Case-control Indian buffet process identifies biomarkers of response to Codrituzumab.

BACKGROUND: Codrituzumab, a humanized monoclonal antibody against Glypican-3 (GPC3), which is expressed in hepatocellular carcinoma (HCC), was tested in a randomized phase II trial in advanced HCC patients who had failed prior systemic therapy. Biomarker analysis was performed to identify a responder population that benefits from treatment. METHODS: A novel statistical method based on the Indian buffet process (IBP) was used to identify biomarkers predictive of response to treatment with Codrituzumab. The IBP is a novel method that allows flexibility in analysis design, and which is sensitive to slight, but meaningful between-group differences in biomarkers in very complex datasets RESULTS: The IBP model identified several subpopulations of patients having defined biomarker values. Tumor necrosis and viable cell content in the tumor were identified as prognostic markers of disease progression, as were the well-known HCC prognostic markers of disease progression, alpha-fetoprotein and Glypican-3 expression. Predictive markers of treatment response included natural killer (NK) cell surface markers and parameters influencing NK cell activity, all related to the mechanism of action of this drug CONCLUSIONS: The Indian buffet process can be effectively used to detect statistically significant signals with high sensitivity in complex and noisy biological data TRIAL REGISTRATION: NCT01507168 , January 6, 2012.

Do clinicians follow heuristics in prescribing antidepressants?

BACKGROUND: While clinicians commonly learn heuristics to guide antidepressant treatment selection, surveys suggest real-world prescribing practices vary widely. We aimed to determine the extent to which antidepressant prescriptions were consistent with commonly-advocated heuristics for treatment selection. METHODS: This retrospective longitudinal cohort study examined electronic health records from psychiatry and non-psychiatry practice networks affiliated with two large academic medical centers between March 2008 and December 2017. Patients included 45,955 individuals with a major depressive disorder or depressive disorder not otherwise specified diagnosis who were prescribed at least one of 11 common antidepressant medications. Specific clinical features that may impact prescribing choices were extracted from coded data, and analyzed for association with index prescription in logistic regression models adjusted for sociodemographic variables and provider type. RESULTS: Multiple clinical features yielded 10% or greater change in odds of prescribing, including overweight and underweight status and sexual dysfunction. These heuristics were generally applied similarly across hospital systems and psychiatrist and non-psychiatrist providers. LIMITATIONS: These analyses rely on coded clinical data, which is likely to substantially underestimate prevalence of particular clinical features. Additionally, numerous other features that may impact prescribing choices are not able to be modeled. CONCLUSION: Our results confirm the hypothesis that clinicians apply heuristics on the basis of clinical features to guide antidepressant prescribing, although the magnitude of these effects is modest, suggesting other patient- or clinician-level factors have larger effects. FUNDING: This work was funded by NSF GRFP (grant no. DGE1745303), Harvard SEAS, the Center for Research on Computation and Society at Harvard, the Harvard Data Science Initiative, and a grant from the National Institute of Mental Health (grant no. 1R01MH106577).

Preferential Mixture-of-Experts: Interpretable Models that Rely on Human Expertise As Much As Possible.

We propose Preferential MoE, a novel human-ML mixture-of-experts model that augments human expertise in decision making with a data-based classifier only when necessary for predictive performance. Our model exhibits an interpretable gating function that provides information on when human rules should be followed or avoided. The gating function is maximized for using human-based rules, and classification errors are minimized. We propose solving a coupled multi-objective problem with convex subproblems. We develop approximate algorithms and study their performance and convergence. Finally, we demonstrate the utility of Preferential MoE on two clinical applications for the treatment of Human Immunodeficiency Virus (HIV) and management of Major Depressive Disorder (MDD).

Predicting change in diagnosis from major depression to bipolar disorder after antidepressant initiation.

We aimed to develop and validate classification models able to identify individuals at high risk for transition from a diagnosis of depressive disorder to one of bipolar disorder. This retrospective health records cohort study applied outpatient clinical data from psychiatry and nonpsychiatry practice networks affiliated with two large academic medical centers between March 2008 and December 2017. Participants included 67,807 individuals with a diagnosis of major depressive disorder or depressive disorder not otherwise specified and no prior diagnosis of bipolar disorder, who received at least one of the nine antidepressant medications. The main outcome was at least one diagnostic code reflective of a bipolar disorder diagnosis within 3 months of index antidepressant prescription. Logistic regression and random forests using diagnostic and procedure codes as well as sociodemographic features were used to predict this outcome, with discrimination and calibration assessed in a held-out test set and then a second academic medical center. Among 67,807 individuals who received at least one antidepressant medication, 925 (1.36%) subsequently received a diagnosis of bipolar disorder within 3 months. Models incorporating coded diagnoses and procedures yielded a mean area under the receiver operating characteristic curve of 0.76 (ranging from 0.73 to 0.80). Standard supervised machine learning methods enabled development of discriminative and transferable models to predict transition to bipolar disorder. With further validation, these scores may enable physicians to more precisely calibrate follow-up intensity for high-risk patients after antidepressant initiation.

How machine-learning recommendations influence clinician treatment selections: the example of the antidepressant selection.

