Predicting premature treatment termination in inpatient psychotherapy: A machine learning approach. | ScholarDeck

Paper

Predicting premature treatment termination in inpatient psychotherapy: A machine learning approach.

New research · Internal Medicine

Psychotherapy research : journal of the Society for Psychotherapy Research · 4w

AI / informaticsPsychotherapy research : journal of the Society for Psychotherapy Research· Jul 2026

Predicting premature treatment termination in inpatient psychotherapy: A machine learning approach.

Marlene Engstler, Wolfgang Lutz, Brian Schwartz … Ulrike Dinger

Read paper

Hospital MedicineAI / informaticsClinical practiceQ1IF 4.4

Admission self-report data predicted 59% of premature psychotherapy treatment terminations.

Predicting premature treatment termination in inpatient psychotherapy: A machine learning approach.

Marlene Engstler … Ulrike Dinger

Psychotherapy research · Jul 2026

Purpose

The study aimed to quantify types of premature treatment termination in a psychosomatic hospital and to investigate if patient characteristic at the beginning of inpatient or day-clinic treatment can predict a subsequent premature termination.

Methods

Routine clinical data were analysed retrospectively for N = 2017 patients.

n = 2017 patients

Results

Model correctly identified 59% of patients who dropped out for therapeutic reasons.

Model 1 (PTT-T)

29%

Model 2 (PTT-T)

59%

More results

In this study, 12.1% of the patients ended treatment prematurely related to therapeutic reasons.

Model 1 predicted 29% of PTT-Ts and 95% of NPTT-Ts in the holdout sample correctly.

The absence of self-report measures at admission was the predictor variable with the greatest influence.

“

Conclusion

PTT-T in inpatient treatment can substantially be predicted by routine clinical intake data, which can therefore provide a valuable source for identifying patients at risk.

Read paper