Data-Driven Predictive Health Screening in a University Workforce: A Machine Learning Approach to Pre-Employment Medical Assessment

DOI

10.2991/978-94-6239-756-9_22How to use a DOI?

Keywords

Predictive Analytics; Pre-Employment Health Screening; Machine Learning in Occupational Health; Hypertension Risk Stratification; Workforce Wellness Programs; University Workforce Health

Abstract

Background

Pre-employment health assessments represent a valuable yet underutilized opportunity for preventive care in university workforces.

Objectives

This study developed a machine learning–based framework to (i) predict early-stage hypertension, (ii) stratify employees into risk-based health profiles, and (iii) integrate anomaly and temporal surveillance into institutional wellness planning.

Methods

We conducted a retrospective analysis of 1,537 pre-employment medical checkups from 2021 to 2023, incorporating demographic, biometric, and laboratory parameters. Logistic regression was used to predict hypertension risk with a 70:30 training-test split, K-means clustering to stratify health profiles, and rule-based algorithms for anomaly detection and temporal trend analysis.

Results

The predictive model achieved a recall of 97.5%, an F1-score of 69.9, and an area under the ROC curve of 0.85, prioritizing sensitivity for early risk capture. Clustering identified three distinct health profiles: normative, over-weight with mild blood pressure elevation, and obese with high blood pressure elevation. Automated surveillance flagged cases of thrombocytopenia, severe anemia, and extreme BMI, while temporal analysis revealed screening volume peaks aligned with institutional hiring cycles.

Conclusions

Embedding predictive analytics into routine pre-employment assessments enables high-sensitivity hypertension triage, tailored wellness path-ways, and data-driven operational planning. This comprehensive framework of-fers a scalable model for preventive workforce health management in universities and comparable organizations striving to become health-promoting institutions. Novelty/Originality: This study presents a machine learning framework for pre-employment health screening, linking clinical risk prediction with administrative planning to enable proactive, data-driven workforce wellness and institutional efficiency.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Rajiv Yeravdekar
AU  - Alaka Chandak
PY  - 2026
DA  - 2026/08/31
TI  - Data-Driven Predictive Health Screening in a University Workforce: A Machine Learning Approach to Pre-Employment Medical Assessment
BT  - Proceedings of the Conference on Bioengineering for Global Health (SYMRESEARCH 2.0 2025)
PB  - Atlantis Press
SP  - 314
EP  - 326
SN  - 2468-5747
UR  - https://doi.org/10.2991/978-94-6239-756-9_22
DO  - 10.2991/978-94-6239-756-9_22
ID  - Yeravdekar2026
ER  -