Decision support systems embodying machine learning models offer the promise of an improved standard of care for major depressive disorder, but little is known about how clinicians' treatment decisions will be influenced by machine learning recommendations and explanations. We used a within-subject factorial experiment to present 220 clinicians with patient vignettes, each with or without a machine-learning (ML) recommendation and one of the multiple forms of explanation. We found that interacting with ML recommendations did not significantly improve clinicians' treatment selection accuracy, assessed as concordance with expert psychopharmacologist consensus, compared to baseline scenarios in which clinicians made treatment decisions independently. Interacting with incorrect recommendations paired with explanations that included limited but easily interpretable information did lead to a significant reduction in treatment selection accuracy compared to baseline questions. These results suggest that incorrect ML recommendations may adversely impact clinician treatment selections and that explanations are insufficient for addressing overreliance on imperfect ML algorithms. More generally, our findings challenge the common assumption that clinicians interacting with ML tools will perform better than either clinicians or ML algorithms individually.

Predicting treatment dropout after antidepressant initiation.

Antidepressants exhibit similar efficacy, but varying tolerability, in randomized controlled trials. Predicting tolerability in real-world clinical populations may facilitate personalization of treatment and maximize adherence. This retrospective longitudinal cohort study aimed to determine the extent to which incorporating patient history from electronic health records improved prediction of unplanned treatment discontinuation at index antidepressant prescription. Clinical data were analyzed from individuals from health networks affiliated with two large academic medical centers between March 1, 2008 and December 31, 2014. In total, the study cohorts included 51,683 patients with at least one International Classification of Diseases diagnostic code for major depressive disorder or depressive disorder not otherwise specified who initiated antidepressant treatment. Among 70,121 total medication changes, 16,665 (23.77%) of them were followed by failure to return; maximum risk was observed with paroxetine (27.71% discontinuation), and minimum with venlafaxine (20.78% discontinuation); Mantel-Haenzel χ2 (8 df) = 126.44, p = 1.54e-23 <1e-6. Models incorporating diagnostic and procedure codes and medication prescriptions improved per-medication Areas Under the Curve (AUCs) to a mean of 0.69 [0.64-0.73] (ranging from 0.62 for paroxetine to 0.80 for escitalopram), with similar performance in the second, replication health system. Machine learning applied to coded electronic health records facilitates identification of individuals at high-risk for treatment dropout following change in antidepressant medication. Such methods may assist primary care physicians and psychiatrists in the clinic to personalize antidepressant treatment on the basis not solely of efficacy, but of tolerability.

Assessment of a Prediction Model for Antidepressant Treatment Stability Using Supervised Topic Models.

Importance: In the absence of readily assessed and clinically validated predictors of treatment response, pharmacologic management of major depressive disorder often relies on trial and error. Objective: To assess a model using electronic health records to identify predictors of treatment response in patients with major depressive disorder. Design, Setting, and Participants: This retrospective cohort study included data from 81 630 adults with a coded diagnosis of major depressive disorder from 2 academic medical centers in Boston, Massachusetts, including outpatient primary and specialty care clinics from December 1, 1997, to December 31, 2017. Data were analyzed from January 1, 2018, to March 15, 2020. Exposures: Treatment with at least 1 of 11 standard antidepressants. Main Outcomes and Measures: Stable treatment response, intended as a proxy for treatment effectiveness, defined as continued prescription of an antidepressant for 90 days. Supervised topic models were used to extract 10 interpretable covariates from coded clinical data for stability prediction. With use of data from 1 hospital system (site A), generalized linear models and ensembles of decision trees were trained to predict stability outcomes from topic features that summarize patient history. Held-out patients from site A and individuals from a second hospital system (site B) were evaluated. Results: Among the 81 630 adults (56 340 women [69%]; mean [SD] age, 48.46 [14.75] years; range, 18.0-80.0 years), 55 303 reached a stable response to their treatment regimen during follow-up. For held-out patients from site A, the mean area under the receiver operating characteristic curve (AUC) for discrimination of the general stability outcome was 0.627 (95% CI, 0.615-0.639) for the supervised topic model with 10 covariates. In evaluation of site B, the AUC was 0.619 (95% CI, 0.610-0.627). Building models to predict stability specific to a particular drug did not improve prediction of general stability even when using a harder-to-interpret ensemble classifier and 9256 coded covariates (specific AUC, 0.647; 95% CI, 0.635-0.658; general AUC, 0.661; 95% CI, 0.648-0.672). Topics coherently captured clinical concepts associated with treatment response. Conclusions and Relevance: The findings suggest that coded clinical data available in electronic health records may facilitate prediction of general treatment response but not response to specific medications. Although greater discrimination is likely required for clinical application, the results provide a transparent baseline for such studies.

Economic complexity unfolded: Interpretable model for the productive structure of economies.

Economic complexity reflects the amount of knowledge that is embedded in the productive structure of an economy. It resides on the premise of hidden capabilities-fundamental endowments underlying the productive structure. In general, measuring the capabilities behind economic complexity directly is difficult, and indirect measures have been suggested which exploit the fact that the presence of the capabilities is expressed in a country's mix of products. We complement these studies by introducing a probabilistic framework which leverages Bayesian non-parametric techniques to extract the dominant features behind the comparative advantage in exported products. Based on economic evidence and trade data, we place a restricted Indian Buffet Process on the distribution of countries' capability endowment, appealing to a culinary metaphor to model the process of capability acquisition. The approach comes with a unique level of interpretability, as it produces a concise and economically plausible description of the instantiated capabilities.