Performance, Scalability and Maintenance: An Experimental Study of RPA vs. Autonomous Agents in the Healthcare Domain
Authors: Daniel Schulz, Pedro Cabral Buchaim, Bernardo Soares, Fernando Rafael Ensslin Schwengber, Lorenzo Farias, Daniela Duarte da Silva Bagatini, Ana Paula Wernz da Cunha Müller
Organizations: Department of Engineering, Computer Science and Architecture, University of Santa Cruz do Sul (UNISC), Santa Cruz do Sul, Rio Grande do Sul, Brazil. · Graduate Program in Industrial Systems and Processes (PPGSPI), University of Santa Cruz do Sul (UNISC), Santa Cruz do Sul, Rio Grande do Sul, Brazil. · Clínica de Mastologia Dra. Ana Paula Muller Ltda., Porto Alegre, Rio Grande do Sul, Brazil.
Healthcare information systems are fragmented, and retrieving data from legacy web portals is a recurrent need. Robotic Process Automation (RPA) is deterministic but sensitive to interface changes, whereas autonomous agents based on large language models (Agent Process Automation, APA) promise adaptability at a higher computational cost. Following Design Science Research, we developed and compared an RPA solution (Playwright) and an APA solution (browser-use, LangGraph and Gemini 2.5 Flash-lite) to retrieve mammography and breast ultrasound reports from a laboratory portal, treating reports solely as informational artifacts. Across two rounds (T and T+7), RPA reached 98.90% accuracy and 98.27% F1-score versus 96.49% and 94.48% for APA, was about 13 times faster (16.07 s vs. 207.21 s per patient) and cost about six times less per report (USD 0.030 vs. 0.187). Both reached 100% step success rates; APA varied more over time. For a stable interface, RPA was superior.
Figures & tables
Figure 1: Macro process flowchart and business rules for report extraction
Figure 2: Technical flowchart of the RPA solution (Playwright)
Figure 3: Technical flowchart of the APA solution (browser-use and LangGraph)
True value
Download
Not download
Authorized
Exam collected (TP)
Exam not collected (FN)
Not authorized
Exam collected (FP)
Exam not collected (TN)
Table 1: Confusion matrix model adopted for the classification of the collected exams
RPA Download
RPA Not download
APA Download
APA Not download
Authorized
142 (TP)
0 (FN)
137 (TP)
5 (FN)
Not authorized
5 (FP)
309 (TN)
11 (FP)
303 (TN)
Table 2: Confusion matrices of the RPA and APA, summing the two executions (T + T+7)
Metric
RPA
APA
Accuracy
98.90%
96.49%
Precision
96.60%
92.57%
Recall
100%
96.48%
F1-score
98.27%
94.48%
Table 3: Classification metrics of exam collection (RPA and APA)
Metric
RPA
APA
Mean execution time per patient (s)
16.07 s
207.21 s
Cost per report (USD)
0.030
0.187
Table 4: Mean execution time per patient and cost per report
Step
RPA
APA
Login rate (%)
100%
100%
Identification/search rate (%)
100%
100%
Complete download rate (%)
100%
100%
Table 5: Success rate per workflow step
Metric
RPA
APA
Accuracy – variation T vs. T+7 (p.p.)
0.44
3.51
Precision – variation T vs. T+7 (p.p.)
1.31
4.26
Recall – variation T vs. T+7 (p.p.)
0.00
7.04
F1-score – variation T vs. T+7 (p.p.)
0.68
5.59
Table 6: Variation of the metrics between T and T+7 (temporal stability)