M. Brandon Westover

Harsh Parikh, Kentaro Hoffman, Haoqi Sun et al.

Epileptiform activity (EA) is associated with worse outcomes including increased risk of disability and death. However, the effect of EA on the neurologic outcome is confounded by the feedback between treatment with anti-seizure medications (ASM) and EA burden. A randomized clinical trial is challenging due to the sequential nature of EA-ASM feedback, as well as ethical reasons. However, some mechanistic knowledge is available, e.g., how drugs are absorbed. This knowledge together with observational data could provide a more accurate effect estimate using causal inference. We performed a retrospective cross-sectional study with 995 patients with the modified Rankin Scale (mRS) at discharge as the outcome and the EA burden defined as the mean or maximum proportion of time spent with EA in six-hour windows in the first 24 hours of electroencephalography as the exposure. We estimated the change in discharge mRS if everyone in the dataset had experienced a certain EA burden and were untreated. We combined pharmacological modeling with an interpretable matching method to account for confounding and EA-ASM feedback. Our matched groups' quality was validated by the neurologists. Having a maximum EA burden greater than 75% when untreated had a 22% increased chance of a poor outcome (severe disability or death), and mild but long-lasting EA increased the risk of a poor outcome by 14%. The effect sizes were heterogeneous depending on pre-admission profile, e.g., patients with hypoxic-ischemic encephalopathy (HIE) or acquired brain injury (ABI) were more affected. Interventions should put a higher priority on patients with an average EA burden higher than 10%, while treatment should be more conservative when the maximum EA burden is low.

Chaoqi Yang, M. Brandon Westover, Jimeng Sun

The vast amount of health data has been continuously collected for each patient, providing opportunities to support diverse healthcare predictive tasks such as seizure detection and hospitalization prediction. Existing models are mostly trained on other patients data and evaluated on new patients. Many of them might suffer from poor generalizability. One key reason can be overfitting due to the unique information related to patient identities and their data collection environments, referred to as patient covariates in the paper. These patient covariates usually do not contribute to predicting the targets but are often difficult to remove. As a result, they can bias the model training process and impede generalization. In healthcare applications, most existing domain generalization methods assume a small number of domains. In this paper, considering the diversity of patient covariates, we propose a new setting by treating each patient as a separate domain (leading to many domains). We develop a new domain generalization method ManyDG, that can scale to such many-domain problems. Our method identifies the patient domain covariates by mutual reconstruction and removes them via an orthogonal projection step. Extensive experiments show that ManyDG can boost the generalization performance on multiple real-world healthcare tasks (e.g., 3.7% Jaccard improvements on MIMIC drug recommendation) and support realistic but challenging settings such as insufficient data and continuous learning.

Alina Jade Barnett, Zhicheng Guo, Jin Jing et al.

In intensive care units (ICUs), critically ill patients are monitored with electroencephalograms (EEGs) to prevent serious brain injury. The number of patients who can be monitored is constrained by the availability of trained physicians to read EEGs, and EEG interpretation can be subjective and prone to inter-observer variability. Automated deep learning systems for EEG could reduce human bias and accelerate the diagnostic process. However, black box deep learning models are untrustworthy, difficult to troubleshoot, and lack accountability in real-world applications, leading to a lack of trust and adoption by clinicians. To address these challenges, we propose a novel interpretable deep learning model that not only predicts the presence of harmful brainwave patterns but also provides high-quality case-based explanations of its decisions. Our model performs better than the corresponding black box model, despite being constrained to be interpretable. The learned 2D embedded space provides the first global overview of the structure of ictal-interictal-injury continuum brainwave patterns. The ability to understand how our model arrived at its decisions will not only help clinicians to diagnose and treat harmful brain activities more accurately but also increase their trust and adoption of machine learning models in clinical practice; this could be an integral component of the ICU neurologists' standard workflow.

Harsh Parikh, Quinn Lanners, Zade Akras et al.

