Human-Centric Clinical AI: A Structural Data Validation Approach for Human-Reliable Medical Inference

Marco Roccetti

doi:10.53941/tai.2026.100013

Abstract

Researchers increasingly rely on Clinical Artificial Intelligence (CAI) to derive predictive insights from massive observational datasets. However, the paradigm of Big Medical Inference often conflates statistical volume with clinical representativeness. This study argues that when methodological rigor is sacrificed for data scale, AI models risk institutionalizing historical biases, thereby compromising patient safety and public health policy integrity. We propose a precautionary, multi-level auditing framework designed to assess the structural architectural integrity of large-scale clinical datasets prior to computational deployment. Rather than contesting specific clinical outcomes, our approach establishes a quantitative prerequisite for CAI: the validation of demographic representativeness and baseline case distribution against official national benchmarks. To demonstrate the validity of our approach, we applied our framework to a prominent, high-profile case study. Our check revealed a tripartite structural divergence: a 32.5% demographic deficit in high-risk elderly (aged ≥ 65 years) strata, an aggregate of approximately 26% cancer incidence suppression, and a 45.1% deflation of expected cases in non-exposed groups. These discrepancies demonstrate that even massive datasets can be fundamentally misaligned with clinical reality. We conclude that structural validation is not an elective procedure but an ethical imperative for Human-Centric Clinical AI. By re-establishing this hierarchy of validation, we ensure that the intelligence of automated AI systems remains subordinate to the structural truth of the data, thereby transitioning from a reliance on Big Data alone toward a more robust, ethically sound, and authentic practice of clinical knowledge.

