Using Machine Learning Imputed Outcomes to Assess Drug-Dependent Risk of Self-Harm in Patients with Bipolar Disorder: A Comparative Effectiveness Study

Nestsiarovich, Anastasiya; Kumar, Praveen; Lauve, Nicolas; Hurwitz, Nathaniel G; Mazurie, Aurélien; Cannon, Daniel C.; Zhu, Yiliang; Nelson, Stuart J.; Crisanti, Annette S.; Kerner, Berit; Tohen, Mauricio; Perkins, Douglas J; Lambert, Christophe G

doi:10.2196/24522

Cited by 4 publications

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, we only highlighted a few more recent studies incorporating machine learning approaches. Nestsiarovich et al [ 174 ] proposed to use supervised machine learning (classification) to impute self-harm cases that were significantly under-reported in EHRs. They demonstrated that using the combined coded and imputed cohort, the power of their analysis could be enhanced.…”

Section: Current Challenges Trends and Future Directionsmentioning

confidence: 99%

Machine Learning in Causal Inference: Application in Pharmacovigilance

Zhao

Wang

et al. 2022

Drug Saf

View full text Add to dashboard Cite

Monitoring adverse drug events or pharmacovigilance has been promoted by the World Health Organization to assure the safety of medicines through a timely and reliable information exchange regarding drug safety issues. We aim to discuss the application of machine learning methods as well as causal inference paradigms in pharmacovigilance. We first reviewed data sources for pharmacovigilance. Then, we examined traditional causal inference paradigms, their applications in pharmacovigilance, and how machine learning methods and causal inference paradigms were integrated to enhance the performance of traditional causal inference paradigms. Finally, we summarized issues with currently mainstream correlation-based machine learning models and how the machine learning community has tried to address these issues by incorporating causal inference paradigms. Our literature search revealed that most existing data sources and tasks for pharmacovigilance were not designed for causal inference. Additionally, pharmacovigilance was lagging in adopting machine learning-causal inference integrated models. We highlight several currently trending directions or gaps to integrate causal inference with machine learning in pharmacovigilance research. Finally, our literature search revealed that the adoption of causal paradigms can mitigate known issues with machine learning models. We foresee that the pharmacovigilance domain can benefit from the progress in the machine learning field.

show abstract

Section: Current Challenges Trends and Future Directionsmentioning

confidence: 99%

Machine Learning in Causal Inference: Application in Pharmacovigilance

Zhao

Wang

et al. 2022

Drug Saf

View full text Add to dashboard Cite

show abstract

“…The treatment of BD is complex because different medications are needed for each phase of the disorder and may differ in the acute and in the maintenance phase [11]. The treatment of bipolar depression is a big challenge because there are few drugs with proven efficacy and the use of antidepressants is controversial [12][13][14], due to the risk for manic switch [15] and the higher risk of suicidal ideation [16,17]. Nevertheless, antidepressants, either in monotherapy or in combination with other psychotropic medications, constitute the treatment of first choice for MDD and for bipolar depression, although on average only about 40 to 60% of treated patients show a significant improvement of symptoms [18,19], with about one third of patients resistant to antidepressants [20].…”

Section: Introductionmentioning

confidence: 99%

Investigating the Role of Leukocyte Telomere Length in Treatment-Resistant Depression and in Response to Electroconvulsive Therapy

Pisanu

Vitali

Meloni

et al. 2021

JPM

View full text Add to dashboard Cite

Psychiatric disorders seem to be characterized by premature cell senescence. However, controversial results have also been reported. In addition, the relationship between accelerated aging and treatment-resistance has scarcely been investigated. In the current study, we measured leukocyte telomere length (LTL) in 148 patients with treatment-resistant depression (TRD, 125 with major depressive disorder, MDD, and 23 with bipolar disorder, BD) treated with electroconvulsive therapy (ECT) and analyzed whether LTL was associated with different response profiles. We also compared LTL between patients with TRD and 335 non-psychiatric controls. For 107 patients for which genome-wide association data were available, we evaluated whether a significant overlap among genetic variants or genes associated with LTL and with response to ECT could be observed. LTL was negatively correlated with age (Spearman’s correlation coefficient = −0.25, p < 0.0001) and significantly shorter in patients with treatment-resistant MDD (Quade’s F = 35.18, p < 0.0001) or BD (Quade’s F = 20.84, p < 0.0001) compared to controls. Conversely, baseline LTL was not associated with response to ECT or remission. We did not detect any significant overlap between genetic variants or genes associated with LTL and response to ECT. Our results support previous findings suggesting premature cell senescence in patients with severe psychiatric disorders and suggest that LTL could not be a predictive biomarker of response to ECT.

show abstract

Machine learning and the prediction of suicide in psychiatric populations: a systematic review

Pigoni,

Delvecchio,

Turtulici

et al. 2024

Transl Psychiatry

View full text Add to dashboard Cite

Machine learning (ML) has emerged as a promising tool to enhance suicidal prediction. However, as many large-sample studies mixed psychiatric and non-psychiatric populations, a formal psychiatric diagnosis emerged as a strong predictor of suicidal risk, overshadowing more subtle risk factors specific to distinct populations. To overcome this limitation, we conducted a systematic review of ML studies evaluating suicidal behaviors exclusively in psychiatric clinical populations. A systematic literature search was performed from inception through November 17, 2022 on PubMed, EMBASE, and Scopus following the PRISMA guidelines. Original research using ML techniques to assess the risk of suicide or predict suicide attempts in the psychiatric population were included. An assessment for bias risk was performed using the transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) guidelines. About 1032 studies were retrieved, and 81 satisfied the inclusion criteria and were included for qualitative synthesis. Clinical and demographic features were the most frequently employed and random forest, support vector machine, and convolutional neural network performed better in terms of accuracy than other algorithms when directly compared. Despite heterogeneity in procedures, most studies reported an accuracy of 70% or greater based on features such as previous attempts, severity of the disorder, and pharmacological treatments. Although the evidence reported is promising, ML algorithms for suicidal prediction still present limitations, including the lack of neurobiological and imaging data and the lack of external validation samples. Overcoming these issues may lead to the development of models to adopt in clinical practice. Further research is warranted to boost a field that holds the potential to critically impact suicide mortality.

show abstract

Using Machine Learning Imputed Outcomes to Assess Drug-Dependent Risk of Self-Harm in Patients with Bipolar Disorder: A Comparative Effectiveness Study

Cited by 4 publications

References 39 publications

Machine Learning in Causal Inference: Application in Pharmacovigilance

Machine Learning in Causal Inference: Application in Pharmacovigilance

Investigating the Role of Leukocyte Telomere Length in Treatment-Resistant Depression and in Response to Electroconvulsive Therapy

Machine learning and the prediction of suicide in psychiatric populations: a systematic review

Contact Info

Product

Resources

About