Artificial Intelligence for Patient Safety: Strengthening Clinical Pharmacy Practice in Primary Health Care within Brazil’s Unified Health System
1
Instituto de Inteligência Artificial na Saúde, NoHarm.ai - Instituto de Inteligência Artificial na Saúde, Porto Alegre, Rio Grande do Sul, Brazil
Popul. Med. 2026;8(Supplement Supplement 1):A1502
ABSTRACT
ABSTRACT:
Context The Brazilian Unified Health System (SUS) Primary Health Care (PHC) faces socioeconomic and clinical resource gaps in the North and Northeast regions, potentially driving preventable adverse events. Implementing systematic medication reviews offers an opportunity to strengthen patient safety. The NOHARM- Intelligence for Patient Safety project was implemented across territories totaling 85000 km² with a GDP of $5.6 billion¹,². For comparison, Austria has a similar area (83000 km²) but a GDP of $520 billion³,⁴. These complex territories feature dispersed populations, predominantly rural areas, and restricted access to health services.
METHODS:
This implementation evaluation study focused on 20 municipalities (16 operational during the analysis), prioritizing areas with high social vulnerability and physician density below 1 per 1000 inhabitants. The intervention utilizes the NOHARM platform⁵ integrated with Electronic Health Records, featuring an AI-based clinical pharmacy module for automated prescription review, drug interaction detection, and dosing alerts. Implementation included structured training for SUS managers, continuous technical support, and infrastructure adaptations to ensure long-term PHC capacity.
RESULTS:
Between March and December 2025, 37000 patients had prescriptions reviewed by pharmacists triggered by NOHARM alerts (representing ~10% of total prescriptions). This resulted in over 8000 pharmaceutical interventions, with a 99% physician acceptance rate for prescriber-correctable recommendations. In one municipality, prescription verification capacity quadrupled. AI-supported clinical pharmacy reinforced patient safety, prevented medication errors, and qualified care for vulnerable populations.
CONCLUSIONS:
AI implementation in PHC improved patient safety by structuring clinical pharmacy and mitigating risks. By reducing preventable errors, the model optimizes resource use and strengthens SUS sustainability. Implemented in highly vulnerable territories, NOHARM is a scalable and adaptable solution for PHC systems, promoting efficiency, equity, and quality in public health care.
Context The Brazilian Unified Health System (SUS) Primary Health Care (PHC) faces socioeconomic and clinical resource gaps in the North and Northeast regions, potentially driving preventable adverse events. Implementing systematic medication reviews offers an opportunity to strengthen patient safety. The NOHARM- Intelligence for Patient Safety project was implemented across territories totaling 85000 km² with a GDP of $5.6 billion¹,². For comparison, Austria has a similar area (83000 km²) but a GDP of $520 billion³,⁴. These complex territories feature dispersed populations, predominantly rural areas, and restricted access to health services.
METHODS:
This implementation evaluation study focused on 20 municipalities (16 operational during the analysis), prioritizing areas with high social vulnerability and physician density below 1 per 1000 inhabitants. The intervention utilizes the NOHARM platform⁵ integrated with Electronic Health Records, featuring an AI-based clinical pharmacy module for automated prescription review, drug interaction detection, and dosing alerts. Implementation included structured training for SUS managers, continuous technical support, and infrastructure adaptations to ensure long-term PHC capacity.
RESULTS:
Between March and December 2025, 37000 patients had prescriptions reviewed by pharmacists triggered by NOHARM alerts (representing ~10% of total prescriptions). This resulted in over 8000 pharmaceutical interventions, with a 99% physician acceptance rate for prescriber-correctable recommendations. In one municipality, prescription verification capacity quadrupled. AI-supported clinical pharmacy reinforced patient safety, prevented medication errors, and qualified care for vulnerable populations.
CONCLUSIONS:
AI implementation in PHC improved patient safety by structuring clinical pharmacy and mitigating risks. By reducing preventable errors, the model optimizes resource use and strengthens SUS sustainability. Implemented in highly vulnerable territories, NOHARM is a scalable and adaptable solution for PHC systems, promoting efficiency, equity, and quality in public health care.
| eISSN: | 2654-1459 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
