Cancer treatments are known to introduce cardiotoxicity, negatively impacting outcomes and survivorship. Identifying cancer patients at risk of heart failure (HF) is critical to improving cancer treatment outcomes and safety. This study examined machine learning (ML) models to identify cancer patients at risk of HF using electronic health records (EHRs), including traditional ML, Time-Aware long short-term memory (T-LSTM), and large language models (LLMs) using novel narrative features derived from the structured medical codes. We identified a cancer cohort of 12,806 patients from the University of Florida Health, diagnosed with lung, breast, and colorectal cancers, among which 1,602 individuals developed HF after cancer. The LLM, GatorTron-3.9B, achieved the best F1 scores, outperforming the traditional support vector machines by 39%, the T-LSTM deep learning model by 7%, and a widely used transformer model, BERT, by 5.6%. The analysis shows that the proposed narrative features remarkably increased feature density and improved performance.
相關內容
In early phase drug development of combination therapy, the primary objective is to preliminarily assess whether there is additive activity when a novel agent combined with an established monotherapy. Due to potential feasibility issues with a large randomized study, uncontrolled single-arm trials have been the mainstream approach in cancer clinical trials. However, such trials often present significant challenges in deciding whether to proceed to the next phase of development. A hybrid design, leveraging data from a completed historical clinical study of the monotherapy, offers a valuable option to enhance study efficiency and improve informed decision-making. Compared to traditional single-arm designs, the hybrid design may significantly enhance power by borrowing external information, enabling a more robust assessment of activity. The primary challenge of hybrid design lies in handling information borrowing. We introduce a Bayesian dynamic power prior (DPP) framework with three components of controlling amount of dynamic borrowing. The framework offers flexible study design options with explicit interpretation of borrowing, allowing customization according to specific needs. Furthermore, the posterior distribution in the proposed framework has a closed form, offering significant advantages in computational efficiency. The proposed framework's utility is demonstrated through simulations and a case study.
Early and timely prediction of patient care demand not only affects effective resource allocation but also influences clinical decision-making as well as patient experience. Accurately predicting patient care demand, however, is a ubiquitous challenge for hospitals across the world due, in part, to the demand's time-varying temporal variability, and, in part, to the difficulty in modelling trends in advance. To address this issue, here, we develop two methods, a relatively simple time-vary linear model, and a more advanced neural network model. The former forecasts patient arrivals hourly over a week based on factors such as day of the week and previous 7-day arrival patterns. The latter leverages a long short-term memory (LSTM) model, capturing non-linear relationships between past data and a three-day forecasting window. We evaluate the predictive capabilities of the two proposed approaches compared to two na\"ive approaches - a reduced-rank vector autoregressive (VAR) model and the TBATS model. Using patient care demand data from Rambam Medical Center in Israel, our results show that both proposed models effectively capture hourly variations of patient demand. Additionally, the linear model is more explainable thanks to its simple architecture, whereas, by accurately modelling weekly seasonal trends, the LSTM model delivers lower prediction errors. Taken together, our explorations suggest the utility of machine learning in predicting time-varying patient care demand; additionally, it is possible to predict patient care demand with good accuracy (around 4 patients) three days or a week in advance using machine learning.
Histopathological staining of human tissue is essential in the diagnosis of various diseases. The recent advances in virtual tissue staining technologies using AI alleviate some of the costly and tedious steps involved in the traditional histochemical staining process, permitting multiplexed rapid staining of label-free tissue without using staining reagents, while also preserving tissue. However, potential hallucinations and artifacts in these virtually stained tissue images pose concerns, especially for the clinical utility of these approaches. Quality assessment of histology images is generally performed by human experts, which can be subjective and depends on the training level of the expert. Here, we present an autonomous quality and hallucination assessment method (termed AQuA), mainly designed for virtual tissue staining, while also being applicable to histochemical staining. AQuA achieves 99.8% accuracy when detecting acceptable and unacceptable virtually stained tissue images without access to ground truth, also presenting an agreement of 98.5% with the manual assessments made by board-certified pathologists. Besides, AQuA achieves super-human performance in identifying realistic-looking, virtually stained hallucinatory images that would normally mislead human diagnosticians by deceiving them into diagnosing patients that never existed. We further demonstrate the wide adaptability of AQuA across various virtually and histochemically stained tissue images and showcase its strong external generalization to detect unseen hallucination patterns of virtual staining network models as well as artifacts observed in the traditional histochemical staining workflow. This framework creates new opportunities to enhance the reliability of virtual staining and will provide quality assurance for various image generation and transformation tasks in digital pathology and computational imaging.
