Research

As the national university, we champion and support innovative research that addresses the country’s most pressing challenges.

30 Apr 2025

Researchers propose a modified inelastic bouncing ball model that includes collision time between the ball and its container

The behavior of granular materials subjected to shaking or vibration remains a complex puzzling phenomenon. A reliable strategy in science...

Read More

25 Apr 2025

A method has been developed to determine the minimum aperture size that a digital micromirror device can accurately render

A digital micromirror device (DMD) is a programmable pixelated instrument that uses an array of tiny individually switchable mirrors as...

Read More

25 Apr 2025

China’s projects aim not only to compete with the US but also to bring about positive change

This research looks at how China is becoming more influential in the world through projects like the Belt and Road...

Read More

24 Apr 2025

Non-democratic states, even if they perform well in sports, receive less media attention than democratic countries

In this study, Panao and Gache delve into the fascinating world of sports and its connection to global politics. Essentially,...

Read More

15 Apr 2025

Survivors of the 1974 Battle of Jolo wish to forget the tragedy but their memories expose the recent struggles of Muslim Mindanao

Moving beyond the disinformation surrounding Filipino memory construction of martial law this study delves into the experiences of civilians during...

Read More

11 Apr 2025

This study of the largest fast food group in the Philippines acquiring its competition adds to the limited, but growing, inventory of business case studies

This case is about the acquisition by the largest quick service restaurant (QSR) group in the Philippines, Jollibee Foods Corporation...

Read More

25 Mar 2025

Tracing Darna’s roots in Filipino folk culture challenges the typically male-centered Western superhero genre

Power is one of the most distinguishing features of the superhero genre. In this regard, one of the most recognizable...

Read More

18 Mar 2025

UP Manila

The clustering of tuberculosis cases could be linked to the El Niño phenomenon

This study focused on tuberculosis (TB) cases in Region III of the Philippines for the years 2019, 2020, and 2021,...

Read More

17 Mar 2025

Perceived factors to teenage pregnancy such as technological influence influence the manner of delivering services

Teenage pregnancy remains to be a major concern in the health of Filipino adolescents despite the nationwide adoption of sexual...

Read More

07 Mar 2025

UP Open University

Research uncovers new information on the voice of the Philippine flat-headed frog found only in Palawan

This study describes the call of Barbourula busuangensis, a peculiar and elusive fully aquatic frog endemic to the Palawan archipelago of...

Read More

07 Mar 2025

UP Manila

High levels of body association lowers the risk of depression, anxiety and stress among Filipino emerging adults

Among Filipino emerging adults, prevalence rates of severe and extreme levels of depression, anxiety, and stress are relatively high. High...

Read More

07 Mar 2025

Research uncovers new information on the voice of the Philippine flat-headed frog found only in Palawan

This study describes the call of Barbourula busuangensis, a peculiar and elusive fully aquatic frog endemic to the Palawan archipelago...

Read More

Research

Large language models such as ChatGPT have been used in different fields of medical education. This study aimed to review the literature on the performance of ChatGPT in neurosurgery board examination-like questions compared to neurosurgery residents.

A literature search was performed following PRISMA guidelines, covering the time period from ChatGPT’s inception (November 2022) to October 25, 2024. Two reviewers screened for eligible studies, selecting those that utilized ChatGPT to answer neurosurgery board examination-like questions and compared the results with those of neurosurgery residents. Risk of bias was assessed using the JBI critical appraisal tool. Overall effect sizes and 95% confidence intervals were determined using a fixed-effects model with alpha at 0.05. After screening, six studies were selected for qualitative and quantitative analysis. The accuracy of ChatGPT ranged from 50.4 to 78.8%, compared to residents’ accuracy of 58.3 to 73.7%. Risk of bias was low in 4 out of 6 studies reviewed; the rest had moderate risk. There was an overall trend favoring neurosurgery residents versus ChatGPT (p < 0.00001), with high heterogeneity (I2 = 96). These findings were similar in the subgroup analysis of studies that used the Self-assessment in Neurosurgery (SANS) examination questions. However, on sensitivity analysis, the removal of the highest weighted study skewed the results toward better performance of ChatGPT.

Our meta-analysis showed that neurosurgery residents performed better than ChatGPT in answering neurosurgery board examination-like questions, although reviewed studies had high heterogeneity. Further improvement is necessary before it can become a useful and reliable supplementary tool in the delivery of neurosurgical education.

Authors: Edgar Dominic A. Bongco, Sean Kendrich N. Cua, Mary Angeline Luz U. Hernandez, Juan Silvestre G. Pascual and Kathleen Joy O. Khu (Division of Neurosurgery, Department of Neurosciences, College of Medicine and Philippine General Hospital, University of the Philippines Manila)

Read full article: https://link.springer.com/article/10.1007/s10143-024-03144-y

Photo by Viktor Duks from Pexels