An official website of the United States government
BackgroundThe treatment of depression in children and adolescents is a substantial public health challenge. This study examined artificial intelligence tools for the prediction of early outcomes in depressed children and adolescents treated with fluoxetine, duloxetine, or placebo. MethodsThe study samples included training datasets (N = 271) from patients with major depressive disorder (MDD) treated with fluoxetine and testing datasets from patients with MDD treated with duloxetine (N = 255) or placebo (N = 265). Treatment trajectories were generated using probabilistic graphical models (PGMs). Unsupervised machine learning identified specific depressive symptom profiles and related thresholds of improvement during acute treatment. ResultsVariation in six depressive symptoms (difficulty having fun, social withdrawal, excessive fatigue, irritability, low self‐esteem, and depressed feelings) assessed with the Children’s Depression Rating Scale‐Revised at 4–6 weeks predicted treatment outcomes with fluoxetine at 10–12 weeks with an average accuracy of 73% in the training dataset. The same six symptoms predicted 10–12 week outcomes at 4–6 weeks in (a) duloxetine testing datasets with an average accuracy of 76% and (b) placebo‐treated patients with accuracies of 67%. In placebo‐treated patients, the accuracies of predicting response and remission were similar to antidepressants. Accuracies for predicting nonresponse to placebo treatment were significantly lower than antidepressants. ConclusionsPGMs provided clinically meaningful predictions in samples of depressed children and adolescents treated with fluoxetine or duloxetine. Future work should augment PGMs with biological data for refined predictions to guide the selection of pharmacological and psychotherapeutic treatment in children and adolescents with depression.
more »
« less
Predicting remission after acute phase pharmacotherapy in patients with bipolar I depression: A machine learning approach with cross‐trial and cross‐drug replication
Abstract ObjectivesInterpatient variability in bipolar I depression (BP‐D) symptoms challenges the ability to predict pharmacotherapeutic outcomes. A machine learning workflow was developed to predict remission after 8 weeks of pharmacotherapy (total score of ≤8 on the Montgomery Åsberg Depression Rating Scale [MADRS]). MethodsSupervised machine learning models were trained on data from BP‐D patients treated with olanzapine (N = 168) and were externally validated on patients treated with olanzapine/fluoxetine combination (OFC;N = 131) and lamotrigine (LTG;N = 126). Top predictors were used to develop a prognosis rule informing how many symptoms should change and by how much within 4 weeks to increase the odds of achieving remission. ResultsAn AUC of 0.76 (NIR:0.59;p = 0.17) was established to predict remission in olanzapine‐treated subjects. These trained models achieved AUCs of 0.70 with OFC (NIR:0.52;p < 0.03) and 0.73 with LTG (NIR:0.52;p < 0.003), demonstrating external replication of prediction performance. Week‐4 changes in four MADRS symptoms (reported sadness, reduced sleep, reduced appetite, and concentration difficulties) were top predictors of remission. Across all pharmacotherapies, three or more of these symptoms needed to improve by ≥2 points at Week‐4 to have a 65% chance of achieving remission at 8 weeks (OR: 3.74, 95% CI: 2.45–5.76;p < 9.3E‐11). ConclusionMachine learning strategies achieved cross‐trial and cross‐drug replication in predicting remission after 8 weeks of pharmacotherapy for BP‐D. Interpretable prognoses rules required only a limited number of depressive symptoms, providing a promising foundation for developing simple quantitative decision aids that may, in the future, serve as companions to clinical judgment at the point of care.