Mental health conditions, prevalent across various demographics, necessitate efficient monitoring to mitigate their adverse impacts on life quality. The surge in data-driven methodologies for mental health monitoring has underscored the importance of privacy-preserving techniques in handling sensitive health data. Despite strides in federated learning for mental health monitoring, existing approaches struggle with vulnerabilities to certain cyber-attacks and data insufficiency in real-world applications. In this paper, we introduce a differential private federated transfer learning framework for mental health monitoring to enhance data privacy and enrich data sufficiency. To accomplish this, we integrate federated learning with two pivotal elements: (1) differential privacy, achieved by introducing noise into the updates, and (2) transfer learning, employing a pre-trained universal model to adeptly address issues of data imbalance and insufficiency. We evaluate the framework by a case study on stress detection, employing a dataset of physiological and contextual data from a longitudinal study. Our finding show that the proposed approach can attain a 10% boost in accuracy and a 21% enhancement in recall, while ensuring privacy protection.
Regionalization of intensive care for premature babies refers to a triage system of mothers with high-risk pregnancies to hospitals of varied capabilities based on risks faced by infants. Due to the limited capacity of high-level hospitals, which are equipped with advanced expertise to provide critical care, understanding the effect of delivering premature babies at such hospitals on infant mortality for different subgroups of high-risk mothers could facilitate the design of an efficient perinatal regionalization system. Towards answering this question, Baiocchi et al. (2010) proposed to strengthen an excess-travel-time-based, continuous instrumental variable (IV) in an IV-based, matched-pair design by switching focus to a smaller cohort amenable to being paired with a larger separation in the IV dose. Three elements changed with the strengthened IV: the study cohort, compliance rate and latent complier subgroup. Here, we introduce a non-bipartite, template matching algorithm that embeds data into a target, pair-randomized encouragement trial which maintains fidelity to the original study cohort while strengthening the IV. We then study randomization-based and IV-dependent, biased-randomization-based inference of partial identification bounds for the sample average treatment effect (SATE) in an IV-based matched pair design, which deviates from the usual effect ratio estimand in that the SATE is agnostic to the IV and who is matched to whom, although a strengthened IV design could narrow the partial identification bounds. Based on our proposed strengthened-IV design, we found that delivering at a high-level NICU reduced preterm babies' mortality rate compared to a low-level NICU for $81,766 \times 2 = 163,532$ mothers and their preterm babies and the effect appeared to be minimal among non-black, low-risk mothers.
Clinical trials are critical in advancing medical treatments but often suffer from immense time and financial burden. Advances in statistical methodologies and artificial intelligence (AI) present opportunities to address these inefficiencies. Here we introduce Prognostic Covariate-Adjusted Mixed Models for Repeated Measures (PROCOVA-MMRM) as an advantageous combination of prognostic covariate adjustment (PROCOVA) and Mixed Models for Repeated Measures (MMRM). PROCOVA-MMRM utilizes time-matched prognostic scores generated from AI models to enhance the precision of treatment effect estimators for longitudinal continuous outcomes, enabling reductions in sample size and enrollment times. We first provide a description of the background and implementation of PROCOVA-MMRM, followed by two case study reanalyses where we compare the performance of PROCOVA-MMRM versus the unadjusted MMRM. These reanalyses demonstrate significant improvements in statistical power and precision in clinical indications with unmet medical need, specifically Alzheimer's Disease (AD) and Amyotrophic Lateral Sclerosis (ALS). We also explore the potential for sample size reduction with the prospective implementation of PROCOVA-MMRM, finding that the same or better results could have been achieved with fewer participants in these historical trials if the enhanced precision provided by PROCOVA-MMRM had been prospectively leveraged. We also confirm the robustness of the statistical properties of PROCOVA-MMRM in a variety of realistic simulation scenarios. Altogether, PROCOVA-MMRM represents a rigorous method of incorporating advances in the prediction of time-matched prognostic scores generated by AI into longitudinal analysis, potentially reducing both the cost and time required to bring new treatments to patients while adhering to regulatory standards.
