Jessica Irving1, Rashmi Patel1, Dominic Oliver1, Craig Colling2, Megan Pritchard2,3, Matthew Broadbent2, Helen Baldwin1,2, Daniel Stahl4, Robert Stewart2,3, Paolo Fusar-Poli1,2,5. 1. Early Psychosis: Interventions and Clinical-Detection (EPIC) Lab, Department of Psychosis Studies, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK. 2. South London and Maudsley NHS Foundation Trust, London, UK. 3. Department of Psychological Medicine, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK. 4. Department of Biostatistics & Health Informatics, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK. 5. Department of Brain and Behavioral Sciences, University of Pavia, Pavia, Italy.
Abstract
BACKGROUND: Using novel data mining methods such as natural language processing (NLP) on electronic health records (EHRs) for screening and detecting individuals at risk for psychosis. METHOD: The study included all patients receiving a first index diagnosis of nonorganic and nonpsychotic mental disorder within the South London and Maudsley (SLaM) NHS Foundation Trust between January 1, 2008, and July 28, 2018. Least Absolute Shrinkage and Selection Operator (LASSO)-regularized Cox regression was used to refine and externally validate a refined version of a five-item individualized, transdiagnostic, clinically based risk calculator previously developed (Harrell's C = 0.79) and piloted for implementation. The refined version included 14 additional NLP-predictors: tearfulness, poor appetite, weight loss, insomnia, cannabis, cocaine, guilt, irritability, delusions, hopelessness, disturbed sleep, poor insight, agitation, and paranoia. RESULTS: A total of 92 151 patients with a first index diagnosis of nonorganic and nonpsychotic mental disorder within the SLaM Trust were included in the derivation (n = 28 297) or external validation (n = 63 854) data sets. Mean age was 33.6 years, 50.7% were women, and 67.0% were of white race/ethnicity. Mean follow-up was 1590 days. The overall 6-year risk of psychosis in secondary mental health care was 3.4 (95% CI, 3.3-3.6). External validation indicated strong performance on unseen data (Harrell's C 0.85, 95% CI 0.84-0.86), an increase of 0.06 from the original model. CONCLUSIONS: Using NLP on EHRs can considerably enhance the prognostic accuracy of psychosis risk calculators. This can help identify patients at risk of psychosis who require assessment and specialized care, facilitating earlier detection and potentially improving patient outcomes.
BACKGROUND: Using novel data mining methods such as natural language processing (NLP) on electronic health records (EHRs) for screening and detecting individuals at risk for psychosis. METHOD: The study included all patients receiving a first index diagnosis of nonorganic and nonpsychotic mental disorder within the South London and Maudsley (SLaM) NHS Foundation Trust between January 1, 2008, and July 28, 2018. Least Absolute Shrinkage and Selection Operator (LASSO)-regularized Cox regression was used to refine and externally validate a refined version of a five-item individualized, transdiagnostic, clinically based risk calculator previously developed (Harrell's C = 0.79) and piloted for implementation. The refined version included 14 additional NLP-predictors: tearfulness, poor appetite, weight loss, insomnia, cannabis, cocaine, guilt, irritability, delusions, hopelessness, disturbed sleep, poor insight, agitation, and paranoia. RESULTS: A total of 92 151 patients with a first index diagnosis of nonorganic and nonpsychotic mental disorder within the SLaM Trust were included in the derivation (n = 28 297) or external validation (n = 63 854) data sets. Mean age was 33.6 years, 50.7% were women, and 67.0% were of white race/ethnicity. Mean follow-up was 1590 days. The overall 6-year risk of psychosis in secondary mental health care was 3.4 (95% CI, 3.3-3.6). External validation indicated strong performance on unseen data (Harrell's C 0.85, 95% CI 0.84-0.86), an increase of 0.06 from the original model. CONCLUSIONS: Using NLP on EHRs can considerably enhance the prognostic accuracy of psychosis risk calculators. This can help identify patients at risk of psychosis who require assessment and specialized care, facilitating earlier detection and potentially improving patient outcomes.
Authors: P Fusar-Poli; M Tantardini; S De Simone; V Ramella-Cravaro; D Oliver; J Kingdon; M Kotlicka-Antczak; L Valmaggia; J Lee; M J Millan; S Galderisi; U Balottin; V Ricca; P McGuire Journal: Eur Psychiatry Date: 2016-12-16 Impact factor: 5.361
Authors: Cheryl M Corcoran; Facundo Carrillo; Diego Fernández-Slezak; Gillinder Bedi; Casimir Klim; Daniel C Javitt; Carrie E Bearden; Guillermo A Cecchi Journal: World Psychiatry Date: 2018-02 Impact factor: 49.548
Authors: Anders Gustavsson; Mikael Svensson; Frank Jacobi; Christer Allgulander; Jordi Alonso; Ettore Beghi; Richard Dodel; Mattias Ekman; Carlo Faravelli; Laura Fratiglioni; Brenda Gannon; David Hilton Jones; Poul Jennum; Albena Jordanova; Linus Jönsson; Korinna Karampampa; Martin Knapp; Gisela Kobelt; Tobias Kurth; Roselind Lieb; Mattias Linde; Christina Ljungcrantz; Andreas Maercker; Beatrice Melin; Massimo Moscarelli; Amir Musayev; Fiona Norwood; Martin Preisig; Maura Pugliatti; Juergen Rehm; Luis Salvador-Carulla; Brigitte Schlehofer; Roland Simon; Hans-Christoph Steinhausen; Lars Jacob Stovner; Jean-Michel Vallat; Peter Van den Bergh; Peter Van den Bergh; Jim van Os; Pieter Vos; Weili Xu; Hans-Ulrich Wittchen; Bengt Jönsson; Jes Olesen Journal: Eur Neuropsychopharmacol Date: 2011-09-15 Impact factor: 4.600
Authors: Paolo Fusar-Poli; Nomi Werbeloff; Grazia Rutigliano; Dominic Oliver; Cathy Davies; Daniel Stahl; Philip McGuire; David Osborn Journal: Schizophr Bull Date: 2019-04-25 Impact factor: 9.306
Authors: Paolo Fusar-Poli; Dominic Stringer; Alice M S Durieux; Grazia Rutigliano; Ilaria Bonoldi; Andrea De Micheli; Daniel Stahl Journal: Transl Psychiatry Date: 2019-10-17 Impact factor: 6.222
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: Alex S Cohen; Zachary Rodriguez; Kiara K Warren; Tovah Cowan; Michael D Masucci; Ole Edvard Granrud; Terje B Holmlund; Chelsea Chandler; Peter W Foltz; Gregory P Strauss Journal: Schizophr Bull Date: 2022-09-01 Impact factor: 7.348
Authors: Leigha A MacNeill; Norrina B Allen; Roshaye B Poleon; Teresa Vargas; K Juston Osborne; Katherine S F Damme; Deanna M Barch; Sheila Krogh-Jespersen; Ashley N Nielsen; Elizabeth S Norton; Christopher D Smyser; Cynthia E Rogers; Joan L Luby; Vijay A Mittal; Lauren S Wakschlag Journal: Dev Psychopathol Date: 2021-12-07
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: Dominic Oliver; Chiew Meng Johnny Wong; Martin Bøg; Linus Jönsson; Bruce J Kinon; Allan Wehnert; Kristian Tore Jørgensen; Jessica Irving; Daniel Stahl; Philip McGuire; Lars Lau Raket; Paolo Fusar-Poli Journal: Transl Psychiatry Date: 2020-10-29 Impact factor: 6.222