Recent statistical and reinforcement learning methods have significantly advanced patient care strategies. However, these approaches face substantial challenges in high-stakes contexts, including missing data, inherent stochasticity, and the critical requirements for interpretability and patient safety. Our work operationalizes a safe and interpretable framework to identify optimal treatment regimes. This approach involves matching patients with similar medical and pharmacological characteristics, allowing us to construct an optimal policy via interpolation. We perform a comprehensive simulation study to demonstrate the framework's ability to identify optimal policies even in complex settings. Ultimately, we operationalize our approach to study regimes for treating seizures in critically ill patients. Our findings strongly support personalized treatment strategies based on a patient's medical history and pharmacological features. Notably, we identify that reducing medication doses for patients with mild and brief seizure episodes while adopting aggressive treatment for patients in intensive care unit experiencing intense seizures leads to more favorable outcomes.

Songchi Zhou, Ge Song, Haoqi Sun et al.

Traditional sleep staging categorizes sleep and wakefulness into five coarse-grained classes, overlooking subtle variations within each stage. It provides limited information about the duration of arousal and may hinder research on sleep fragmentation and relevant sleep disorders. To address this issue, we propose a deep learning method for automatic and scalable annotation of continuous sleep depth index (SDI) using existing discrete sleep staging labels. Our approach was validated using polysomnography from over 10,000 recordings across four large-scale cohorts. The results showcased a strong correlation between the decrease in sleep depth index and the increase in duration of arousal. Specific case studies indicated that the sleep depth index captured more nuanced sleep structures than conventional sleep staging. Gaussian mixture models based on the digital biomarkers extracted from the sleep depth index identified two subtypes of sleep, where participants in the disturbed sleep group had a higher prevalence of sleep apnea, insomnia, poor subjective sleep quality, hypertension, and cardiovascular disease. The disturbed subtype was associated with a 42% (hazard ratio 1.42, 95% CI 1.24-1.62) increased risk of mortality and a 29% (hazard ratio 1.29, 95% CI 1.00-1.67) increased risk of fatal cardiovascular disease. Our study underscores the utility of the proposed method for continuous sleep depth annotation, which could reveal more detailed information about the sleep structure and yield novel digital biomarkers for routine clinical use in sleep medicine.

Guang-Bin Huang, M. Brandon Westover, Eng-King Tan et al.

Artificial Intelligence (AI) has apparently become one of the most important techniques discovered by humans in history while the human brain is widely recognized as one of the most complex systems in the universe. One fundamental critical question which would affect human sustainability remains open: Will artificial intelligence (AI) evolve to surpass human intelligence in the future? This paper shows that in theory new AI twins with fresh cellular level of AI techniques for neuroscience could approximate the brain and its functioning systems (e.g. perception and cognition functions) with any expected small error and AI without restrictions could surpass human intelligence with probability one in the end. This paper indirectly proves the validity of the conjecture made by Frank Rosenblatt 70 years ago about the potential capabilities of AI, especially in the realm of artificial neural networks. Intelligence is just one of fortuitous but sophisticated creations of the nature which has not been fully discovered. Like mathematics and physics, with no restrictions artificial intelligence would lead to a new subject with its self-contained systems and principles. We anticipate that this paper opens new doors for 1) AI twins and other AI techniques to be used in cellular level of efficient neuroscience dynamic analysis, functioning analysis of the brain and brain illness solutions; 2) new worldwide collaborative scheme for interdisciplinary teams concurrently working on and modelling different types of neurons and synapses and different level of functioning subsystems of the brain with AI techniques; 3) development of low energy of AI techniques with the aid of fundamental neuroscience properties; and 4) new controllable, explainable and safe AI techniques with reasoning capabilities of discovering principles in nature.

Dennis Tang, Jon Donnelly, Alina Jade Barnett et al.

