Process Automation and Business Intelligence Applied to Healthcare Management

The increasing availability of health data creates opportunities to improve public health surveillance and evidence-based decision-making. However, data inconsistencies, lack of standardization, and time-consuming manual processing limit the effective use of epidemiological information. This study aimed to develop and implement an automated data-processing solution integrated with Business Intelligence (BI) dashboards to improve data quality, streamline information processing, and support decision-making at the VIII Regional Health Management Office (VIII GERES), Pernambuco, Brazil. An applied technological case study with a quantitative approach was conducted between July 21 and August 11, 2025. The solution was developed using Python, incorporating data manipulation, approximate string matching, and an iterative learning mechanism based on human validation and decisions stored in JSON files. The processed data were integrated into Microsoft Power BI to develop three dashboards covering Land Transport Accidents (ATT), epidemiological surveillance data from the Notifiable Diseases Information System (SINAN), and healthcare regulation. The consolidated databases comprised 100,300 records. The software identified and corrected more than 60% of inconsistencies in neighborhood names and processed approximately 10,000 records per minute. In the final test, a database containing more than 30,000 records was processed without human intervention, using previously validated information. Processing time decreased from more than 30 days under the previous manual workflow to approximately 10 minutes. The dashboards enabled historical, epidemiological, geographic, and healthcare regulation analyses previously constrained by data inconsistencies. The findings demonstrate the feasibility of integrating automation and BI to strengthen data quality, operational efficiency, and information management in regional health surveillance.