Trustworthy Data and AI Environments for Clinical Prediction: Application to Crisis-Risk in People With Depression

被引:8
作者
Msosa, Yamiko Joseph [1 ]
Grauslys, Arturas [2 ]
Zhou, Yifan [2 ]
Wang, Tao [1 ]
Buchan, Iain [3 ]
Langan, Paul [4 ]
Foster, Steven [5 ]
Walker, Michael [4 ]
Pearson, Michael [3 ]
Folarin, Amos [1 ]
Roberts, Angus [1 ]
Maskell, Simon [2 ]
Dobson, Richard [1 ]
Kullu, Cecil [5 ]
Kehoe, Dennis [4 ]
机构
[1] Kings Coll London, Inst Psychiat Psychol & Neurosci, Dept Biostat & Hlth Informat, London WC2R 2LS, England
[2] Univ Liverpool, Dept Elect Engn & Elect, Liverpool L69 3BX, Merseyside, England
[3] Univ Liverpool, Inst Populat Hlth, Liverpool L69 3BX, Merseyside, England
[4] AIMES, Liverpool L7 9NJ, Merseyside, England
[5] Mersey Care NHS Fdn Trust, Prescot L34 1PJ, England
关键词
Artificial intelligence; depression; digital health; mental health crisis; natural language processing; HEALTH; CARE; OUTCOMES;
D O I
10.1109/JBHI.2023.3312011
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Depression is a common mental health condition that often occurs in association with other chronic illnesses, and varies considerably in severity. Electronic Health Records (EHRs) contain rich information about a patient's medical history and can be used to train, test and maintain predictive models to support and improve patient care. This work evaluated the feasibility of implementing an environment for predicting mental health crisis among people living with depression based on both structured and unstructured EHRs. A large EHR from a mental health provider, Mersey Care, was pseudonymised and ingested into the Natural Language Processing (NLP) platform CogStack, allowing text content in binary clinical notes to be extracted. All unstructured clinical notes and summaries were semantically annotated by MedCAT and BioYODIE NLP services. Cases of crisis in patients with depression were then identified. Random forest models, gradient boosting trees, and Long Short-Term Memory (LSTM) networks, with varying feature arrangement, were trained to predict the occurrence of crisis. The results showed that all the prediction models can use a combination of structured and unstructured EHR information to predict crisis in patients with depression with good and useful accuracy. The LSTM network that was trained on a modified dataset with only 1000 most-important features from the random forest model with temporality showed the best performance with a mean AUC of 0.901 and a standard deviation of 0.006 using a training dataset and a mean AUC of 0.810 and 0.01 using a hold-out test dataset. Comparing the results from the technical evaluation with the views of psychiatrists shows that there are now opportunities to refine and integrate such prediction models into pragmatic point-of-care clinical decision support tools for supporting mental healthcare delivery.
引用
收藏
页码:5588 / 5598
页数:11
相关论文
共 55 条
[11]  
Department of Health and Social Care, 2018, Code of conduct for data-driven health and care technology
[12]   Using natural language processing to extract structured epilepsy data from unstructured clinic letters: development and validation of the ExECT (extraction of epilepsy clinical text) system [J].
Fonferko-Shadrach, Beata ;
Lacey, Arron S. ;
Roberts, Angus ;
Akbari, Ashley ;
Thompson, Simon ;
Ford, David V. ;
Lyons, Ronan A. ;
Rees, Mark I. ;
Pickrell, William Owen .
BMJ OPEN, 2019, 9 (04)
[13]   Greedy function approximation: A gradient boosting machine [J].
Friedman, JH .
ANNALS OF STATISTICS, 2001, 29 (05) :1189-1232
[14]  
Full Fact, 2019, Mental health spending in the english NHS
[15]   Machine learning model to predict mental health crises from electronic health records [J].
Garriga, Roger ;
Mas, Javier ;
Abraha, Semhar ;
Nolan, Jon ;
Harrison, Oliver ;
Tadros, George ;
Matic, Aleksandar .
NATURE MEDICINE, 2022, 28 (06) :1240-+
[16]   Taking Psychiatry Research Online [J].
Gillan, Claire M. ;
Daw, Nathaniel D. .
NEURON, 2016, 91 (01) :19-23
[17]  
Goodfellow I, 2016, ADAPT COMPUT MACH LE, P1
[18]  
Gorrell G, 2018, Arxiv, DOI arXiv:1811.04860
[19]  
Hochreiter S, 1997, NEURAL COMPUT, V9, P1735, DOI [10.1162/neco.1997.9.1.1, 10.1007/978-3-642-24797-2]
[20]   Technological innovations in mental healthcare: harnessing the digital revolution [J].
Hollis, Chris ;
Morriss, Richard ;
Martin, Jennifer ;
Amani, Sarah ;
Cotton, Rebecca ;
Denis, Mike ;
Lewis, Shon .
BRITISH JOURNAL OF PSYCHIATRY, 2015, 206 (04) :263-265