The presence of interictal epileptiform discharges (IEDs) in electroencephalogram (EEG) recordings is a critical biomarker of epilepsy. Even trained neurologists find detecting IEDs difficult, leading many practitioners to turn to machine learning for help. While existing machine learning algorithms can achieve strong accuracy on this task, most models are uninterpretable and cannot justify their conclusions. Absent the ability to understand model reasoning, doctors cannot leverage their expertise to identify incorrect model predictions and intervene accordingly. To improve the human-model interaction, we introduce ProtoEEG-kNN, an inherently interpretable model that follows a simple case-based reasoning process. ProtoEEG-kNN reasons by comparing an EEG to similar EEGs from the training set and visually demonstrates its reasoning both in terms of IED morphology (shape) and spatial distribution (location). We show that ProtoEEG-kNN can achieve state-of-the-art accuracy in IED detection while providing explanations that experts prefer over existing approaches.

Chaoqi Yang, M. Brandon Westover, Jimeng Sun

Biological signals, such as electroencephalograms (EEG), play a crucial role in numerous clinical applications, exhibiting diverse data formats and quality profiles. Current deep learning models for biosignals are typically specialized for specific datasets and clinical settings, limiting their broader applicability. Motivated by the success of large language models in text processing, we explore the development of foundational models that are trained from multiple data sources and can be fine-tuned on different downstream biosignal tasks. To overcome the unique challenges associated with biosignals of various formats, such as mismatched channels, variable sample lengths, and prevalent missing values, we propose a Biosignal Transformer (\method). The proposed \method model can enable cross-data learning with mismatched channels, variable lengths, and missing values by tokenizing diverse biosignals into unified "biosignal sentences". Specifically, we tokenize each channel into fixed-length segments containing local signal features, flattening them to form consistent "sentences". Channel embeddings and {\em relative} position embeddings are added to preserve spatio-temporal features. The \method model is versatile and applicable to various biosignal learning settings across different datasets, including joint pre-training for larger models. Comprehensive evaluations on EEG, electrocardiogram (ECG), and human activity sensory signals demonstrate that \method outperforms robust baselines in common settings and facilitates learning across multiple datasets with different formats. Use CHB-MIT seizure detection task as an example, our vanilla \method model shows 3\% improvement over baselines in balanced accuracy, and the pre-trained \method models (optimized from other data sources) can further bring up to 4\% improvements.

Tanish Tyagi, Colin G. Magdamo, Ayush Noori et al.

Dementia related cognitive impairment (CI) is a neurodegenerative disorder, affecting over 55 million people worldwide and growing rapidly at the rate of one new case every 3 seconds. 75% cases go undiagnosed globally with up to 90% in low-and-middle-income countries, leading to an estimated annual worldwide cost of USD 1.3 trillion, forecasted to reach 2.8 trillion by 2030. With no cure, a recurring failure of clinical trials, and a lack of early diagnosis, the mortality rate is 100%. Information in electronic health records (EHR) can provide vital clues for early detection of CI, but a manual review by experts is tedious and error prone. Several computational methods have been proposed, however, they lack an enhanced understanding of the linguistic context in complex language structures of EHR. Therefore, I propose a novel and more accurate framework, NeuraHealth, to identify patients who had no earlier diagnosis. In NeuraHealth, using patient EHR from Mass General Brigham BioBank, I fine-tuned a bi-directional attention-based deep learning natural language processing model to classify sequences. The sequence predictions were used to generate structured features as input for a patient level regularized logistic regression model. This two-step framework creates high dimensionality, outperforming all existing state-of-the-art computational methods as well as clinical methods. Further, I integrate the models into a real-world product, a web app, to create an automated EHR screening pipeline for scalable and high-speed discovery of undetected CI in EHR, making early diagnosis viable in medical facilities and in regions with scarce health services.

Tanish Tyagi, Colin G. Magdamo, Ayush Noori et al.

Dementia is a neurodegenerative disorder that causes cognitive decline and affects more than 50 million people worldwide. Dementia is under-diagnosed by healthcare professionals - only one in four people who suffer from dementia are diagnosed. Even when a diagnosis is made, it may not be entered as a structured International Classification of Diseases (ICD) diagnosis code in a patient's charts. Information relevant to cognitive impairment (CI) is often found within electronic health records (EHR), but manual review of clinician notes by experts is both time consuming and often prone to errors. Automated mining of these notes presents an opportunity to label patients with cognitive impairment in EHR data. We developed natural language processing (NLP) tools to identify patients with cognitive impairment and demonstrate that linguistic context enhances performance for the cognitive impairment classification task. We fine-tuned our attention based deep learning model, which can learn from complex language structures, and substantially improved accuracy (0.93) relative to a baseline NLP model (0.84). Further, we show that deep learning NLP can successfully identify dementia patients without dementia-related ICD codes or medications.