References

1.
Topol, E.J. High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 2019, 25, 44–56. https://doi.org/10.1038/s41591-018-0300-7.
2.
Roccetti, M. Quantifying structural selection bias in observational cohort data: a ponderation analysis of age—specific incidence rates to inform vaccine safety verification. Front. Pharmacol. 2026, 16, 1754809. https://doi.org/10.3389/fphar.2025.1754809.
3.
Roccetti, M.; Delnevo, G.; Casini, L.; et al. Is bigger always better? A controversial journey to the center of machine learning design, with uses and misuses of big data for predicting water meter failures. J. Big Data 2019, 6, 70. https://doi.org/10.1186/s40537-019-0235-y.
4.
Kim, H.J.; Kim, M.H.; Choi, M.G.; et al. 1-year risks of cancers associated with COVID-19 vaccination: A large population-based cohort study in South Korea. Biomark. Res. 2025, 13, 114. https://doi.org/10.1186/s40364-025-00831-w.
5.
Fisher, R. Studies in Crop Variation (I). An Examination of the Yield of Dressed Grain from Broadbalk. J. Agric. Sci. 1921, 11, 107–135. https://doi.org/10.1017/s0021859600003750.
6.
Pearson, K. On the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling. Lond. Edinb. Dublin Philos. Mag. J. Sci. 1900, 50, 157–175. https://doi.org/10.1080/14786440009463897.
7.
Neyman, J.; Pearson, E.S. On the problem of the most efficient tests of statistical hypotheses. Philos. Trans. R. Soc. Lond. A 1933, 231, 289–337. https://doi.org/10.1098/rsta.1933.0009.
8.
Cox, D.R. Regression Models and Life-Tables. J. R. Stat. Soc. B 1972, 34, 187–220. https://doi.org/10.1111/j.2517-6161.1972.tb00899.x.
9.
Wilson, R. Feminine Forever; M. Evans and Company: New York, NY, USA, 1966.
10.
Anderson, G.; Limacher, M.; Assaf, A.; et al. Effects of conjugated equine estrogen in postmenopausal women with hysterectomy: The Women’s Health Initiative randomized controlled trial. JAMA 2004, 291, 1701–1712. https://doi.org/10.1001/jama.291.14.1701.
11.
Cagnacci, A.; Venier, M. The Controversial History of Hormone Replacement Therapy. Medicina 2019, 55, 602. https://doi.org/10.3390/medicina55090602.
12.
Deer, B. How the case against the MMR vaccine was fixed. BMJ 2011, 342, c5347. https://doi.org/10.1136/bmj.c5347.
13.
Spitzer, W.; Suissa, S.; Ernst, P.; et al. The use of beta-agonists and the risk of death and near death from asthma. N. Engl. J. Med. 1992, 326, 501–506. https://doi.org/10.1056/nejm199202203260801.
14.
Roccetti, M. Enhancing public health surveillance: A statistical validation of potential sampling bias in large retrospective vaccine cohorts. AIMS Public Health 2026, 13, 589–597. https://doi.org/10.3934/publichealth.2026031.
15.
Kang, M.; Jung, K.; Bang, S.; et al. Cancer Statistics in Korea: Incidence, Mortality, Survival, and Prevalence in 2020. Cancer Res. Treat. 2023, 55, 385–399. https://doi.org/10.4143/crt.2023.447.
16.
Park, E.; Jung, K.W.; Park, N.; et al. Cancer Statistics in Korea: Incidence, Mortality, Survival, and Prevalence in 2021. Cancer Res. Treat. 2024, 56, 357–371. https://doi.org/10.4143/crt.2024.253.
17.
Park, E.; Jung, K.W.; Park, N.; et al. Cancer Statistics in Korea: Incidence, Mortality, Survival, and Prevalence in 2022. Cancer Res. Treat. 2025, 57, 312–330. https://doi.org/10.4143/crt.2025.264.
18.
Statista. Crude Incidence Rate of Cancer in South Korea in 2022, by Age Group (Per 100,000 Population). Available online: https://www.statista.com/statistics/1440818/south-korea-cancer-crude-incidence-rate-by-age/ (accessed on 20 May 2026).
19.
World Bank. Population Ages 65 and Above (% of Total Population)—Korea, Rep. Available online: https://data.worldbank.org/indicator/SP.POP.65UP.TO.ZS?locations=KR (accessed on 20 May 2026).
20.
Roccetti, M. Unlocking the stochastic parrot: Epistemic obligation and the decline of biological plausibility in clinical reality. Inform. Med. Unlocked 2026, 62, 101752. https://doi.org/10.1016/j.imu.2026.101752.
21.
Chemaitelly, H.; Ayoub, H.H.; Coyle, P.; et al. Assessing healthy vaccinee effect in COVID-19 vaccine effectiveness studies: a national cohort study in Qatar. eLife 2025, 14, e103690. https://doi.org/10.7554/elife.103690.
22.
D’Agostino, R.B. Propensity score methods for bias reduction in the comparison of a treatment to a non-randomized control group. Stat. Med. 1998, 17, 2265–2281. https://doi.org/10.1002/(SICI)1097-0258(19981015)17:19<2265::AID-SIM918>3.0.CO;2-B.
23.
Qin, R.; Titler, M.G.; Shever, L.L.; et al. Estimating effects of nursing intervention via propensity score analysis. Nurs. Res. 2008, 57, 444–452. https://doi.org/10.1097/nnr.0b013e31818c66f6.
24.
Austin, P.; Grootendorst, P.; Anderson, G. A comparison of the ability of different propensity score models to balance measured variables between treated and untreated subjects: A Monte Carlo study. Stat. Med. 2007, 26, 734–753. https://doi.org/10.1002/sim.2580.
25.
Austin, P.C. Goodness-of-fit diagnostics for the propensity score model when estimating treatment effects using covariate adjustment with the propensity score. Pharmacoepidemiol. Drug Saf. 2008, 17, 1202–1217. https://doi.org/10.1002/pds.1673.
26.
von Elm, E.; Altman, D.; Egger, M.; et al. The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) Statement: guidelines for reporting observational studies. PLoS Med 2007, 4, e296. https://doi.org/10.1371/journal.pmed.0040296.
27.
Meng, X.L. Statistical paradises and paradoxes in big data (I): Law of large populations, big data paradox, and the 2016 US presidential election. Ann. Appl. Stat. 2018, 12, 685–726. https://doi.org/10.1214/18-aoas1161sf.
28.
Guo, S.; Wu, D.O. Game Theoretical AI for Precision Medicine. Trans. Artif. Intell. 2025, 1, 170–196. https://doi.org/10.53941/tai.2025.100011.

Scilight Press

Author Information

Abstract

Keywords

References

About Scilight

Journals

Publishing Policies

Contact Us