| 1. |
- Guillen-Grima, Francisco, et al.
(författare)
-
Evaluating the Efficacy of ChatGPT in Navigating the Spanish Medical Residency Entrance Examination (MIR): Promising Horizons for AI in Clinical Medicine
- 2023
-
Ingår i: CLINICS AND PRACTICE. - 2039-7275 .- 2039-7283. ; 13:6, s. 1460-1487
-
Tidskriftsartikel (refereegranskat)abstract
- The rapid progress in artificial intelligence, machine learning, and natural language processing has led to increasingly sophisticated large language models (LLMs) for use in healthcare. This study assesses the performance of two LLMs, the GPT-3.5 and GPT-4 models, in passing the MIR medical examination for access to medical specialist training in Spain. Our objectives included gauging the model's overall performance, analyzing discrepancies across different medical specialties, discerning between theoretical and practical questions, estimating error proportions, and assessing the hypothetical severity of errors committed by a physician. Material and methods: We studied the 2022 Spanish MIR examination results after excluding those questions requiring image evaluations or having acknowledged errors. The remaining 182 questions were presented to the LLM GPT-4 and GPT-3.5 in Spanish and English. Logistic regression models analyzed the relationships between question length, sequence, and performance. We also analyzed the 23 questions with images, using GPT-4's new image analysis capability. Results: GPT-4 outperformed GPT-3.5, scoring 86.81% in Spanish (p < 0.001). English translations had a slightly enhanced performance. GPT-4 scored 26.1% of the questions with images in English. The results were worse when the questions were in Spanish, 13.0%, although the differences were not statistically significant (p = 0.250). Among medical specialties, GPT-4 achieved a 100% correct response rate in several areas, and the Pharmacology, Critical Care, and Infectious Diseases specialties showed lower performance. The error analysis revealed that while a 13.2% error rate existed, the gravest categories, such as "error requiring intervention to sustain life" and "error resulting in death", had a 0% rate. Conclusions: GPT-4 performs robustly on the Spanish MIR examination, with varying capabilities to discriminate knowledge across specialties. While the model's high success rate is commendable, understanding the error severity is critical, especially when considering AI's potential role in real-world medical practice and its implications for patient safety.
|
|
| 2. |
- Onambele, Luc, et al.
(författare)
-
Trends, Projections, and Regional Disparities of Maternal Mortality in Africa (1990-2030): An ARIMA Forecasting Approach
- 2023
-
Ingår i: EPIDEMIOLOGIA. - 2673-3986. ; 4:3, s. 322-351
-
Tidskriftsartikel (refereegranskat)abstract
- With the United Nations Sustainable Development Goals (SDG) (2015-2030) focused on the reduction in maternal mortality, monitoring and forecasting maternal mortality rates (MMRs) in regions like Africa is crucial for health strategy planning by policymakers, international organizations, and NGOs. We collected maternal mortality rates per 100,000 births from the World Bank database between 1990 and 2015. Joinpoint regression was applied to assess trends, and the autoregressive integrated moving average (ARIMA) model was used on 1990-2015 data to forecast the MMRs for the next 15 years. We also used the Holt method and the machine-learning Prophet Forecasting Model. The study found a decline in MMRs in Africa with an average annual percentage change (APC) of -2.6% (95% CI -2.7; -2.5). North Africa reported the lowest MMR, while East Africa experienced the sharpest decline. The region-specific ARIMA models predict that the maternal mortality rate (MMR) in 2030 will vary across regions, ranging from 161 deaths per 100,000 births in North Africa to 302 deaths per 100,000 births in Central Africa, averaging 182 per 100,000 births for the continent. Despite the observed decreasing trend in maternal mortality rate (MMR), the MMR in Africa remains relatively high. The results indicate that MMR in Africa will continue to decrease by 2030. However, no region of Africa will likely reach the SDG target.
|
|