more »
« less
- Award ID(s):
- 2041339
- PAR ID:
- 10576488
- Publisher / Repository:
- Wiley-Blackwell
- Date Published:
- Journal Name:
- Bipolar Disorders
- Volume:
- 27
- Issue:
- 1
- ISSN:
- 1398-5647
- Format(s):
- Medium: X Size: p. 36-46
- Size(s):
- p. 36-46
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Abstract Heterogeneity in the clinical presentation of major depressive disorder and response to antidepressants limits clinicians’ ability to accurately predict a specific patient’s eventual response to therapy. Validated depressive symptom profiles may be an important tool for identifying poor outcomes early in the course of treatment. To derive these symptom profiles, we first examined data from 947 depressed subjects treated with selective serotonin reuptake inhibitors (SSRIs) to delineate the heterogeneity of antidepressant response using probabilistic graphical models (PGMs). We then used unsupervised machine learning to identify specific depressive symptoms and thresholds of improvement that were predictive of antidepressant response by 4 weeks for a patient to achieve remission, response, or nonresponse by 8 weeks. Four depressive symptoms (depressed mood, guilt feelings and delusion, work and activities and psychic anxiety) and specific thresholds of change in each at 4 weeks predicted eventual outcome at 8 weeks to SSRI therapy with an average accuracy of 77% ( p = 5.5E-08). The same four symptoms and prognostic thresholds derived from patients treated with SSRIs correctly predicted outcomes in 72% ( p = 1.25E-05) of 1996 patients treated with other antidepressants in both inpatient and outpatient settings in independent publicly-available datasets. These predictive accuracies were higher than the accuracy of 53% for predicting SSRI response achieved using approaches that (i) incorporated only baseline clinical and sociodemographic factors, or (ii) used 4-week nonresponse status to predict likely outcomes at 8 weeks. The present findings suggest that PGMs providing interpretable predictions have the potential to enhance clinical treatment of depression and reduce the time burden associated with trials of ineffective antidepressants. Prospective trials examining this approach are forthcoming.more » « less
-
Common antiretroviral combinations are associated with somatic depressive symptoms in women with HIVObjective:While modern antiretroviral therapy (ART) is highly effective and safe, depressive symptoms have been associated with certain ART drugs. We examined the association between common ART regimens and depressive symptoms in women with HIV (WWH) with a focus on somatic vs. nonsomatic symptoms. Design:Analysis of longitudinal data from the Women's Interagency HIV Study. Methods:Participants were classified into three groups based on the frequency of positive depression screening (CES-D ≥16): chronic depression (≥50% of visits since study enrollment), infrequent depression (<50% of visits), and never depressed (no visits). Novel Bayesian machine learning methods building upon a subset-tree kernel approach were developed to estimate the combined effects of ART regimens on depressive symptoms in each group after covariate adjustment. Results:The analysis included 1538 WWH who participated in 12 924 (mean = 8.4) visits. The mean age was 49.9 years, 72% were Black, and 14% Hispanic. In the chronic depression group, combinations including tenofovir alafenamide and cobicistat-boosted elvitegravir and/or darunavir were associated with greater somatic symptoms of depression, whereas those combinations containing tenofovir disoproxil fumarate and efavirenz or rilpivirine were associated with less somatic depressive symptoms. ART was not associated with somatic symptoms in the infrequent depression or never depressed groups. ART regimens were not associated with nonsomatic symptoms in any group. Conclusions:Specific ART combinations are associated with somatic depressive symptoms in WWH with chronic depression. Future studies should consider specific depressive symptoms domains as well as complete drug combinations when assessing the relationship between ART and depression.more » « less
-
Abstract IntroductionStudies investigating the relationship between blood pressure (BP) measurements from electronic health records (EHRs) and Alzheimer's disease (AD) rely on summary statistics, like BP variability, and have only been validated at a single institution. We hypothesize that leveraging BP trajectories can accurately estimate AD risk across different populations. MethodsIn a retrospective cohort study, EHR data from Veterans Affairs (VA) patients were used to train and internally validate a machine learning model to predict AD onset within 5 years. External validation was conducted on patients from Michigan Medicine (MM). ResultsThe VA and MM cohorts included 6860 and 1201 patients, respectively. Model performance using BP trajectories was modest but comparable (area under the receiver operating characteristic curve [AUROC] = 0.64 [95% confidence interval (CI) = 0.54–0.73] for VA vs. AUROC = 0.66 [95% CI = 0.55–0.76] for MM). ConclusionApproaches that directly leverage BP trajectories from EHR data could aid in AD risk stratification across institutions.more » « less
-
BackgroundEsophageal cancer management lacks reliable response predictors to chemotherapy. In this study we evaluated the feasibility and accuracy of Biodynamic Imaging (BDI), a technology that employs digital holography as a rapid predictor of chemotherapy sensitivity in locoregional esophageal adenocarcinoma. MethodsPre-treatment endoscopic pinch biopsies were collected from patients with esophageal adenocarcinoma during standard staging procedures. BDI analyzed the tumor samples and assessedin vitrochemotherapy sensitivity. BDI sensitivity predictions were compared to patients’ pathological responses, the gold standard for determining clinical response, in the surgically treated subset (n=18). ResultBDI was feasible with timely tissue acquisition, collection, and processing in all 30 enrolled patients and successful BDI analysis in 28/29 (96%) eligible. BDI accurately predicted chemotherapy response in 13/18 (72.2%) patients using a classifier for complete, marked, and partial/no-response. BDI technology had 100% negative predictive value for complete pathological response hence identifying patients unlikely to respond to treatment. ConclusionBDI technology can potentially predict patients’ response to platinum chemotherapy. Additionally, this technology represents a promising step towards optimizing treatment strategies for esophageal adenocarcinoma patients by pre-emptively identifying non-responders to conventional platinum-based chemotherapy.more » « less
