Home › Research › Health systems and care delivery
Artificial Intelligence in Medicare and Medicaid: A Review of Clinical Decision Support, Fraud Detection, Prior Authorization, and Healthcare Utilization
Monika Nanjappa. Not indexed, 2026
Topic: Risk, prevention and care in population studies
Plain-language summary
Medicare and Medicaid provide health coverage to millions of Americans, including older adults, people with disabilities, low-income families, children, and individuals with complex medical and social needs. The large volume of claims, pharmacy, demographic, clinical, and healthcare utilization data generated through these programs has created opportunities for artificial intelligence and machine-learning applications. Recent research has examined the use of these methods for clinical risk prediction, care management, healthcare utilization, fraud detection, payment modeling, and administrative review. This review analyzes recent studies related to artificial intelligence in Medicare and Medicaid, with particular attention to clinical decision support, healthcare utilization, fraud detection, prior authorization, and beneficiary risk assessment. The literature shows that machine-learning models can identify patterns associated with cognitive impairment, falls, acutecare use, emergency-department visits, elder mistreatment, and healthcare spending. Recent Medicaid research has also explored reinforcement learning as a method for selecting care-management interventions. At the administrative level, machine learning is increasingly being considered for claims review, fraud detection, and prior authorization support. Several limitations remain. Many studies rely on retrospective data and have limited prospective or external validation. Administrative claims may not fully capture functional status, social conditions, or barriers to care. Complex models may also be difficult to interpret when their predictions influence clinical decisions, healthcare access, or public spending. This review identifies major research gaps and proposes an implementation framework in which AI supports clinical and administrative decision-making while maintaining human review, fairness assessment, privacy protection, and continuous monitoring.
What this study adds
Evidence grade: Low
This review reports that machine-learning models can identify patterns associated with cognitive impairment, falls, acute care use, emergency-department visits, elder mistreatment, and healthcare spending. It notes that many studies rely on retrospective data and that several limitations remain.
Taken from this record’s own fields, not from reading the paper. The grade is assigned from the abstract’s wording; what that means.
Cite this study APA, Vancouver, BibTeX · download .bib or .ris
APA 7th
Nanjappa, M. (2026). Artificial Intelligence in Medicare and Medicaid: A Review of Clinical Decision Support, Fraud Detection, Prior Authorization, and Healthcare Utilization. https://doi.org/10.2139/ssrn.7316383
Vancouver
Nanjappa M. Artificial Intelligence in Medicare and Medicaid: A Review of Clinical Decision Support, Fraud Detection, Prior Authorization, and Healthcare Utilization. 2026. doi:10.2139/ssrn.7316383.
BibTeX
@article{nanjappa2026-f75ba529,
author = {Nanjappa, Monika},
title = {{Artificial Intelligence in Medicare and Medicaid: A Review of Clinical Decision Support, Fraud Detection, Prior Authorization, and Healthcare Utilization}},
year = {2026},
doi = {10.2139/ssrn.7316383},
url = {https://doi.org/10.2139/ssrn.7316383}
}
Built from the record alzhub holds for this paper, not looked up. This record has no journal, so the citation leaves it out. Volume, issue and page numbers are not held in the record. Check the citation against the original before you use it.
Key findings
- The literature shows that machine-learning models can identify patterns associated with cognitive impairment, falls, acutecare use, emergency-department visits, elder mistreatment, and healthcare spending.
Why it matters
This review reports that machine-learning models can identify patterns associated with cognitive impairment, falls, acute care use, emergency-department visits, elder mistreatment, and healthcare spending. It notes that many studies rely on retrospective data and that several limitations remain.
Study details
- Evidence strengthLow
How this study scored 15/100
Preprint — not yet peer-reviewed. It scored 15 on the same rubric, which is below the 16 cap we apply to non-peer-reviewed sources. Scored zero for study design, sample size, effect reported, studied in people and randomized / blinded because the record does not state it. We have no data on impact for its field and year, senior author's track record and institution's track record, so those were left out: it earned 13 of the 87 points we could judge it on, which is 15 out of 100.
| Component | Points | Why |
|---|---|---|
| Journal tier | 2 / 10 | Tier 4 — not a peer-reviewed journal (Not indexed) |
| Journal's citation record | 0 / 4 | Not a journal article, so the journal's record does not count |
| Study design | 0 / 12 | No study design recorded — scores zero, not guessed (not stated in the record — scored 0) |
| Strength of evidence | 1 / 5 | Rated “low” in our summary |
| Peer-review validation | 4 / 10 | Preprint — not yet peer-reviewed. Hosted on a preprint server. |
| How recent | 5 / 5 | 2026 — within 1 year(s) of the newest study here |
| Sample size | 0 / 4 | Participant count not stated — scores zero (not stated in the record — scored 0) |
| Effect reported | 0 / 3 | No effect size reported — scores zero (not stated in the record — scored 0) |
| Studied in people | 0 / 3 | Not stated whether this was studied in people — scores zero (not stated in the record — scored 0) |
| Randomized / blinded | 0 / 2 | No randomization or blinding stated — scores zero (not stated in the record — scored 0) |
| Times cited | 0 / 7 | Cited 0 times (OpenAlex, 2026-10-10) |
| Citations per year | 0 / 5 | 0.0 citations a year over 2 year(s) since 2026 |
| Impact for its field and year | — / 6 | No field-weighted citation impact (OpenAlex has none yet) — left out of this score |
| Cited by studies here | 0 / 6 | No other study in this library cites it |
| Still being cited | 0 / 4 | Cited 0 times in 2024–2026 (2026 still in progress; OpenAlex) |
| Senior author's track record | — / 4 | OpenAlex's profile for last-listed author Monika Nanjappa holds only 5 work(s), too few to judge a track record — left out of this score |
| Institution's track record | — / 3 | No institution listed in OpenAlex — left out of this score |
| Multicenter collaboration | 0 / 3 | OpenAlex lists 0 institution(s) in 0 countries — scores zero (affiliation lists can be incomplete) |
| Indexed in PubMed | 1 / 2 | Not in PubMed, but has a DOI |
| Free to read | 0 / 2 | Behind a paywall — scores zero |
| Points | 13 / 87 | Scored on 17 of 20 parts. We have no data for the rest, so they are left out: 13 of the 87 points we could judge it on is 15 out of 100. |
| Total | 15 / 100 | — |
What each of these 20 components measures, and what this score is not →
Read the original
Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).
Related
Studies in the library that share something with this one. The line above each title says what.
Related studies in Health systems and care delivery from nearby years
Also in Health systems and care delivery
172 studies in the library are filed under Health systems and care delivery with no topic tag they share with another; these are this study's neighbours in a fixed tour of them. The Health systems and care delivery hub.