Ryan Hata

Ryan Hata

Auto-generated profile, based on publicly available information

Ryan Hata

Department of Emergency Medicine, Indiana University School of Medicine, Indianapolis, IN, United States

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 December 2023 in Public Health
Verified
Journal Article
Open access
DTD. Tin
D. Tin
LCL. Cheng
L. Cheng
DLD. Le
D. Le
RHR. Hata
R. Hata
GCGregory Ciottone
Gregory Ciottone
The frequency, intensity, and geographical reach of natural disasters, fueled in part by factors such as climate change, population growth, and urbanization, have undeniably been escalating concerns around the world. This is a retrospective analysis of natural disasters recorded in the Emergency Events Database from 1995 to 2022. Between 1995 and 2022, 11,360 natural disasters occurred, with a mean of 398 per year. Asia experienced the most disasters (4390) and the highest number of casualties (918,198). Hydrological disasters were the most common subgroup (4969), while geophysical disasters led in terms of deaths (770,644). Biological disasters caused the most injuries (2544), particularly in Africa. Recognizing the historical impacts of the various subtypes of natural disasters may help different regions better risk analyze and mitigate the unique risks associated with such events.

30 September 2024 in Journal of Medical Internet Research
Verified
Journal Article
Open access
JFJeffrey Micheal Franc
Jeffrey Micheal Franc
Attila HertelendyAttila Hertelendy
Attila Hertelendy
LCLenard Cheng
Lenard Cheng
RHRyan Hata
Ryan Hata
MVManuela Verde
Manuela Verde
Background: The release of ChatGPT (OpenAI) in November 2022 drastically reduced the barrier to using artificial intelligence by allowing a simple web-based text interface to a large language model (LLM). One use case where ChatGPT could be useful is in triaging patients at the site of a disaster using the Simple Triage and Rapid Treatment (START) protocol. However, LLMs experience several common errors including hallucinations (also called confabulations) and prompt dependency. Objective: This study addresses the research problem: “Can ChatGPT adequately triage simulated disaster patients using the START protocol?” by measuring three outcomes: repeatability, reproducibility, and accuracy. Methods: Nine prompts were developed by 5 disaster medicine physicians. A Python script queried ChatGPT Version 4 for each prompt combined with 391 validated simulated patient vignettes. Ten repetitions of each combination were performed for a total of 35,190 simulated triages. A reference standard START triage code for each simulated case was assigned by 2 disaster medicine specialists (JMF and MV), with a third specialist (LC) added if the first two did not agree. Results were evaluated using a gage repeatability and reproducibility study (gage R and R). Repeatability was defined as variation due to repeated use of the same prompt. Reproducibility was defined as variation due to the use of different prompts on the same patient vignette. Accuracy was defined as agreement with the reference standard. Results: Although 35,102 (99.7%) queries returned a valid START score, there was considerable variability. Repeatability (use of the same prompt repeatedly) was 14% of the overall variation. Reproducibility (use of different prompts) was 4.1% of the overall variation. The accuracy of ChatGPT for START was 63.9% with a 32.9% overtriage rate and a 3.1% undertriage rate. Accuracy varied by prompt with a maximum of 71.8% and a minimum of 46.7%. Conclusions: This study indicates that ChatGPT version 4 is insufficient to triage simulated disaster patients via the START protocol. It demonstrated suboptimal repeatability and reproducibility. The overall accuracy of triage was only 63.9%. Health care professionals are advised to exercise caution while using commercial LLMs for vital medical determinations, given that these tools may commonly produce inaccurate data, colloquially referred to as hallucinations or confabulations. Artificial intelligence–guided tools should undergo rigorous statistical evaluation—using methods such as gage R and R—before implementation into clinical settings.

5 April 2023 in The American Journal of Emergency Medicine
Verified
Journal Article
Closed access
DTDerrick Tin
Derrick Tin
RHRyan Hata
Ryan Hata
FGFredrik Granholm
Fredrik Granholm
RCRobert G. Ciottone
Robert G. Ciottone
RSRichard Staynings
Richard Staynings
GCGregory Ciottone
Gregory Ciottone

30 January 2023 in Prehospital and Disaster Medicine
Verified
Journal Article
Closed access
PDF file
RHRyan Hata
Ryan Hata
AHAlexander Hart
Alexander Hart
Attila HertelendyAttila Hertelendy
Attila Hertelendy
DTDerrick Tin
Derrick Tin
CTCara Taubman
Cara Taubman
GCGregory R. Ciottone
Gregory R. Ciottone
Background: Sub-Saharan Africa (SSA) has become a hotspot for global terrorism, with nearly 50% of global terror-related deaths occurring in SSA in 2021. With a large population and complex geopolitical and social climate, terrorist activity further burdens an already strained medical system. This study provides a retrospective descriptive analysis of terrorist-related activity in SSA from 1970-2020. Methods: A retrospective analysis of the Global Terrorism Database (GTD) was performed for the region of SSA from 1970-2020. Data were filtered using the internal database search function for all events in the following countries: Angola, Benin, Botswana, Burkina Faso, Burundi, Cameroon, Central African Republic, Chad, Comoros, the Democratic Republic of the Congo, Djibouti, Equatorial Guinea, Eritrea, Ethiopia, Gabon, Gambia, Ghana, Guinea, Guinea-Bissau, Ivory Coast, Kenya, Lesotho, Liberia, Madagascar, Malawi, Mali, Mauritania, Mozambique, Namibia, Niger, Nigeria, People’s Republic of the Congo, Republic of the Congo, Rhodesia, Rwanda, Senegal, Seychelles, Sierra Leone, Somalia, South Africa, South Sudan, Sudan, Swaziland, Tanzania, Togo, Uganda, Zaire, Zambia, and Zimbabwe. Number of attacks, deaths, and injuries, as well as primary weapons types, country where attacks occurred, and primary target types, were collated and analyzed. Results: A total 19,320 attacks were recorded, resulting in 77,565 deaths and 52,986 injuries. Firearms were the most frequent weapons used (8,745), followed by explosives (6,031), unknown (2,615), and incendiary (1,246), with all others making up the remainder (683.) Private citizens and property were the most frequently targeted entities (8,031), followed by general government facilities (2,582), police (1,854), business (1,446), military (805), diplomatic government facilities (741), and religious figures/institution (678), with all other targets making up the remainder (3,183). Conclusion: The majority of deaths from terrorism in SSA are the result of firearm attacks and explosions. Nigeria, Somalia, South Africa, The Democratic Republic of the Congo, and Sudan have had the largest number of attacks since 1970, and Nigeria has the largest number of people killed and injured. The health implications of terrorist attacks are often compounded by violence and pose unique challenges to governments, populations, and aid organizations. By understanding the impact and scope of terrorist activity in SSA, Counter-Terrorism Medicine (CTM) initiatives can be employed to improve health care outcomes.


17 July 2023 in Public Health
Verified
Journal Article
Closed access
DTD. Tin
D. Tin
LCL. Cheng
L. Cheng
RHR. Hata
R. Hata
HSH. Shin
H. Shin
GCGregory Ciottone
Gregory Ciottone