RESUMEN
Detecting patients with a high-risk profile for treatment-resistant schizophrenia (TRS) can be beneficial for implementing individually adapted therapeutic strategies and better understanding the TRS etiology. The aim of this study was to explore, with machine learning methods, the impact of demographic and clinical patient characteristics on TRS prediction, for already established risk factors and unexplored ones. This was a retrospective study of 500 patients admitted during 2020 to the University Hospital Group for Paris Psychiatry. We hypothesized potential TRS risk factors. The selected features were coded into structured variables in a new dataset, by processing patients discharge summaries and medical narratives with natural-language processing methods. We compared three machine learning models (XGBoost, logistic elastic net regression, logistic regression without regularization) for predicting TRS outcome. We analysed feature impact on the models, suggesting the following factors as markers of a high-risk TRS profile: early age at first contact with psychiatry, antipsychotic treatment interruptions due to non-adherence, absence of positive symptoms at baseline, educational problems and adolescence mental disorders in the personal psychiatric history. Specifically, we found a significant association with TRS outcome for age at first contact with psychiatry and medication non-adherence. Our findings on TRS risk factors are consistent with the review of the literature and suggest potential in using early pathophysiologic features for TRS prediction. Results were encouraging with the use of natural-langage processing techniques to leverage raw data provided by discharge summaries, combined with machine leaning models. These findings are a promising step for helping clinicians adapt their guidelines to early detection of TRS.
Asunto(s)
Aprendizaje Automático , Esquizofrenia Resistente al Tratamiento , Humanos , Masculino , Femenino , Adulto , Estudios Retrospectivos , Esquizofrenia Resistente al Tratamiento/tratamiento farmacológico , Esquizofrenia Resistente al Tratamiento/fisiopatología , Antipsicóticos/farmacología , Factores de Riesgo , Adulto Joven , Persona de Mediana Edad , Cumplimiento de la Medicación , Adolescente , Pronóstico , Esquizofrenia/tratamiento farmacológico , Esquizofrenia/fisiopatologíaRESUMEN
Despite an increasing number of adults older than 60 years with psychiatric disorders, there are few studies on older patients in psychiatric emergencies and no European data. We aimed to describe the population of patients aged 60 years and older who presented to the main French psychiatric emergency centre and identify predictors of psychiatric hospitalization. This monocentric study included 300 consecutive patients aged 60 years and older. Patients presenting because of psychiatric emergencies were frequently female and lived autonomously. More than 40% had a history of at least one psychiatric hospitalization and 44% had consulted a psychiatrist in the previous 6 months. The most common reasons for consultation were depression, anxiety, sleep disorders and suicidal thoughts. Psychiatric disorders were mainly mood disorders; neurotic, stress-related and somatoform disorders; and schizophrenic, schizotypal and delusional disorders. Only 10% had a diagnosis of organic mental disorders. Overall, 39% of the patients were admitted to the psychiatric hospital. Factors predicting hospitalization were a history of psychiatric hospitalization, suicidal thoughts and a diagnosis of a mood disorder or schizophrenia/schizotypal/delusional disorder. In conclusion, among people aged 60 years and older who consulted for psychiatric emergencies, 39% had to be hospitalized in psychiatry and only psychiatric factors influenced the decision to hospitalize. Our study highlights the need for further studies of older people in psychiatric emergencies in Europe, to anticipate the needs of this specific population and adapt multidisciplinary mental health care.
Asunto(s)
Trastornos de Ansiedad/epidemiología , COVID-19 , Servicios de Urgencia Psiquiátrica/tendencias , Tratamiento Psiquiátrico Involuntario/tendencias , Trastornos Psicóticos/epidemiología , Derivación y Consulta/tendencias , Intento de Suicidio/tendencias , Adolescente , Adulto , Anciano , Femenino , Francia/epidemiología , Hospitalización/tendencias , Humanos , Masculino , Persona de Mediana Edad , Trastornos del Humor/epidemiología , Paris/epidemiología , Psiquiatría , Población Suburbana , Población Urbana , Adulto JovenRESUMEN
To date, we have no French data about the psychiatric consequences of the Covid-19 pandemic and the confinement. In the largest French psychiatric emergency centre, we compared the average number of consultations per day during the confinement with the same period preceding the confinement and with the same periods of previous years, and we observed a significant drop in attendance. Our team had to adapt promptly to these changes in public mental health services, and we set up a telephone hotline dedicated to psychiatric patients and their families, in order to prevent a secondary psychiatric crisis.