Evaluating the performance of ChatGPT in clinical pharmacy: A comparative study of ChatGPT and clinical pharmacists

AIMS

To evaluate the performance of chat generative pretrained transformer (ChatGPT) in key domains of clinical pharmacy practice, including prescription review, patient medication education, adverse drug reaction (ADR) recognition, ADR causality assessment and drug counselling.

METHODS

Questions and clinical pharmacist's answers were collected from real clinical cases and clinical pharmacist competency assessment. ChatGPT's responses were generated by inputting the same question into the 'New Chat' box of ChatGPT Mar 23 Version. Five licensed clinical pharmacists independently rated these answers on a scale of 0 (Completely incorrect) to 10 (Completely correct). The mean scores of ChatGPT and clinical pharmacists were compared using a paired 2-tailed Student's t-test. The text content of the answers was also descriptively summarized together.

RESULTS

The quantitative results indicated that ChatGPT was excellent in drug counselling (ChatGPT: 8.77 vs. clinical pharmacist: 9.50, P = .0791) and weak in prescription review (5.23 vs. 9.90, P = .0089), patient medication education (6.20 vs. 9.07, P = .0032), ADR recognition (5.07 vs. 9.70, P = .0483) and ADR causality assessment (4.03 vs. 9.73, P = .023). The capabilities and limitations of ChatGPT in clinical pharmacy practice were summarized based on the completeness and accuracy of the answers. ChatGPT revealed robust retrieval, information integration and dialogue capabilities. It lacked medicine-specific datasets as well as the ability for handling advanced reasoning and complex instructions.

CONCLUSIONS

While ChatGPT holds promise in clinical pharmacy practice as a supplementary tool, the ability of ChatGPT to handle complex problems needs further improvement and refinement.

Effects of β-blockers on all-cause mortality in patients with diabetes and coronary heart disease: A systematic review and meta-analysis

Beta-blockers have been considered as an effective treatment in secondary prevention of coronary heart disease (CHD). However, there is still disputed whether β-blockers can increase all-cause mortality in patients with coronary heart disease and diabetes mellitus (DM). Here, our systematic review and meta-analysis is aiming to assess the effects of β-blockers on all-cause mortality in patients with coronary heart disease and diabetes mellitus. Four databases (PubMed, Embase, Cochrane Library and Web of Science) and other sources were searched to collect randomized controlled trials (RCTs) and cohort studies related to the treatment of β-blockers for coronary heart disease and diabetes mellitus patients. We further evaluated quality of evidence using the grading of recommendations assessment, development, and evaluation (GRADE) approach. Finally, a total of 16,188 records were identified, and four randomized controlled trials and six cohort studies (206,490 patients) were included. Random effects analysis revealed that β-blockers combined with routine treatment (RT) significantly decreased all-cause mortality in patients with coronary heart disease and diabetes mellitus compared with RT in control group (RR 0.59, 95% CI 0.47 to 0.75; p < 0.000 01; I² = 72%). Subgroup analysis of all-cause mortality by the subtype of diabetes mellitus and definite MI patients (RR 0.54, 95% CI 0.45 to 0.65, p < 0.000 01, I² = 29%) and the subtype of randomized controlled trials (RR 0.49, 95% CI 0.32 to 0.76, p = 0.001, I² = 0%) indicated a relatively small heterogeneity and stable results. β-blockers application significantly reduced cardiovascular death as well (RR 0.56, 95% CI 0.42 to 0.74; p < 0.000 1; I² = 0%). Our meta-analysis provided critical evidence of β-blockers treatment for patients with coronary heart disease (especially MI type) and diabetes mellitus, and discussed the advantages and potential metabolic risks for the clinical use of β-blockers. This study suggested that β-blockers application may improve all-cause mortality and cardiovascular death in coronary heart disease (especially MI type) and diabetes mellitus patients. However, given a small number of included studies, the aforementioned conclusion should be confirmed in a multi-center, large-scale, and strictly designed trial.