Background Ensuring medication safety requires accurate identification of antibiotic packaging, especially within pharmacy automation and dispensing systems. Advanced imaging and machine learning offer novel avenues for physical package recognition. Objective To investigate visual and textual features of antibiotic packages and evaluate their relationship with identification outcomes using unsupervised learning and efficiency-based analysis. Methods Thirty-six antibiotic formulations from Thailand (2016–2021) were analyzed using binary imaging, entropy metrics, packaging area ratio (PAR), and optical character recognition (OCR). K-means clustering was applied to segment package groups, and data envelopment analysis (DEA) was used to assess relative efficiency without assuming predefined functional relationships between inputs and outputs. Results Nine distinct image clusters were identified. Packages with mid-range entropy (7.1–7.5) and PAR (1.2–1.45) were associated with higher identification consistency. OCR text confidence influenced identification outcomes. DEA identified clusters with relatively efficient input–output configurations. Conclusion Integrating image-derived metrics and OCR-based features supports automated antibiotic package identification. This framework provides a structured approach for evaluating packaging characteristics in pharmacy workflows.

Background.: Tacrolimus (TAC) trough-level variability has been associated with patient outcomes and renal graft survival. However, its relationship with posttransplant diabetes mellitus (PTDM) remains unclear. This study aims to evaluate the association between the coefficient of variation (CV) of TAC (TAC-CV) and the incidence of PTDM within the first year after kidney transplantation (KT). Methods.: A multicenter retrospective study was conducted on 516 Thai KT patients who received TAC-based immunosuppressive regimens from 2011 to 2020, with a 1-y post-KT follow-up period. TAC-CV was calculated for the 0–12 mo post-KT period, and optimal cutoff values were determined using receiver operating characteristic analysis. Results.: Of the 516 patients, 208 (40.31%) developed PTDM, whereas 308 (59.69%) did not during the first year post-KT. Significant associations were found between TAC-CV and PTDM throughout the study period ( P < 0.001). The optimal CV cutoff values were identified as 36% (at 0–3 and 0–6 mo), 23% (at 6–12 mo), and 33% (at 0–12 mo) post-KT. High TAC-CV was strongly associated with an increased risk of PTDM during the first year post-KT. Conclusions.: These findings suggest that TAC-CV may serve as a valuable marker for identifying patients at high risk of PTDM and may aid in its prevention and effective management in KT recipients.

Background Ensuring medication safety requires accurate identification of antibiotic packaging, especially within pharmacy automation and dispensing systems. Advanced imaging and machine learning offer novel avenues for physical package recognition. Objective To investigate visual and textual features of antibiotic packages and evaluate their relationship with identification outcomes using unsupervised learning and efficiency-based analysis. Methods Thirty-six antibiotic formulations from Thailand (2016–2021) were analyzed using binary imaging, entropy metrics, packaging area ratio (PAR), and optical character recognition (OCR). K-means clustering was applied to segment package groups, and data envelopment analysis (DEA) was used to assess relative efficiency without assuming predefined functional relationships between inputs and outputs. Results Nine distinct image clusters were identified. Packages with mid-range entropy (7.1–7.5) and PAR (1.2–1.45) were associated with higher identification consistency. OCR text confidence influenced identification outcomes. DEA identified clusters with relatively efficient input–output configurations. Conclusion Integrating image-derived metrics and OCR-based features supports automated antibiotic package identification. This framework provides a structured approach for evaluating packaging characteristics in pharmacy workflows.

Background Ensuring medication safety requires accurate identification of antibiotic packaging, especially within pharmacy automation and dispensing systems. Advanced imaging and machine learning offer novel avenues for physical package recognition. Objective To investigate visual and textual features of antibiotic packages and evaluate their relationship with identification outcomes using unsupervised learning and efficiency-based analysis. Methods Thirty-six antibiotic formulations from Thailand (2016–2021) were analyzed using binary imaging, entropy metrics, packaging area ratio (PAR), and optical character recognition (OCR). K-means clustering was applied to segment package groups, and data envelopment analysis (DEA) was used to assess relative efficiency without assuming predefined functional relationships between inputs and outputs. Results Nine distinct image clusters were identified. Packages with mid-range entropy (7.1–7.5) and PAR (1.2–1.45) were associated with higher identification consistency. OCR text confidence influenced identification outcomes. DEA identified clusters with relatively efficient input–output configurations. Conclusion Integrating image-derived metrics and OCR-based features supports automated antibiotic package identification. This framework provides a structured approach for evaluating packaging characteristics in pharmacy workflows.

Background Ensuring medication safety requires accurate identification of antibiotic packaging, especially within pharmacy automation and dispensing systems. Advanced imaging and machine learning offer novel avenues for physical package recognition. Objective To investigate visual and textual features of antibiotic packages and evaluate their relationship with identification outcomes using unsupervised learning and efficiency-based analysis. Methods Thirty-six antibiotic formulations from Thailand (2016–2021) were analyzed using binary imaging, entropy metrics, packaging area ratio (PAR), and optical character recognition (OCR). K-means clustering was applied to segment package groups, and data envelopment analysis (DEA) was used to assess relative efficiency without assuming predefined functional relationships between inputs and outputs. Results Nine distinct image clusters were identified. Packages with mid-range entropy (7.1–7.5) and PAR (1.2–1.45) were associated with higher identification consistency. OCR text confidence influenced identification outcomes. DEA identified clusters with relatively efficient input–output configurations. Conclusion Integrating image-derived metrics and OCR-based features supports automated antibiotic package identification. This framework provides a structured approach for evaluating packaging characteristics in pharmacy workflows.

Background Ensuring medication safety requires accurate identification of antibiotic packaging, especially within pharmacy automation and dispensing systems. Advanced imaging and machine learning offer novel avenues for physical package recognition. Objective To investigate visual and textual features of antibiotic packages and evaluate their relationship with identification outcomes using unsupervised learning and efficiency-based analysis. Methods Thirty-six antibiotic formulations from Thailand (2016–2021) were analyzed using binary imaging, entropy metrics, packaging area ratio (PAR), and optical character recognition (OCR). K-means clustering was applied to segment package groups, and data envelopment analysis (DEA) was used to assess relative efficiency without assuming predefined functional relationships between inputs and outputs. Results Nine distinct image clusters were identified. Packages with mid-range entropy (7.1–7.5) and PAR (1.2–1.45) were associated with higher identification consistency. OCR text confidence influenced identification outcomes. DEA identified clusters with relatively efficient input–output configurations. Conclusion Integrating image-derived metrics and OCR-based features supports automated antibiotic package identification. This framework provides a structured approach for evaluating packaging characteristics in pharmacy workflows.