiac arrest up to three hours in advance. METHODS: Our data consists of 240 Hz ECG waveform data, 0.5 Hz physiological time series data, medications, and demographics from 1,145 patients in the pediatric intensive care unit at the Johns Hopkins Hospital, 15 of whom experienced a cardiac arrest. The data were divided into training, validating, and testing sets, and features were generated every five minutes. 23 heart rate variability (HRV) metrics were determined from ECG waveforms. 96 summary statistics were calculated for 12 vital signs, such as respiratory rate and blood pressure. Medications were classified into 42 therapeutic drug classes. Binary features were generated to indicate the administration of these different drugs. Next, six machine learning models were evaluated: logistic regression, support vector machine, random forest, XGBoost, LightGBM, and a soft voting ensemble. RESULTS: XGBoost performed the best, with 0.971 auROC, 0.797 auPRC, 99.5% sensitivity, and 69.6% specificity on an independent test set. CONCLUSION: We have created high-performing models that identify signatures of in-hospital cardiac arrest (IHCA) that may not be evident to clinicians. These signatures include a combination of heart rate variability metrics, vital signs data, and therapeutic drug classes. These machine learning models can predict IHCA up to three hours prior to onset with high performance, allowing clinicians to intervene earlier, improving patient outcomes.

Deep Learning Model for Static Ocular Torsion Detection Using Synthetically Generated Fundus Images.

Purpose: The objective of the study is to develop deep learning models using synthetic fundus images to assess the direction (intorsion versus extorsion) and amount (physiologic versus pathologic) of static ocular torsion. Static ocular torsion assessment is an important clinical tool for classifying vertical ocular misalignment; however, current methods are time-intensive with steep learning curves for frontline providers. Methods: We used a dataset (n = 276) of right eye fundus images. The disc-foveal angle was calculated using ImageJ to generate synthetic images via image rotation. Using synthetic datasets (n = 12,740 images per model) and transfer learning (the reuse of a pretrained deep learning model on a new task), we developed a binary classifier (intorsion versus extorsion) and a multiclass classifier (physiologic versus pathologic intorsion and extorsion). Model performance was evaluated on unseen synthetic and nonsynthetic data. Results: On the synthetic dataset, the binary classifier had an accuracy and area under the receiver operating characteristic curve (AUROC) of 0.92 and 0.98, respectively, whereas the multiclass classifier had an accuracy and AUROC of 0.77 and 0.94, respectively. The binary classifier generalized well on the nonsynthetic data (accuracy = 0.94; AUROC = 1.00). Conclusions: The direction of static ocular torsion can be detected from synthetic fundus images using deep learning methods, which is key to differentiate between vestibular misalignment (skew deviation) and ocular muscle misalignment (superior oblique palsies). Translational Relevance: Given the robust performance of our models on real fundus images, similar strategies can be adopted for deep learning research in rare neuro-ophthalmologic diseases with limited datasets.

Adequacy of samples obtained via percutaneous core-needle rebiopsy for EGFR T790M molecular analysis in patients with non-small cell lung cancer following acquired resistance to first-line therapy: A systematic review and meta-analysis.

MICRO ABSTRACT: Rebiopsies characterizing resistance mutations in patients with non-small cell lung cancer (NSCLC) can guide personalized medicine and improve overall survival rates. In this systematic review, we examine the suitability of percutaneous core-needle biopsy (PT-CNB) to obtain adequate samples for molecular characterization of the acquired resistance mutation T790M. This review provides evidence that PT-CNB can obtain samples with high adequacy, with a mutation detection rate that is in accordance with prior literature. BACKGROUND: Non-small cell lung cancer (NSCLC) comprises 85% of all lung cancers and has seen improved survival rates with the rise of personalized medicine. Resistance mutations to first-line therapies, such as T790M, however, render first-line therapies ineffective. Rebiopsies characterizing resistance mutations inform therapeutic decisions, which result in prolonged survival. Given the high efficacy of percutaneous core-needle biopsy (PT-CNB), we conducted the first systematic review to analyze the ability of PT-CNB to obtain samples of high adequacy in order to characterize the acquired resistance mutation T790M in patients with NSCLC. METHODS: We performed a comprehensive literature search across PubMed, Embase, and CENTRAL. Search terms related to "NSCLC," "rebiopsy," and "PT-CNB" were used to obtain results. We included all prospective and retrospective studies that satisfied our inclusion and exclusion criteria. A random effects model was utilized to pool adequacy and detection rates of the chosen articles. We performed a systematic review, meta-analysis, and meta-regression to investigate the adequacy and T790M detection rates of samples obtained via PT-CNB. RESULTS: Out of the 173 studies initially identified, 5 studies met the inclusion and exclusion criteria and were chosen for our final cohort of 436 patients for meta-analysis. The pooled adequacy rate of samples obtained via PT-CNB was 86.92% (95% CI: [79.31%, 92.0%]) and the pooled T790M detection rate was 46.0% (95% CI: [26.6%, 66.7%]). There was considerable heterogeneity among studies (I2 > 50%) in both adequacy and T790M detection rates. CONCLUSION: PT-CNB can obtain adequate samples for T790M molecular characterization in NSCLC lung cancer patients. Additional prospective studies are needed to corroborate the results in this review.