Chaoqi Yang, Danica Xiao, M. Brandon Westover et al.

Background: Deep learning models have shown great success in automating tasks in sleep medicine by learning from carefully annotated Electroencephalogram (EEG) data. However, effectively utilizing a large amount of raw EEG remains a challenge. Objective: In this paper, we aim to learn robust vector representations from massive unlabeled EEG signals, such that the learned vectorized features (1) are expressive enough to replace the raw signals in the sleep staging task; and (2) provide better predictive performance than supervised models in scenarios of fewer labels and noisy samples. Methods: We propose a self-supervised model, named Contrast with the World Representation (ContraWR), for EEG signal representation learning, which uses global statistics from the dataset to distinguish signals associated with different sleep stages. The ContraWR model is evaluated on three real-world EEG datasets that include both at-home and in-lab EEG recording settings. Results: ContraWR outperforms 4 recent self-supervised learning methods on the sleep staging task across 3 large EEG datasets. ContraWR also beats supervised learning when fewer training labels are available (e.g., 4% accuracy improvement when less than 2% data is labeled). Moreover, the model provides informative representative feature structures in 2D projection. Conclusions: We show that ContraWR is robust to noise and can provide high-quality EEG representations for downstream prediction tasks. The proposed model can be generalized to other unsupervised physiological signal learning tasks. Future directions include exploring task-specific data augmentations and combining self-supervised with supervised methods, building upon the initial success of self-supervised learning in this paper.

Zhen Lin, Cao Xiao, Lucas Glass et al.

Despite deep learning (DL) success in classification problems, DL classifiers do not provide a sound mechanism to decide when to refrain from predicting. Recent works tried to control the overall prediction risk with classification with rejection options. However, existing works overlook the different significance of different classes. We introduce Set-classifier with Class-specific RIsk Bounds (SCRIB) to tackle this problem, assigning multiple labels to each example. Given the output of a black-box model on the validation set, SCRIB constructs a set-classifier that controls the class-specific prediction risks with a theoretical guarantee. The key idea is to reject when the set classifier returns more than one label. We validated SCRIB on several medical applications, including sleep staging on electroencephalogram (EEG) data, X-ray COVID image classification, and atrial fibrillation detection based on electrocardiogram (ECG) data. SCRIB obtained desirable class-specific risks, which are 35\%-88\% closer to the target risks than baseline methods.

Wolfgang Ganglberger, Abigail A. Bucklin, Ryan A. Tesh et al.

Objective: Sleep related respiratory abnormalities are typically detected using polysomnography. There is a need in general medicine and critical care for a more convenient method to automatically detect sleep apnea from a simple, easy-to-wear device. The objective is to automatically detect abnormal respiration and estimate the Apnea-Hypopnea-Index (AHI) with a wearable respiratory device, compared to an SpO2 signal or polysomnography using a large (n = 412) dataset serving as ground truth. Methods: Simultaneously recorded polysomnographic (PSG) and wearable respiratory effort data were used to train and evaluate models in a cross-validation fashion. Time domain and complexity features were extracted, important features were identified, and a random forest model employed to detect events and predict AHI. Four models were trained: one each using the respiratory features only, a feature from the SpO2 (%)-signal only, and two additional models that use the respiratory features and the SpO2 (%)-feature, one allowing a time lag of 30 seconds between the two signals. Results: Event-based classification resulted in areas under the receiver operating characteristic curves of 0.94, 0.86, 0.82, and areas under the precision-recall curves of 0.48, 0.32, 0.51 for the models using respiration and SpO2, respiration-only, and SpO2-only respectively. Correlation between expert-labelled and predicted AHI was 0.96, 0.78, and 0.93, respectively. Conclusions: A wearable respiratory effort signal with or without SpO2 predicted AHI accurately. Given the large dataset and rigorous testing design, we expect our models are generalizable to evaluating respiration in a variety of environments, such as at home and in critical care.

