Exploring machine learning to predict depressive relapses of bipolar disorder patients

Rotenberg, Luísa de Siqueira; Borges-Júnior, Renato Gomes; Lafer, Beny; Salvini, Rogerio; Dias, Rodrigo da Silva

doi:10.1016/j.jad.2021.08.127

Cited by 13 publications

(7 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the benefits linked to using naturalistic data such as electronic health records, future research may benefit from adopting a machine learning approach to better predict who may relapse and why. Recent work has utilised machine learning approaches to pinpoint important predictors to depressive relapses in BD (Siqueira et al 2021 ) using the STEP-BD dataset. However, replicating this approach within a large UK mental health Trust would be advantageous to better determine relapse risk factors and aid decision-making in the treatment and prevention of BD, specifically within the UK.…”

Section: Discussionmentioning

confidence: 99%

Rates and associations of relapse over 5 years of 2649 people with bipolar disorder: a retrospective UK cohort study

Hett,

Morales-Muñoz,

Durdurak

et al. 2023

Int J Bipolar Disord

View full text Add to dashboard Cite

Background Evidence regarding the rate of relapse in people with bipolar disorder (BD), particularly from the UK, is lacking. This study aimed to evaluate the rate and associations of clinician-defined relapse over 5 years in a large sample of BD patients receiving routine care from a UK mental health service. Method We utilised de-identified electronic health records to sample people with BD at baseline. Relapse was defined as either hospitalisation, or a referral to acute mental health crisis services, between June 2014 and June 2019. We calculated the 5-year rate of relapse and examined the sociodemographic and clinical factors that were independently associated with relapse status and the number of relapses, over the 5-year period. Results Of 2649 patients diagnosed with BD and receiving care from secondary mental health services, 25.5% (n = 676) experienced at least one relapse over 5 years. Of the 676 people who relapsed, 60.9% experienced one relapse, with the remainder experiencing multiple relapses. 7.2% of the baseline sample had died during the 5-year follow-up. Significant factors associated with experiencing any relapse, after adjustment for relevant covariates, were history of self-harm/suicidality (OR 2.17, CI 1.15–4.10, p = 0.02), comorbidity (OR 2.59, CI 1.35–4.97, p = 0.004) and psychotic symptoms (OR 3.66, CI 1.89–7.08, p < 0.001). Factors associated with the number of relapses over 5 years, after adjustment for covariates, were self-harm/suicidality (β = 0.69, CI 0.21–1.17, p = 0.005), history of trauma (β = 0.51, CI = 0.07–0.95, p = 0.03), psychotic symptoms (β = 1.05, CI 0.55–1.56, p < 0.001), comorbidity (β = 0.52, CI 0.07–1.03, p = 0.047) and ethnicity (β = − 0.44, CI − 0.87 to − 0.003, p = 0.048). Conclusions Around 1 in 4 people with BD in a large sample of people with BD receiving secondary mental health services in the UK relapsed over a 5-year period. Interventions targeting the impacts of trauma, suicidality, presence of psychotic symptoms and comorbidity could help to prevent relapse in people with BD and should be considered in relapse prevention plans.

show abstract

Section: Discussionmentioning

confidence: 99%

Rates and associations of relapse over 5 years of 2649 people with bipolar disorder: a retrospective UK cohort study

Hett,

Morales-Muñoz,

Durdurak

et al. 2023

Int J Bipolar Disord

View full text Add to dashboard Cite

show abstract

“…ML also offers a platform to predict individual responses to BD treatment and potential future medical complications. de Siqueira et al [23] document the use of ML to predict depressive relapses among BD patients. They implement multiplayer perceptron, Naïve Bayes, RFs, and SWMs on a dataset comprising data from 507 relapse and 293 no-relapse patients.…”

