Predicting Lifetime Suicide Attempts in a Community Sample of Adolescents Using Machine Learning Algorithms

Jankowsky, Kristin; Steger, Diana; Schroeders, Ulrich

doi:10.1177/10731911231167490

Cited by 5 publications

(3 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the current study, it was possible to correctly classify 67% (Sample 1) and 75% (Sample 2) of all patients into either therapy dropouts or completers using machine learning prediction models including only baseline indicators of large naturalistic inpatient samples. As it is common for classification tasks with highly unequal group sizes (e.g., Belsher et al, 2019;Jankowsky et al, 2023), we found that members of the majority group, that is therapy completers, could be predicted more accurately. Compared to Bennemann et al (2022) who predicted therapy dropout in a German outpatient sample, AUC were higher in our analyses (.74/.83 vs. .66) which might be attributed to several reasons such as the different dropout rations, predictor variables, length of therapies, or settings (inpatient vs. outpatients).…”

Section: Discussionmentioning

confidence: 60%

First impressions count: Therapists’ impression on patients’ motivation and helping alliance predicts psychotherapy dropout

Jankowsky,

Zimmermann,

Jaeger

et al. 2023

Preprint

View full text Add to dashboard Cite

ObjectiveWith meta-analytically estimated rates of about 25%, dropout in psychotherapies is a major concern for individuals, clinicians, and the healthcare system at large. To be able to counteract dropout in psychotherapy, accurate insights about its predictors are needed. MethodWe compared logistic regression models with two machine learning algorithms (elastic net regressions and gradient boosting machines) in the prediction of therapy dropout in two large inpatient samples (N = 1,691 and N = 12,473) using patient- and therapist-reported variables collected at the time of admission to the clinic.ResultsPredictive accuracies of the two machine learning algorithms were similar and higher than for logistic regressions: Therapy dropout could be predicted with an AUC of .73 and .83 for Sample 1 and 2, respectively. The initial evaluation of patients’ motivation and the therapeutic alliance rated by the respective therapist were the most important predictors of dropout. ConclusionsTherapy dropout in naturalistic inpatient settings can be predicted to a considerable degree by using baseline indicators. Feature selection via regularization leads to higher predictive performances whereas non-linear or interaction effects are dispensable. The most promising point of intervention to reduce therapy dropouts seems to be patients’ motivation and the therapeutic alliance.

show abstract

Section: Discussionmentioning

confidence: 60%

First impressions count: Therapists’ impression on patients’ motivation and helping alliance predicts psychotherapy dropout

Jankowsky,

Zimmermann,

Jaeger

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…As a final robustness check, we reran all our analyses with a random training-test split of 90–10 and repeated the process 1000 times. Except for minor details (90–10 instead of 80–20 and 1000 repetitions instead of 100), we used the protocol that Jankowsky et al used in a recent study 38 . Differences in the amount of variance explained between the model based on Jankowsky et al’s protocol and our original model reported in the manuscript ranged from 0.00 to 0.01 for all research questions.…”

Section: Resultsmentioning

confidence: 99%

Taking another look at intelligence and personality using an eye-tracking approach

Bardach,

Schumacher,

Trautwein

et al. 2024

npj Sci. Learn.

View full text Add to dashboard Cite

Intelligence and personality are both key drivers of learning. This study extends prior research on intelligence and personality by adopting a behavioral-process-related eye-tracking approach. We tested 182 adults on fluid intelligence and the Big Five personality traits. Eye-tracking information (gaze patterns) was recorded while participants completed the intelligence test. Machine learning models showed that personality explained 3.18% of the variance in intelligence test scores, with Openness and, surprisingly, Agreeableness most meaningfully contributing to the prediction. Facet-level measures of personality explained a larger amount of variance (7.67%) in intelligence test scores than the trait-level measures, with the largest coefficients obtained for Ideas and Values (Openness) and Compliance and Trust (Agreeableness). Gaze patterns explained a substantial amount of variance in intelligence test performance (35.91%). Gaze patterns were unrelated to the Big Five personality traits, but some of the facets (especially Self-Consciousness from Neuroticism and Assertiveness from Extraversion) were related to gaze. Gaze patterns reflected the test-solving strategies described in the literature (constructive matching, response elimination) to some extent. A combined feature vector consisting of gaze-based predictions and personality traits explained 37.50% of the variance in intelligence test performance, with significant unique contributions from both personality and gaze patterns. A model that included personality facets and gaze explained 38.02% of the variance in intelligence test performance. Although behavioral data thus clearly outperformed “traditional” psychological measures (Big Five personality) in predicting intelligence test performance, our results also underscore the independent contributions of personality and gaze patterns in predicting intelligence test performance.

show abstract

“…Again, these weights indicate that gaze explained the most variance, but personality facets provided complementary information about participants' intelligence test scores.As a final robustness check, we reran all our analyses with a random training-test split of 90-10 and repeated the process 1,000 times. Except for minor details (90-10 instead of 80-20 and 1,000 repetitions instead of 100), we used the protocol thatJankowsky et al (2023) used in a recent study. Differences in the amount of variance explained between the model based on Jankowsky et al's protocol and our original model reported in the manuscript ranged from 0.00 to 0.01 for all research questions.…”

mentioning

confidence: 99%

Taking Another Look at Intelligence and Personality: An Eye-Tracking Approach

Bardach¹,

Schumacher²,

Trautwein³

et al. 2023

Preprint

View full text Add to dashboard Cite

Intelligence and personality are both key drivers of learning; hence, there is long-standing interest in their associations. This study expands on prior research by adopting a behavioral process-related eye-tracking approach. We tested 182 adults on Big Five personality traits and fluid intelligence. Eye-tracking information (gaze patterns) was recorded while participants completed the intelligence test. Machine learning models showed that personality explained 3.18% of the variance in intelligence test scores, with Openness and, surprisingly, Agreeableness most meaningfully contributing to the prediction. Whereas gaze patterns explained a substantial amount of variance in intelligence test performance (35.91%), they were unrelated to personality traits. Gaze patterns reflected the test-solving strategies described in the literature (constructive matching, response elimination) to some extent. A combined feature vector consisting of gaze-based predictions and personality traits explained 37.50% of the variance in intelligence test performance, with significant unique contributions from both personality and gaze patterns.

show abstract

Predicting Lifetime Suicide Attempts in a Community Sample of Adolescents Using Machine Learning Algorithms

Cited by 5 publications

References 75 publications

First impressions count: Therapists’ impression on patients’ motivation and helping alliance predicts psychotherapy dropout

First impressions count: Therapists’ impression on patients’ motivation and helping alliance predicts psychotherapy dropout

Taking another look at intelligence and personality using an eye-tracking approach

Taking Another Look at Intelligence and Personality: An Eye-Tracking Approach

Contact Info

Product

Resources

About