Comparative analysis of ChatGPT and Bard in answering pathology examination questions requiring image interpretation

OBJECTIVES

To evaluate the accuracy of ChatGPT and Bard in answering pathology examination questions requiring image interpretation.

METHODS

The study evaluated ChatGPT-4 and Bard's performance using 86 multiple-choice questions, with 17 (19.8%) focusing on general pathology and 69 (80.2%) on systemic pathology. Of these, 62 (72.1%) included microscopic images, and 57 (66.3%) were first-order questions focusing on diagnosing the disease. The authors presented these artificial intelligence (AI) tools with questions, both with and without clinical contexts, and assessed their answers against a reference standard set by pathologists.

RESULTS

ChatGPT-4 achieved a 100% (n = 86) accuracy rate in questions with clinical context, surpassing Bard's 87.2% (n = 75). Without context, the accuracy of both AI tools declined significantly, with ChatGPT-4 at 52.3% (n = 45) and Bard at 38.4% (n = 33). ChatGPT-4 consistently outperformed Bard across various categories, particularly in systemic pathology and first-order questions. A notable issue identified was Bard's tendency to "hallucinate" or provide plausible but incorrect answers, especially without clinical context.

CONCLUSIONS

This study demonstrated the potential of ChatGPT and Bard in pathology education, stressing the importance of clinical context for accurate AI interpretations of pathology images. It underlined the need for careful AI integration in medical education.

Accuracy of GPT-4 in histopathological image detection and classification of colorectal adenomas

AIMS

To evaluate the accuracy of Chat Generative Pre-trained Transformer (ChatGPT) powered by GPT-4 in histopathological image detection and classification of colorectal adenomas using the diagnostic consensus provided by pathologists as a reference standard.

METHODS

A study was conducted with 100 colorectal polyp photomicrographs, comprising an equal number of adenomas and non-adenomas, classified by two pathologists. These images were analysed by classic GPT-4 for 1 time in October 2023 and custom GPT-4 for 20 times in December 2023. GPT-4's responses were compared against the reference standard through statistical measures to evaluate its proficiency in histopathological diagnosis, with the pathologists further assessing the model's descriptive accuracy.

RESULTS

GPT-4 demonstrated a median sensitivity of 74% and specificity of 36% for adenoma detection. The median accuracy of polyp classification varied, ranging from 16% for non-specific changes to 36% for tubular adenomas. Its diagnostic consistency, indicated by low kappa values ranging from 0.06 to 0.11, suggested only poor to slight agreement. All of the microscopic descriptions corresponded with their diagnoses. GPT-4 also commented about the limitations in its diagnoses (eg, slide diagnosis best done by pathologists, the inadequacy of single-image diagnostic conclusions, the need for clinical data and a higher magnification view).

CONCLUSIONS

GPT-4 showed high sensitivity but low specificity in detecting adenomas and varied accuracy for polyp classification. However, its diagnostic consistency was low. This artificial intelligence tool acknowledged its diagnostic limitations, emphasising the need for a pathologist's expertise and additional clinical context.

Postinflammatory and rebound hyperpigmentation as a complication after treatment efficacy of telangiectatic melasma with 585 nanometers Q-switched Nd: YAG laser and 4% hydroquinone cream in skin phototypes III-V

BACKGROUND

The potential efficacy of vascular component-targeted laser has been evaluated for the treatment of melasma, which commonly found with the co-existence of telangiectasia.

AIMS

To evaluate the treatment efficacy and safety of 585-nm QSNYL and 4% HQ cream combination vs 4% HQ cream alone for telangiectatic melasma in the skin phototypes III-V.

PATIENTS/METHODS

Twenty-one Thai female patients with telangiectatic melasma and Fitzpatrick skin phototypes (FPTs) III-V were randomly treated with the 585-nm QSNYL on one side of the face for five sessions at 2-week intervals. All patients were assigned to apply HQ cream daily at night on both sides of the face for 10 weeks and a broad-spectrum sunscreen regularly throughout the study. The treatment efficacy and safety were evaluated using the Modified Melasma Area and Severity Index (mMASI), biometric evaluation, patient assessment, and adverse effects.

RESULTS

The combination-treated side yielded more significant improvement of mMASI than the topical-treated side at weeks 2, 4, and 8, respectively. However, 19% of the patients developed postinflammatory hyperpigmentation (PIH) on the laser-treated side, especially in FPTs IV-V and rebound hyperpigmentation. There was a significant improvement of hemoglobin and melanin index, but without statistical difference between the two treatment groups.

CONCLUSIONS

The combination of 585-nm QSNYL and HQ treatment yields treatment efficacy and skin rejuvenation effects for telangiectatic melasma. Nonetheless, a high incidence of PIH and rebound hyperpigmentation is adversely developed in dark FPT. Thus, this laser treatment should be cautiously applied in those with dark FPTs IV-V to avoid laser-induced pigment alteration.

Intradermal Tranexamic Acid Injection for the Treatment of Melasma: A Pilot Study with 48-week Follow-up

BACKGROUND: Despite being an effective treatment for melasma, there have been limited reports on the long-term efficacy of intradermal tranexamic acid (TA) injection. OBJECTIVE: This study sought to evaluate the 48-week efficacy of a 4mg/mL intradermal TA injection for the treatment of melasma. METHODS: Five female patients with melasma participated in the 48-week follow-up after receiving 4-mg/mL intradermal TA injections on the face every two weeks for seven sessions and a sunscreen prescription. Assessments were performed at baseline and Weeks 4, 8, 12, 16, and 48 using the modified Melasma Area Severity Index (mMASI) score, melanin index, and patient satisfaction score. Safety and adverse effects were also evaluated. RESULTS: The mean (standard deviation) age of patients was 53.6 (8.14) years and Fitzpatrick Skin Type IV (60%) and Fitzpatrick Skin Type V (40%) were observed. The mean (standard deviation) duration of melasma was 7.6 (2.51) years and 60 percent of participants reported a family history of melasma. There was a significant decrease in mMASI score and melanin index at 16 weeks, without a statistically significant improvement of mMASI score at 48 weeks. Melasma recurrence was observed in 60 percent of the participants, with higher mMASI scores recorded, but the severity remained less than at baseline. The patient satisfaction score was lower from Week 16 to Week 48. Interestingly, a statistically significant decrease in the melanin index was observed up to Week 48, with no serious adverse effects. CONCLUSION: The 4-mg/mL intradermal TA injection yields significant efficacy at Week 16; however, melasma recurrence occurred during the 48-week follow-up. In addition to tranexamic acid injections, maintenance therapy and sun protection should be considered for patients with melasma.