Section: Clinical Applications Of ML To Bipolar Affective Disordermentioning

confidence: 99%

Clinical Application of Machine Learning Methods in Psychiatric Disorders

Mohammadi

2023

IJRASET

View full text Add to dashboard Cite

Psychiatric disorders, especially bipolar affective disorder, present a significant burden on national and global healthcare systems, warranting advanced clinical management methods. Machine learning (ML) has emerged as a reliable tool to advance diagnosis, treatment, and monitoring. This paper compiles insights from literature to confirm the applicability of ML models in the clinical setting. The findings indicate that ML can predict psychiatric disorder symptoms from speech and imaging data with up to 89% accuracy. Furthermore, individual responses to treatment and remission cases can be forecasted with accuracies exceeding 80%. ML can also predict prevailing symptoms after treatment with up to 91.26% accuracy.

show abstract

“…Despite the considerable number of publications in the field of patient admission prediction, most studies address this issue in patients with non-psychiatric illness (17)(18)(19)(20)(21), substance abuse disorders, schizophrenia or postpartum depression (22)(23)(24). Prior work by Rotenberg et al aimed to predict depressive relapses in patients with bipolar disorder using machine learning techniques, achieving F measures as high as 0.993 for a random forest model (25). Although certainly related, depressive relapses are only one potential form of relapse of BD and may indeed be less likely to require hospitalization than manic episodes.…”

Section: Introductionmentioning

confidence: 99%

Prediction of patient admission and readmission in adults from a Colombian cohort with bipolar disorder using artificial intelligence

Palacios-Ariza,

Morales-Mendoza,

Murcia

et al. 2023

Front. Psychiatry

View full text Add to dashboard Cite

IntroductionBipolar disorder (BD) is a chronically progressive mental condition, associated with a reduced quality of life and greater disability. Patient admissions are preventable events with a considerable impact on global functioning and social adjustment. While machine learning (ML) approaches have proven prediction ability in other diseases, little is known about their utility to predict patient admissions in this pathology.AimTo develop prediction models for hospital admission/readmission within 5 years of diagnosis in patients with BD using ML techniques.MethodsThe study utilized data from patients diagnosed with BD in a major healthcare organization in Colombia. Candidate predictors were selected from Electronic Health Records (EHRs) and included sociodemographic and clinical variables. ML algorithms, including Decision Trees, Random Forests, Logistic Regressions, and Support Vector Machines, were used to predict patient admission or readmission. Survival models, including a penalized Cox Model and Random Survival Forest, were used to predict time to admission and first readmission. Model performance was evaluated using accuracy, precision, recall, F1 score, area under the receiver operating characteristic curve (AUC) and concordance index.ResultsThe admission dataset included 2,726 BD patients, with 354 admissions, while the readmission dataset included 352 patients, with almost half being readmitted. The best-performing model for predicting admission was the Random Forest, with an accuracy score of 0.951 and an AUC of 0.98. The variables with the greatest predictive power in the Recursive Feature Elimination (RFE) importance analysis were the number of psychiatric emergency visits, the number of outpatient follow-up appointments and age. Survival models showed similar results, with the Random Survival Forest performing best, achieving an AUC of 0.95. However, the prediction models for patient readmission had poorer performance, with the Random Forest model being again the best performer but with an AUC below 0.70.ConclusionML models, particularly the Random Forest model, outperformed traditional statistical techniques for admission prediction. However, readmission prediction models had poorer performance. This study demonstrates the potential of ML techniques in improving prediction accuracy for BD patient admissions.

show abstract

Exploring machine learning to predict depressive relapses of bipolar disorder patients

Cited by 13 publications

References 51 publications

Rates and associations of relapse over 5 years of 2649 people with bipolar disorder: a retrospective UK cohort study

Rates and associations of relapse over 5 years of 2649 people with bipolar disorder: a retrospective UK cohort study

Clinical Application of Machine Learning Methods in Psychiatric Disorders

Prediction of patient admission and readmission in adults from a Colombian cohort with bipolar disorder using artificial intelligence

Contact Info

Product

Resources

About