Siddharth Biswal, Cao Xiao, Lucas M. Glass et al.

Generating clinical reports from raw recordings such as X-rays and electroencephalogram (EEG) is an essential and routine task for doctors. However, it is often time-consuming to write accurate and detailed reports. Most existing methods try to generate the whole reports from the raw input with limited success because 1) generated reports often contain errors that need manual review and correction, 2) it does not save time when doctors want to write additional information into the report, and 3) the generated reports are not customized based on individual doctors' preference. We propose {\it CL}inic{\it A}l {\it R}eport {\it A}uto-completion (CLARA), an interactive method that generates reports in a sentence by sentence fashion based on doctors' anchor words and partially completed sentences. CLARA searches for most relevant sentences from existing reports as the template for the current report. The retrieved sentences are sequentially modified by combining with the input feature representations to create the final report. In our experimental evaluation, CLARA achieved 0.393 CIDEr and 0.248 BLEU-4 on X-ray reports and 0.482 CIDEr and 0.491 BLEU-4 for EEG reports for sentence-level generation, which is up to 35% improvement over the best baseline. Also via our qualitative evaluation, CLARA is shown to produce reports which have a significantly higher level of approval by doctors in a user study (3.74 out of 5 for CLARA vs 2.52 out of 5 for the baseline).

Irfan Al-Hussaini, Cao Xiao, M. Brandon Westover et al.

Sleep staging is a crucial task for diagnosing sleep disorders. It is tedious and complex as it can take a trained expert several hours to annotate just one patient's polysomnogram (PSG) from a single night. Although deep learning models have demonstrated state-of-the-art performance in automating sleep staging, interpretability which defines other desiderata, has largely remained unexplored. In this study, we propose Sleep staging via Prototypes from Expert Rules (SLEEPER), which combines deep learning models with expert defined rules using a prototype learning framework to generate simple interpretable models. In particular, SLEEPER utilizes sleep scoring rules and expert defined features to derive prototypes which are embeddings of PSG data fragments via convolutional neural networks. The final models are simple interpretable models like a shallow decision tree defined over those phenotypes. We evaluated SLEEPER using two PSG datasets collected from sleep studies and demonstrated that SLEEPER could provide accurate sleep stage classification comparable to human experts and deep neural networks with about 85% ROC-AUC and .7 kappa.

Olivier Deiss, Siddharth Biswal, Jing Jin et al.

Efficient label acquisition processes are key to obtaining robust classifiers. However, data labeling is often challenging and subject to high levels of label noise. This can arise even when classification targets are well defined, if instances to be labeled are more difficult than the prototypes used to define the class, leading to disagreements among the expert community. Here, we enable efficient training of deep neural networks. From low-confidence labels, we iteratively improve their quality by simultaneous learning of machines and experts. We call it Human And Machine co-LEarning Technique (HAMLET). Throughout the process, experts become more consistent, while the algorithm provides them with explainable feedback for confirmation. HAMLET uses a neural embedding function and a memory module filled with diverse reference embeddings from different classes. Its output includes classification labels and highly relevant reference embeddings as explanation. We took the study of brain monitoring at intensive care unit (ICU) as an application of HAMLET on continuous electroencephalography (cEEG) data. Although cEEG monitoring yields large volumes of data, labeling costs and difficulty make it hard to build a classifier. Additionally, while experts agree on the labels of clear-cut examples of cEEG patterns, labeling many real-world cEEG data can be extremely challenging. Thus, a large minority of sequences might be mislabeled. HAMLET has shown significant performance gain against deep learning and other baselines, increasing accuracy from 7.03% to 68.75% on challenging inputs. Besides improved performance, clinical experts confirmed the interpretability of those reference embeddings in helping explaining the classification results by HAMLET.