Spiking neural networks (SNNs) have garnered interest due to their energy efficiency and superior effectiveness on neuromorphic chips compared with traditional artificial neural networks (ANNs). One of the mainstream approaches to implementing deep SNNs is the ANN-SNN conversion, which integrates the efficient training strategy of ANNs with the energy-saving potential and fast inference capability of SNNs. However, under extreme low-latency conditions, the existing conversion theory suggests that the problem of misrepresentation of residual membrane potentials in SNNs, i.e., the inability of IF neurons with a reset-by-subtraction mechanism to respond to residual membrane potentials beyond the range from resting potential to threshold, leads to a performance gap in the converted SNNs compared to the original ANNs. This severely limits the possibility of practical application of SNNs on delay-sensitive edge devices. Existing conversion methods addressing this problem usually involve modifying the state of the conversion spiking neurons. However, these methods do not consider their adaptability and compatibility with neuromorphic chips. We propose a new approach based on explicit modeling of residual errors as additive noise. The noise is incorporated into the activation function of the source ANN, which effectively reduces the residual error. Our experiments on the CIFAR10/100 dataset verify that our approach exceeds the prevailing ANN-SNN conversion methods and directly trained SNNs concerning accuracy and the required time steps. Overall, our method provides new ideas for improving SNN performance under ultra-low-latency conditions and is expected to promote practical neuromorphic hardware applications for further development.
Understanding causality helps to structure interventions to achieve specific goals and enables predictions under interventions. With the growing importance of learning causal relationships, causal discovery tasks have transitioned from using traditional methods to infer potential causal structures from observational data to the field of pattern recognition involved in deep learning. The rapid accumulation of massive data promotes the emergence of causal search methods with brilliant scalability. Existing summaries of causal discovery methods mainly focus on traditional methods based on constraints, scores and FCMs, there is a lack of perfect sorting and elaboration for deep learning-based methods, also lacking some considers and exploration of causal discovery methods from the perspective of variable paradigms. Therefore, we divide the possible causal discovery tasks into three types according to the variable paradigm and give the definitions of the three tasks respectively, define and instantiate the relevant datasets for each task and the final causal model constructed at the same time, then reviews the main existing causal discovery methods for different tasks. Finally, we propose some roadmaps from different perspectives for the current research gaps in the field of causal discovery and point out future research directions.
Due to their increasing spread, confidence in neural network predictions became more and more important. However, basic neural networks do not deliver certainty estimates or suffer from over or under confidence. Many researchers have been working on understanding and quantifying uncertainty in a neural network's prediction. As a result, different types and sources of uncertainty have been identified and a variety of approaches to measure and quantify uncertainty in neural networks have been proposed. This work gives a comprehensive overview of uncertainty estimation in neural networks, reviews recent advances in the field, highlights current challenges, and identifies potential research opportunities. It is intended to give anyone interested in uncertainty estimation in neural networks a broad overview and introduction, without presupposing prior knowledge in this field. A comprehensive introduction to the most crucial sources of uncertainty is given and their separation into reducible model uncertainty and not reducible data uncertainty is presented. The modeling of these uncertainties based on deterministic neural networks, Bayesian neural networks, ensemble of neural networks, and test-time data augmentation approaches is introduced and different branches of these fields as well as the latest developments are discussed. For a practical application, we discuss different measures of uncertainty, approaches for the calibration of neural networks and give an overview of existing baselines and implementations. Different examples from the wide spectrum of challenges in different fields give an idea of the needs and challenges regarding uncertainties in practical applications. Additionally, the practical limitations of current methods for mission- and safety-critical real world applications are discussed and an outlook on the next steps towards a broader usage of such methods is given.
Clinical Named Entity Recognition (CNER) aims to identify and classify clinical terms such as diseases, symptoms, treatments, exams, and body parts in electronic health records, which is a fundamental and crucial task for clinical and translational research. In recent years, deep neural networks have achieved significant success in named entity recognition and many other Natural Language Processing (NLP) tasks. Most of these algorithms are trained end to end, and can automatically learn features from large scale labeled datasets. However, these data-driven methods typically lack the capability of processing rare or unseen entities. Previous statistical methods and feature engineering practice have demonstrated that human knowledge can provide valuable information for handling rare and unseen cases. In this paper, we address the problem by incorporating dictionaries into deep neural networks for the Chinese CNER task. Two different architectures that extend the Bi-directional Long Short-Term Memory (Bi-LSTM) neural network and five different feature representation schemes are proposed to handle the task. Computational results on the CCKS-2017 Task 2 benchmark dataset show that the proposed method achieves the highly competitive performance compared with the state-of-the-art deep learning methods.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191