Lars Lau Raket1, Jörn Jaskolowski2, Bruce J Kinon3, Jens Christian Brasen4, Linus Jönsson5, Allan Wehnert4, Paolo Fusar-Poli6. 1. Lundbeck, Valby, Denmark; Clinical Memory Research Unit, Lund University, Lund, Sweden. Electronic address: llra@lundbeck.com. 2. IBM Danmark, Brøndby, Denmark. 3. Lundbeck US, Deerfield, IL, USA. 4. Lundbeck, Valby, Denmark. 5. Lundbeck, Valby, Denmark; Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden. 6. Department of Psychosis Studies, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK; OASIS, South London and Maudsley NHS Foundation Trust, London, UK; National Institute for Health Research Maudsley Biomedical Research Centre, South London and Maudsley NHS Foundation Trust, London, UK; South London and Maudsley NHS Foundation Trust, London, UK; Department of Brain and Behavioral Sciences, University of Pavia, Pavia, Italy.
Abstract
BACKGROUND: Many individuals who will experience a first episode of psychosis (FEP) are not detected before occurrence, limiting the effect of preventive interventions. The combination of machine-learning methods and electronic health records (EHRs) could help address this gap. METHODS: This case-control development and validation study is based on EHR data from IBM Explorys. The IBM Explorys Platform holds standardised, longitudinal, de-identified, patient-level EHR data pooled from different health-care systems with distinct EHRs. The present EHR-based studies were retrospective, matched (1:1), case-control studies compliant with RECORD, STROBE, and TRIPOD statements. The study included individuals in the IBM Explorys database who at some point between 1990 and 2018 had a diagnosis of FEP followed by schizophrenia, and psychosis-free matched control individuals from a random subsample of the full cohort. For every individual in the FEP cohort, the individual in the control cohort was matched to have a similar date for inclusion in the database and a similar total observation time. Individuals in the FEP cohort had their index date defined as the first diagnosis of psychosis or the first prescription of antipsychotic medication. Individuals in the control cohort had their index date defined to occur the same number of days after inclusion in the database as their matching FEP individual. The FEP and control cohorts were both randomly split into development and validation datasets in a ratio of 7:3. The subset of individuals in the validation dataset who had all their health-care encounters at providers that were not seen in the development dataset made up the external validation subset. A novel recurrent neural network model was developed to predict the risk of FEP 1 year before the index date by employing demographics and medical events (in the categories diagnoses, prescriptions, procedures, encounters and admissions, observations, and laboratory test results) dynamically collected in the EHR as part of clinical routine. We named the recurrent neural network Dynamic ElecTronic hEalth reCord deTection (DETECT). The main outcomes were accuracy and area under receiver operating characteristic curve (AUROC). Decision-curve analyses and dynamic patient journey plots were used to evaluate clinical usefulness. FINDINGS: The FEP and control cohorts each comprised 72 860 individuals. 102 030 individuals (51 015 matching pairs) were randomly allocated to the development dataset and the remaining 43 690 to the validation dataset. In the validation dataset, 4770 individuals had all their encounters outside of the 118 790 health-care providers that were encountered in the development dataset. The data from these individuals made up the external validation subset. The median follow-up (observation time before index date) was 6·0 years (IQR 3·0-10·4). In the development dataset, DETECT's prognostic accuracy was 0·787 and AUROC was 0·868. In the validation dataset, DETECT's prognostic accuracy was 0·774 and AUROC was 0·856. In the external test subset, DETECT's balanced prognostic accuracy was 0·724 and AUROC was 0·799. Prevalence-adjusted decision-curve analyses suggested that DETECT was associated with a positive net benefit in two different scenarios for FEP detection. INTERPRETATION: DETECT showed adequate prognostic accuracy to detect individuals at risk of developing a FEP in primary and secondary care. Replication and refinement in a population-based setting are needed to consolidate these findings. FUNDING: Lundbeck.
