A Data-Driven Event-Time Optimization Model Based on Individualized Risk Segmentation

Jie Ma

doi:10.54097/ztxprv89

Authors

Jie Ma

DOI:

https://doi.org/10.54097/ztxprv89

Keywords:

Event-time modeling; Risk-aware optimization; Data-driven grouping; Threshold-based decision system; Cost-sensitive learning

Abstract

Event-driven decision optimization has become a critical research area in computational modeling, especially in systems where outcomes depend on threshold-based signals and individual feature heterogeneity. This study proposes a data-driven event-time optimization model that determines the optimal decision timing under uncertain and feature-dependent conditions. The framework considers individual-level variations—such as body-mass-related indicators—as covariates influencing the time required for a measurable signal to reach a predefined threshold. A feature-based grouping strategy is developed to cluster individuals with similar dynamic patterns, assigning each group an optimal initial decision point. For cases where the threshold is not reached, a secondary decision (re-evaluation) mechanism is introduced to minimize overall cost and risk. By integrating risk segmentation functions, survival-type event-time modeling, and cost-sensitive optimization, the proposed model achieves improved accuracy, lower uncertainty, and higher efficiency in threshold-based decision systems. This framework not only enhances reliability within its biomedical origin but also provides a transferable methodology for broader applications in computational intelligence, predictive maintenance, and big-data-driven decision optimization.

References

[1]Rose, N. C., Barrie, E. S., Malinowski, J., Jenkins, G. P., McClain, M. R., LaGrave, D., ... & ACMG Professional Practice and Guidelines Committee. (2022). Systematic evidence-based review: the application of noninvasive prenatal screening using cell-free DNA in general-risk pregnancies. Genetics in Medicine, 24(7), 1379-1391.

[2]Dungan, J. S., Klugman, S., Darilek, S., Malinowski, J., Akkari, Y. M., Monaghan, K. G., ... & ACMG Board of Directors. (2023). Noninvasive prenatal screening (NIPS) for fetal chromosome abnormalities in a general-risk population: an evidence-based clinical guideline of the American College of Medical Genetics and Genomics (ACMG). Genetics in Medicine, 25(2), 100336.

[3]Cernat, A., De Freitas, C., Majid, U., Trivedi, F., Higgins, C., & Vanstone, M. (2019). Facilitating informed choice about non-invasive prenatal testing (NIPT): a systematic review and qualitative meta-synthesis of women’s experiences. BMC pregnancy and childbirth, 19(1), 27.

[4]Oliveri, S., Ongaro, G., Cutica, I., Menicucci, G., Belperio, D., Spinella, F., & Pravettoni, G. (2023). Decision-making process about prenatal genetic screening: how deeply do moms-to-be want to know from Non-Invasive Prenatal Testing?. BMC pregnancy and childbirth, 23(1), 38.

[5]Zheng, J., Lu, H., Li, M., Guan, Y., Yang, F., Xu, M., ... & Zhou, Y. (2020). The clinical utility of non-invasive prenatal testing for pregnant women with different diagnostic indications. Frontiers in Genetics, 11, 624.

[6]Kater‐Kuipers, A., De Beaufort, I. D., Galjaard, R. J. H., & Bunnik, E. M. (2020). Rethinking counselling in prenatal screening: an ethical analysis of informed consent in the context of non‐invasive prenatal testing (NIPT). Bioethics, 34(7), 671-678.

[7]Allyse, M., Sayres, L. C., Goodspeed, T., Michie, M., & Cho, M. K. (2015). “Don't want no risk and don't want no problems”: public understandings of the risks and benefits of noninvasive prenatal testing in the United States. AJOB empirical bioethics, 6(1), 5-20.

[8]Schöne-Seifert, B., & Junker, C. (2021). Making use of non-invasive prenatal testing (NIPT): rethinking issues of routinization and pressure. Journal of Perinatal Medicine, 49(8), 959-964.