EUVIMEDSkopri EUVIMED
Open access

Predicting Call Abandonment in a Health Care Call Center Using Nonpersonal Operational Data: Machine Learning Study

Hilmi Al-Shakhshir iD, Sara Kier iD, Dan Hoke iD, Stephanie Hoiriis iD, Mary-Ellen Vicinus iD, Ravi Thadhani iD, Anant Madabhushi iD

JMIR Medical Informatics · 2026

DOI: 10.2196/88441 ↗

At a glance

Journal article in JMIR Medical Informatics, 2026. Written by Hilmi Al-Shakhshir and 6 co-authors. Institution: Atlanta VA Medical Center, Decatur, GA, United States. Major MEDLINE topics: Machine Learning, Call Centers. 23 references. The full text is freely available in PubMed Central.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Background

Call abandonment is a critical barrier to patient access in health care call centers; yet, predictive modeling efforts are limited by strict privacy regulations that restrict the use of personal or behavioral data. Whether abandonment can be accurately predicted using only anonymized operational metrics remains unclear.

Objective

This study evaluated the feasibility, performance, and operational use of machine learning models trained exclusively on nonpersonal, routinely collected call center metrics to predict call abandonment across distinct organizational phases.

Methods

We analyzed 1,037,363 call records from a large academic health care system spanning 4 operational periods marked by workflow changes and skill consolidation. Features included temporal variables, skill identifiers, and rolling operational metrics (in-queue time, occupancy, handle time, after-call work time, and active agents). Random forest and CatBoost models were trained on 3 phases defined as: (T1 [January-April 2023; original workflows], T2 [May-August 2023; post skill consolidation, cross-training, and new workflows], and T3a [September-December 2023; optimized processes]) using 5-fold cross-validation with 3 imbalance-handling strategies (none, class weighting, and synthetic minority oversampling technique). Temporal generalizability was assessed by evaluating all models on all 4 phases, with T3b serving as an unseen holdout set. Performance was evaluated using area under the curve (AUC), precision-recall area under the curve (PR-AUC), Brier score, and calibration error. Shapley additive explanations (SHAP) values quantified feature contributions.

Results

Across all training phases and algorithms, adding operational metrics improved the area under the receiver operating characteristic curve by 0.03-0.13 vs models using only temporal and skill features. The best configuration was a CatBoost model trained on T2 with operational metrics and no imbalance correction (T3b AUC 0.767, PR-AUC 0.068, expected calibration error 0.006, and Brier 0.027). Models trained solely on preintervention data (T1) generalized poorly to postintervention periods when restricted to temporal and skill features (AUC 0.32-0.38) but achieved AUC 0.715 on T3b when operational metrics were included. SHAP analysis consistently identified in-queue time as the dominant predictor, with the number of logged-in agents, hour-of-day, and skill identifiers comprising the remaining top features. Abandonment declined from 8.7% (20,809/238,722) in T1 to 2.8% (8293/300,060) in T3b; model-based analyses of temporal features (day of week and hour of day) showed the highest risk on Mondays and between 11:00 and 16:00. Skill-level analyses showed marked improvement in high-volume imaging teams with high abandonment.

Conclusions

Models trained on nonpersonal operational data predicted call abandonment on the T3b temporal holdout, with real-time queue and staffing metrics providing the dominant signal. These findings support the feasibility of interpretable, operationally grounded abandonment prediction in health care call centers and indicate that models should be retrained after major operational changes.

Subjects

MeSH terms (MEDLINE)

Machine LearningCall CentersHumansPredictive Learning ModelsRandom ForestPrediction AlgorithmsWorkflow

Author keywords

CatBoostSHAPcall abandonmentcall centerclass imbalancehealth care call centermachine learningoperational analyticspatient accessrandom foresttemporal validation

Authors and institutions

  • Atlanta VA Medical Center, Decatur, GA, United States.
  • Executive Consulting Group Management Consultants, Atlanta, GA, United States.
  • Emory Healthcare, Atlanta, GA, United States.
  • Disruptive Innovations, Atlanta, GA, United States.
  • Department of Biomedical Engineering, Wallace H. Coulter, Emory University, Atlanta, GA, United States.

ORCID profiles: Hilmi Al-Shakhshir, Sara Kier, Dan Hoke, Stephanie Hoiriis, Mary-Ellen Vicinus, Ravi Thadhani, Anant Madabhushi

Cite

APA

Al-Shakhshir, H., Kier, S., Hoke, D., Hoiriis, S., Vicinus, M. E., Thadhani, R., & Madabhushi, A. (2026). Predicting Call Abandonment in a Health Care Call Center Using Nonpersonal Operational Data: Machine Learning Study. JMIR Medical Informatics. https://doi.org/10.2196/88441

Vancouver

Al-Shakhshir H, Kier S, Hoke D, Hoiriis S, Vicinus ME, Thadhani R, et al. Predicting Call Abandonment in a Health Care Call Center Using Nonpersonal Operational Data: Machine Learning Study. JMIR Medical Informatics. 2026. doi:10.2196/88441

BibTeX
@article{AlShakhshir2026,
  author = {Al-Shakhshir, Hilmi and Kier, Sara and Hoke, Dan and Hoiriis, Stephanie and Vicinus, Mary-Ellen and Thadhani, Ravi and Madabhushi, Anant},
  title = {Predicting Call Abandonment in a Health Care Call Center Using Nonpersonal Operational Data: Machine Learning Study},
  journal = {JMIR Medical Informatics},
  year = {2026},
  doi = {10.2196/88441}
}
Start for free →