Search

Introduction: Artificial intelligence (AI) is revolutionizing medical workflows, with self-learning systems like ChatGPT showing promise in therapy recommendations. Our study evaluated ChatGPT's performance in suggesting treatments for 30 breast cancer cases. AI's role in healthcare is expanding, particularly with tools like ChatGPT becoming accessible. However, understanding its limitations is vital for safe implementation. Material and Methods: We used 30 breast cancer cases from our medical board, assessing ChatGPT's suggestions. The input was standardized, incorporating relevant patient details and treatment options. ChatGPT's output was evaluated by oncologists based on a given questionnaire. Results: Treatment recommendations by ChatGPT were overall rated sufficient with minor limitations by the oncologists. The HER2 treatment category was the best-rated therapy option, with the most accurate recommendations. Primary cases received more accurate recommendations, especially regarding chemotherapy. Conclusions: While ChatGPT demonstrated potential, difficulties were shown in intricate cases and postoperative scenarios. Challenges arose in offering chronological treatment sequences and partially lacked precision. Refining inputs, addressing ethical intricacies, and ensuring chronological treatment suggestions are essential. Ongoing research is vital to improving AI's accuracy, balancing AI-driven suggestions with expert insights and ensuring safe and reliable AI integration into patient care. [ABSTRACT FROM AUTHOR]

Simple Summary: Precancerous cervical lesions, especially among young women, are frequently cleared by the immune system. Consequently, immediate surgical treatment is not mandatory and patients are monitored closely for up to 24 months. To avoid anxiety and to allow for a more individualized treatment, molecular markers that could predict the outcome of the lesion would be desirable. Women with a high risk of progression could be identified earlier. In this study, we could show that the majority of lesions that were negative for the cancer-associated methylation markers comprising the test GynTect® have regressed over time. Cervical intraepithelial neoplasia (CIN) grade 2/3 has a high spontaneous regression rate, especially among women ≤29 years of age. To reduce overtreatment, reliable prognostic biomarkers would be helpful. The main aim of this study was to analyze the negative predictive value of the methylation marker panel GynTect® for lesion regression. In this prospective, multicenter, longitudinal observational proof-of-concept study, women aged ≤29 years with histologically confirmed CIN2 (n = 24) or CIN3 (n = 36) were closely monitored without treatment for up to 24 or 12 months, respectively. The outcome was either regression, persistence, or progression of the lesion. For each patient, a single baseline sample (V0) for cytology, hrHPV detection and methylation analysis was taken. In a primary analysis, the negative predictive value (NPV) of a GynTect®-negative test result at V0 for regression was determined. We tested the null hypothesis NPV ≤ 70% against the alternative hypothesis NPV ≥ 90%. Twelve of the eighteen GynTect®-negative CIN2 patients showed regression (NPV = 67%, 90% CI 44–85%, p = 0.53). Of the 27 GynTect®-negative CIN3 lesions, 15 regressed (NPV = 56%, 90% CI 38–72%, p = 0.92). Although the majority of GynTect®-negative lesions regressed, the postulated NPV of ≥90% was not observed. Thus, the clinical relevance for an implementation of the GynTect® assay for patients undergoing watchful waiting remains questionable. Further studies with longer observation periods should be undertaken. [ABSTRACT FROM AUTHOR]

Pregnant women diagnosed with CIN3 have high regression rates after delivery. Biomarkers are needed to only identify pregnant women with progressive CIN requiring treatment to reduce overreferral and overtreatment. In our study we evaluated the performance of the FAM19A4/miR124‐2 methylation test for molecular triage on FFPE samples of CIN3+‐diagnosed pregnant women with known clinical course over time as well in a cross‐sectional setting. In this German multicenter retrospective study biopsy material was collected from pregnant women diagnosed with cervical cancer (n = 16), with CIN3 that progressed to cancer during pregnancy (n = 7), with CIN3 that regressed to CIN1 or less within 6 months after delivery (n = 41), without CIN (n = 16), CIN3 covering 3‐4 quadrants (n = 14) and randomly selected CIN3 (n = 41). FAM19A4/miR124‐2 methylation analysis was performed blinded on first diagnosis. All pregnant women with cervical cancer and with CIN3 progressing to cancer tested positive for FAM19A4/miR124‐2 methylation (100%, 22/22). In the regressing CIN3 group 47.5% and in the group without CIN 21.6% tested methylation positive. High‐volume CIN3 and random selected CIN3 were methylation‐positive in 91.7% and 82.1%, respectively. Methylation levels were significantly higher in progressive CIN3 and cancer compared to the controls (P <.0005). The likelihood ratio of a negative methylation test (LR−) for progressive CIN3+ was 0 (95% CI: 0‐0.208). A negative FAM19A4/miR124‐2 methylation test can rule out progressive CIN disease in pregnant women diagnosed with CIN3. This can help the clinician by managing these pregnant women with conservative follow‐up until after delivery. [ABSTRACT FROM AUTHOR]

