Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 13 min ago
Peer-reviewedCC BYHealthcare (Basel, Switzerland)

Effectiveness of Artificial Intelligence Systems in Healthcare: A Systematic Review of Clinical and Organizational Outcomes.

  • Andrea Ceccarelli1,2,3
  • Tommaso Montagnani3
  • Tristan Darius Marin4
  • Vincenzo Cassetta3
  • Marco Senni5
  • Marco Montalti6
  • Francesco Sintoni2
  • Davide Gori3
6 affiliations
  1. 1Department of Medicine and Surgery, University of Milano-Bicocca, Via Cadore 48, 20900 Monza, Italy.
  2. 2Romagna Local Health Authority, Forlì Health District, 47121 Forlì, Italy.
  3. 3Unit of Hygiene and Medical Statistics, Department of Biomedical and Neuromotor Sciences, University of Bologna, 40126 Bologna, Italy.
  4. 4Department of Public Health, Azienda USL di Bologna, Via Castiglione 29, 40124 Bologna, Italy.
  5. 5Nursing Unit, Primary Care and Community Medicine Department of Forlì-Cesena, Romagna Local Health Authority, Via Carlo Boni 67, 47521 Cesena, Italy.
  6. 6Romagna Local Health Authority, Cesena and Rubicone Health District, 47121 Forlì, Italy.
Read full textPDFDOICite

Abstract

Background

The integration of artificial intelligence (AI)-based systems into healthcare is accelerating rapidly, yet evidence of their real-world clinical and organizational effectiveness remains fragmented.Methods

A PRISMA 2020-compliant systematic review of randomized controlled trials (RCTs) evaluating AI-based interventions in real-world healthcare settings was conducted. MEDLINE (PubMed), CINAHL, Cochrane CENTRAL, and ClinicalTrials.gov were searched up to January 2026. AI interventions were classified post hoc into three functional categories: perceptive AI, predictive/decision support AI, and conversational/adaptive AI. The direction of effect was classified as positive, neutral, mixed, or negative based on the primary endpoint, effect magnitude, and authors' interpretation. Risk of bias was assessed using the Cochrane RoB-2 tool.Results

A total of 54 RCTs were included. Overall, 40 studies (74.1%) reported a positive direction of effect, nine a neutral result, four a mixed result, and one a negative result. Perceptive AI (n = 17) showed consistent benefits in diagnostic accuracy. Predictive/decision support AI (n = 15) showed heterogeneous results, with effectiveness dependent on workflow integration. Conversational/adaptive AI (n = 22) showed the most consistent positive signal, particularly for chronic disease self-management, behavioral change, and therapeutic adherence.Conclusions

Evidence from randomized trials suggests that AI-based interventions may provide meaningful benefits in real-world healthcare settings, with effectiveness varying by functional category, implementation context, and outcome domain. Future research should prioritize pragmatic multicenter trials with standardized reporting of clinical, organizational, and implementation outcomes.

Related

  1. Effectiveness of intervention using artificial intelligence for students with disabilities: systematic review and meta-analysis
    Eun-Young Park, Ok-In Lee, Heeju Kim +2
    Frontiers in Public HealthPeer-reviewedCC BY 4.0Epidemiology & public healthFrontiersCrossref
  2. Effectiveness and user experience of ambient artificial intelligence-driven scribe technology among clinicians: a protocol for a systematic review.
    Ravi Shankar, Fiona Devi Siva Kumar, Anjali Bundele +1
    Systematic reviewsPeer-reviewedCC BY-NC-NDFull textClinical trials & evidence synthesisEurope PMCDOAJ
  3. Effectiveness of artificial intelligence-assisted colonoscopy for colorectal lesion detection: a systematic review and meta-analysis of randomized controlled trials
    Xia Liu, Jian Qin, Yuxia Zhao +3
    BMC Medical ImagingPeer-reviewedCC BYFull textOncologyDOAJ
  4. Mathematical foundations of artificial intelligence in healthcare: a systematic review
    Yuliana Jiménez-Gaona, Vasudevan Lakshminarayanan
    Frontiers in Artificial IntelligencePeer-reviewedCC BY 4.0Full textEpidemiology & public healthPMC
  5. Clinical Effectiveness, Safety, and Implementation of Artificial Intelligence-Assisted Insulin Management Systems in Type 1 and Type 2 Diabetes: A Systematic Review of Randomized Controlled Trials.
    Victória Dogani Rodrigues, Virgínia Maria Cavallari Strozze Catharin, Mauro Audi +6
    Diseases (Basel, Switzerland)Peer-reviewedCC BYFull textEndocrinology & metabolismEurope PMC

Cite

BibTeXRIS
BibTeX
@article{ceccarelli2026effectiveness,
  title = {{Effectiveness of Artificial Intelligence Systems in Healthcare: A Systematic Review of Clinical and Organizational Outcomes.}},
  author = {Andrea Ceccarelli and Tommaso Montagnani and Tristan Darius Marin and Vincenzo Cassetta and Marco Senni and Marco Montalti and Francesco Sintoni and Davide Gori},
  journal = {Healthcare (Basel, Switzerland)},
  year = {2026},
  month = oct,
  doi = {10.3390/healthcare14203532},
  url = {https://europepmc.org/article/MED/42940577},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Effectiveness of Artificial Intelligence Systems in Healthcare: A Systematic Review of Clinical and Organizational Outcomes.
AU  - Andrea Ceccarelli
AU  - Tommaso Montagnani
AU  - Tristan Darius Marin
AU  - Vincenzo Cassetta
AU  - Marco Senni
AU  - Marco Montalti
AU  - Francesco Sintoni
AU  - Davide Gori
PY  - 2026
DA  - 2026/10/20
JO  - Healthcare (Basel, Switzerland)
DO  - 10.3390/healthcare14203532
UR  - https://europepmc.org/article/MED/42940577
AB  - Background  The integration of artificial intelligence (AI)-based systems into healthcare is accelerating rapidly, yet evidence of their real-world clinical and organizational effectiveness remains fragmented.Methods  A PRISMA 2020-compliant systematic review of randomized controlled trials (RCTs) evaluating AI-based interventions in real-world healthcare settings was conducted. MEDLINE (PubMed), CINAHL, Cochrane CENTRAL, and ClinicalTrials.gov were searched up to January 2026. AI interventions were classified post hoc into three functional categories: perceptive AI, predictive/decision support AI, and conversational/adaptive AI. The direction of effect was classified as positive, neutral, mixed, or negative based on the primary endpoint, effect magnitude, and authors' interpretation. Risk of bias was assessed using the Cochrane RoB-2 tool.Results  A total of 54 RCTs were included. Overall, 40 studies (74.1%) reported a positive direction of effect, nine a neutral result, four a mixed result, and one a negative result. Perceptive AI (n = 17) showed consistent benefits in diagnostic accuracy. Predictive/decision support AI (n = 15) showed heterogeneous results, with effectiveness dependent on workflow integration. Conversational/adaptive AI (n = 22) showed the most consistent positive signal, particularly for chronic disease self-management, behavioral change, and therapeutic adherence.Conclusions  Evidence from randomized trials suggests that AI-based interventions may provide meaningful benefits in real-world healthcare settings, with effectiveness varying by functional category, implementation context, and outcome domain. Future research should prioritize pragmatic multicenter trials with standardized reporting of clinical, organizational, and implementation outcomes.
SN  - 2227-9032
ER  -