DeconDTN: Deconfounding Deep Transformer Networks for Clinical NLP

DeconDTN：为临床 NLP 解构深度 Transformer 网络

• 批准号: 10626888
• 负责人: Trevor Cohen
• 金额: $ 34.2万
• 依托单位: UNIVERSITY OF WASHINGTON
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-06-01 至 2026-02-28
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10626888
• 关键词: Address; Architecture; Area; Automobile Driving; Behavior; Bridge to Artificial Intelligence; COVID-19; Caring; Categories; Characteristics; Classification; Clinical; Clinical Services; Cognitive; Computer software; Confounding Factors (Epidemiology); Coupled; Data; Data Aggregation; Data Set; Data Sources; Dementia; Development; Diagnosis; Diagnostic; Ensure; Equilibrium; Evaluation; Genetic Transcription; Goals; High Prevalence; Individual; Institution; Investments; Label; Language; Learning; Linguistics; Location; Medical; Methods; Modeling; Modification; Natural Language Processing; Nature; Neural Network Simulation; Outcome; Output; Participant; Patients; Performance; Physicians; Prevalence; Research; SARS-CoV-2 positive; Sampling; Services; Site; Source; Speech; Systematic Bias; Testing; Text; Time; Training; Transcript; United States National Institutes of Health; United States National Library of Medicine; Update; Vision; Weight; Work; artificial intelligence method; coronavirus disease; deep learning; deep learning model; design; heterogenous data; interest; large datasets; learning strategy; loss of function; machine learning model; network models; neural; novel; open source; open source tool; portability; predictive modeling; programs; statistical and machine learning

Natural Language Processing (NLP) methods have been broadly applied to clinical problems, from recognition of clinical findings in physician notes to identification of transcribed speech samples indicating changes in cognitive status. Deep transformer networks (DTNs) have dramatically advanced NLP accuracy. These deep learning models have multiple hidden layers that may correspond to billions of trainable parameters, allowing them to apply information learned from training on large unlabeled corpora to a specific task of interest. However, their size leaves them especially vulnerable to confounding bias, induced by variables that can influence both the predictor (text) and the outcome (e.g. an associated diagnosis) of a predictive model. Such systematic biases are a recognized danger in the application of artificial intelligence methods to clinical problems, and are the focus of NLM NOT-LM-19-003 which invites applications proposing methods to identify and address them. Deep learning models in general require large amounts of training data, spurring initiatives to aggregate medical data from across institutional siloes. This can increase data set size and enhance model portability, but leaves the resulting models vulnerable to confounding by provenance, where models learn to recognize the origin of dataset components and make biased predictions based on site-specific class distributions (e.g. COVID prevalence). Such models will assign classes based on indicators of dataset provenance, rather than diagnostically meaningful linguistic differences, and make erroneous predictions when the provenance-specific distributions at the point of deployment differ from those in the training set. Confounding of this nature is a pervasive problem that presents a fundamental barrier to the portability of trained models, and threatens the utility of datasets assembled from across institutions and services. Unlike traditional statistical and machine learning models, with deep transformer networks feature representations are distributed across parameters spread throughout the entire network. New methods are needed to meet the challenge of identifying and mitigating the influence of confounding variables in such models. In the proposed research we will develop a systematic approach to Deconfounding Deep Transformer Networks (DeconDTN), embodied in an eponymous and publicly available set of open source tools for (1) identification of provenance-related biases, (2) mitigation of these biases using a novel set of validated methods, and (3) systematic evaluation of the resulting effects on model performance. While DeconDTN will be generally applicable, development and evaluation will occur in the context of three use cases involving data sets drawn from different sources: classification of speech transcripts from participants with dementia drawn from two locations, identification of goals-of-care discussions in clinical notes drawn from multiple studies involving a range of clinical services, and prediction of COVID-19 status in notes drawn from different clinical units. Our driving hypothesis is that the resulting models will make more accurate predictions in these heterogenous datasets than corresponding models without correction for confounding by provenance.

自然语言处理（NLP）方法已广泛应用于临床问题，从识别