Background/Aims: Adults with congenital heart disease exhibit a 3-fold higher mortality in the presence of chronic kidney disease, hence assessment of renal function is crucial in this patient population. Formulas for the estimation of glomerular filtration rate (GFR) have not been evaluated in this patient population. Therefore, this study compares different markers and equations for the estimation of renal function in adults with congenital heart disease. Methods: Renal function was assessed in 102 patients using the Modification of Diet in Renal Disease (MDRD) equation, the simplified MDRD equation, the Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI) equation and the Cockcroft-Gault formula. Additionally, symmetrical dimethylarginine (SDMA) was measured. Those parameters were compared to cystatin C-derived GFR using the Larsson equation. Results: GFR estimates using the original MDRD (r = 0.465, p < 0.001) and the CKD-EPI equation (r = 0.462, p < 0.001) showed a similar strong correlation with the cystatin C-based eGFR equation, while eGFR using the simplified MDRD equation showed a slightly weaker correlation (r = 0.439, p < 0.001). The Cockcroft-Gault formula showed no correlation at all to the cystatin C-based eGFR (r = 0.144, p = 0.17). The strongest correlation was observed for SDMA and cystatin C-based eGFR (r = -0.552, p < 0.001). Conclusion: GFR in adults with congenital heart disease should be estimated using the original MDRD or the CKD-EPI formula. SDMA seems to be a promising marker of renal function for this patient group. Copyright © 2010 S. Karger AG, Basel [ABSTRACT FROM AUTHOR]

Aim: There is currently no protocol for classifying patients with HPV persistence and preoperative stenosis of the cervical canal. This has a significant impact on cytology results, colposcopy results and the possibility of obtaining reliable cervical histology outcomes. Our analysis clearly shows that colposcopy and cytology underestimate the histological results in patients with limited visibility due to the presence of a type 3 transformation zone (TZ). Our analysis revealed a significant discrepancy between the colposcopy and cytology results and the histological outcomes. Insufficient colposcopy led to the underdiagnosis of dysplastic lesions in patients with a type 3 TZ and cervical stenosis. In the case of repeated cytological abnormalities and inadequate colposcopy examination, it is crucial to perform a diagnostic conization to exclude high-grade dysplastic changes and cervical carcinoma., Methods: We conducted a retrospective analysis of 1,021 conizations performed in tertiary care hospital in Wolfsburg, Germany between 2014 and 2020. Of these surgical procedures, 89 were diagnostic conizations. In our analysis, we defined diagnostic conization as a procedure performed when there is HPV persistence and repeated cytologic abnormalities in combination with a type 3 TZ, and when it is not possible to retrieve a relevant cervical histology sample., Results: In this period, 8.7% of all conizations were diagnostic excisions. We found histological abnormalities in 48 of 89 patients (53.9%). The histological examination of the excised cone revealed high-grade cervical intraepithelial neoplasia (CIN/HSIL) in 9 patients (10.1%) and CIN 2+ (HSIL) in 23 out of the 89 patients (25.8%). Two cases of early-stage cervical carcinoma (FIGO IA1 and FIGO IA2) were confirmed (2.3%)., Conclusion: Patients with cervical stenosis, high-risk HPV persistence and repeated cytological abnormalities are at high risk of undetected high-grade cervical dysplasia. Histologic confirmation must be ensured in this patient consultation and this can be achieved by performing diagnostic excisions., (© 2024. The Author(s).)