A class-contrastive human-interpretable machine learning approach to predict mortality in severe mental illness.
A class-contrastive human-interpretable machine learning approach to predict mortality in severe mental illness.
复制标题
DOI：
10.1038/s41537-021-00191-y
复制
发表时间：
2021-12-08
影响因子：
5.4
通讯作者：
Cardinal RN
中科院分区：
文献类型：
--
作者：
Banerjee S;Lio P;Jones PB;Cardinal RN
机器学习（ML）是人工智能（AI）的一个方面，涉及到自我训练的计算机算法。它们在医疗保健领域得到了广泛的应用。然而，许多训练有素的机器学习算法就像“黑盒子”一样运行，从输入数据中产生预测，而没有明确解释其工作原理。不透明的预测在许多临床领域的效用有限，在这些领域，决策必须是合理的。在这里，我们将类别对比反事实推理应用于ML，以证明输入的特定变化如何导致严重精神疾病（SMI）患者死亡率的不同预测，这是一个重大的公共卫生挑战。我们产生的预测伴随着视觉和文字的解释，如何预测会有不同的具体改变输入。我们将其应用于从精神分裂症患者的精神卫生二级保健提供者常规收集的数据。利用临床知识提供的数据结构框架，我们获取了有关身体健康、心理健康和社会易感因素的信息。然后我们训练了机器学习算法和其他统计学习技术来预测死亡风险。ML算法预测死亡率的受试者工作特征曲线下面积（AUROC）为0.80（95%置信区间[0.78,0.82]）。我们使用类别对比分析来为模型预测提供解释。我们概述了阶级对比分析可能成功地为模型预测提供解释的情景。我们的目的不是提倡一种特定的模型，而是展示类对比分析技术在具有公共卫生意义的疾病的电子医疗记录数据中的应用。在精神分裂症患者中，我们的研究表明，使用或处方抗抑郁药等药物与较低的死亡风险有关。酒精/药物滥用和谵妄诊断与较高的死亡风险相关。我们的ML模型强调了共病在确定精神分裂症患者死亡率中的作用，以及对这些患者的共病进行管理的必要性。我们希望这些生物社会因素中的一些可以通过患者水平或服务水平的干预来靶向治疗。我们的方法结合了临床知识、健康数据和统计学习，通过分类对比推理使临床医生可以解释预测。这是朝着在精神分裂症患者和潜在的其他疾病患者的管理中使用可解释的人工智能迈出的一步。
Machine learning (ML), one aspect of artificial intelligence (AI), involves computer algorithms that train themselves. They have been widely applied in the healthcare domain. However, many trained ML algorithms operate as ‘black boxes’, producing a prediction from input data without a clear explanation of their workings. Non-transparent predictions are of limited utility in many clinical domains, where decisions must be justifiable. Here, we apply class-contrastive counterfactual reasoning to ML to demonstrate how specific changes in inputs lead to different predictions of mortality in people with severe mental illness (SMI), a major public health challenge. We produce predictions accompanied by visual and textual explanations as to how the prediction would have differed given specific changes to the input. We apply it to routinely collected data from a mental health secondary care provider in patients with schizophrenia. Using a data structuring framework informed by clinical knowledge, we captured information on physical health, mental health, and social predisposing factors. We then trained an ML algorithm and other statistical learning techniques to predict the risk of death. The ML algorithm predicted mortality with an area under receiver operating characteristic curve (AUROC) of 0.80 (95% confidence intervals [0.78, 0.82]). We used class-contrastive analysis to produce explanations for the model predictions. We outline the scenarios in which class-contrastive analysis is likely to be successful in producing explanations for model predictions. Our aim is not to advocate for a particular model but show an application of the class-contrastive analysis technique to electronic healthcare record data for a disease of public health significance. In patients with schizophrenia, our work suggests that use or prescription of medications like antidepressants was associated with lower risk of death. Abuse of alcohol/drugs and a diagnosis of delirium were associated with higher risk of death. Our ML models highlight the role of co-morbidities in determining mortality in patients with schizophrenia and the need to manage co-morbidities in these patients. We hope that some of these bio-social factors can be targeted therapeutically by either patient-level or service-level interventions. Our approach combines clinical knowledge, health data, and statistical learning, to make predictions interpretable to clinicians using class-contrastive reasoning. This is a step towards interpretable AI in the management of patients with schizophrenia and potentially other diseases.
登录
查看更多内容
影响因子：
4.3
作者：
Cunningham H;Tablan V;Roberts A;Bontcheva K
通讯作者：
Bontcheva K
影响因子：
25.8
作者：
Pedersen, Carsten Bocker;Mors, Ole;Eaton, William W.
通讯作者：
Eaton, William W.
影响因子：
14.4
作者：
Miller, Tim
通讯作者：
Miller, Tim
影响因子：
1.9
作者：
BOURLARD, H;KAMP, Y
通讯作者：
KAMP, Y
影响因子：
5.8
作者：
Bates, Douglas;Maechler, Martin;Walker, Steven C.
通讯作者：
Walker, Steven C.