BACKGROUND: Many individuals who will experience a first episode of psychosis (FEP) are not detected before occurrence, limiting the effect of preventive interventions. The combination of machine-learning methods and electronic health records (EHRs) could help address this gap. METHODS: This case-control development and validation study is based on EHR data from IBM Explorys. The IBM Explorys Platform holds standardised, longitudinal, de-identified, patient-level EHR data pooled from different health-care systems with distinct EHRs. The present EHR-based studies were retrospective, matched (1:1), case-control studies compliant with RECORD, STROBE, and TRIPOD statements. The study included individuals in the IBM Explorys database who at some point between 1990 and 2018 had a diagnosis of FEP followed by schizophrenia, and psychosis-free matched control individuals from a random subsample of the full cohort. For every individual in the FEP cohort, the individual in the control cohort was matched to have a similar date for inclusion in the database and a similar total observation time. Individuals in the FEP cohort had their index date defined as the first diagnosis of psychosis or the first prescription of antipsychotic medication. Individuals in the control cohort had their index date defined to occur the same number of days after inclusion in the database as their matching FEP individual. The FEP and control cohorts were both randomly split into development and validation datasets in a ratio of 7:3. The subset of individuals in the validation dataset who had all their health-care encounters at providers that were not seen in the development dataset made up the external validation subset. A novel recurrent neural network model was developed to predict the risk of FEP 1 year before the index date by employing demographics and medical events (in the categories diagnoses, prescriptions, procedures, encounters and admissions, observations, and laboratory test results) dynamically collected in the EHR as part of clinical routine. We named the recurrent neural network Dynamic ElecTronic hEalth reCord deTection (DETECT). The main outcomes were accuracy and area under receiver operating characteristic curve (AUROC). Decision-curve analyses and dynamic patient journey plots were used to evaluate clinical usefulness. FINDINGS: The FEP and control cohorts each comprised 72 860 individuals. 102 030 individuals (51 015 matching pairs) were randomly allocated to the development dataset and the remaining 43 690 to the validation dataset. In the validation dataset, 4770 individuals had all their encounters outside of the 118 790 health-care providers that were encountered in the development dataset. The data from these individuals made up the external validation subset. The median follow-up (observation time before index date) was 6·0 years (IQR 3·0-10·4). In the development dataset, DETECT's prognostic accuracy was 0·787 and AUROC was 0·868. In the validation dataset, DETECT's prognostic accuracy was 0·774 and AUROC was 0·856. In the external test subset, DETECT's balanced prognostic accuracy was 0·724 and AUROC was 0·799. Prevalence-adjusted decision-curve analyses suggested that DETECT was associated with a positive net benefit in two different scenarios for FEP detection. INTERPRETATION: DETECT showed adequate prognostic accuracy to detect individuals at risk of developing a FEP in primary and secondary care. Replication and refinement in a population-based setting are needed to consolidate these findings. FUNDING: Lundbeck.
Authors: Dominic Oliver; Maite Arribas; Joaquim Radua; Gonzalo Salazar de Pablo; Andrea De Micheli; Giulia Spada; Martina Maria Mensi; Magdalena Kotlicka-Antczak; Renato Borgatti; Marco Solmi; Jae Il Shin; Scott W Woods; Jean Addington; Philip McGuire; Paolo Fusar-Poli Journal: Mol Psychiatry Date: 2022-06-03 Impact factor: 15.992
Authors: Rashmi Patel; Soon Nan Wee; Rajagopalan Ramaswamy; Simran Thadani; Jesisca Tandi; Ruchir Garg; Nathan Calvanese; Matthew Valko; A John Rush; Miguel E Rentería; Joydeep Sarkar; Scott H Kollins Journal: BMJ Open Date: 2022-04-22 Impact factor: 3.006
Authors: Paolo Fusar-Poli; Christoph U Correll; Celso Arango; Michael Berk; Vikram Patel; John P A Ioannidis Journal: World Psychiatry Date: 2021-06 Impact factor: 79.683
Authors: Paolo Fusar-Poli; Andrea De Micheli; Lorenzo Signorini; Helen Baldwin; Gonzalo Salazar de Pablo; Philip McGuire Journal: EClinicalMedicine Date: 2020-10-07
Authors: Dominic Oliver; Giulia Spada; Craig Colling; Matthew Broadbent; Helen Baldwin; Rashmi Patel; Robert Stewart; Daniel Stahl; Richard Dobson; Philip McGuire; Paolo Fusar-Poli Journal: Schizophr Res Date: 2020-06-19 Impact factor: 4.939