cam.issuedOnline	2021-12-08
datacite.isderivedfrom.doi	10.1101/2021.04.05.21254684
dc.contributor.author	Banerjee, Soumya
dc.contributor.author	Lio, Pietro
dc.contributor.author	Jones, Peter
dc.contributor.author	Cardinal, Rudolf
dc.contributor.orcid	Banerjee, Soumya [0000-0001-7748-9885]
dc.contributor.orcid	Lio, Pietro [0000-0002-0540-5053]
dc.contributor.orcid	Jones, Peter [0000-0002-0387-880X]
dc.contributor.orcid	Cardinal, Rudolf [0000-0002-8751-5167]
dc.date.accessioned	2021-12-24T14:39:27Z
dc.date.available	2021-12-24T14:39:27Z
dc.date.issued	2021-12-08
dc.date.submitted	2021-04-19
dc.date.updated	2021-12-24T14:39:26Z
dc.description	Funder: MRC Mental Health Data Pathfinder grant (MC_PC_17213)
dc.description	Funder: MRC Mental Health Data Pathfinder grant (MC PC 17213)
dc.description.abstract	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 them. 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.
dc.description.sponsorship	This work was funded by an MRC Mental Health Data Pathfinder grant (MC_PC_17213).
dc.identifier.doi	10.17863/CAM.79276
dc.identifier.eissn	2334-265X
dc.identifier.issn	2334-265X
dc.identifier.other	s41537-021-00191-y
dc.identifier.other	191
dc.identifier.uri	https://www.repository.cam.ac.uk/handle/1810/331827
dc.language	en
dc.language.iso	eng
dc.publisher	Nature Research
dc.publisher.url	http://dx.doi.org/10.1038/s41537-021-00191-y
dc.subject	32 Biomedical and Clinical Sciences
dc.subject	5202 Biological Psychology
dc.subject	5203 Clinical and Health Psychology
dc.subject	3202 Clinical Sciences
dc.subject	52 Psychology
dc.subject	Clinical Research
dc.subject	Brain Disorders
dc.subject	Mental Health
dc.subject	Schizophrenia
dc.subject	Serious Mental Illness
dc.subject	Mental health
dc.subject	3 Good Health and Well Being
dc.title	A class-contrastive human-interpretable machine learning approach to predict mortality in severe mental illness
dc.type	Article
dcterms.dateAccepted	2021-11-10
prism.issueIdentifier	1
prism.publicationName	npj Schizophrenia
prism.volume	7
pubs.funder-project-id	Medical Research Council (MC_PC_17213)
rioxxterms.licenseref.uri	http://creativecommons.org/licenses/by/4.0/
rioxxterms.version	VoR
rioxxterms.versionofrecord	10.1038/s41537-021-00191-y

A class-contrastive human-interpretable machine learning approach to predict mortality in severe mental illness

Files

Original bundle

Collections