Empowering inclusivity: improving readability of living kidney donation information with ChatGPT
BackgroundAddressing disparities in living kidney donation requires making information accessible across literacy levels, especially important given that the average American adult reads at an 8th-grade level. This study evaluated the effectiveness of ChatGPT, an advanced AI language model, in simpl...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-04-01
|
| Series: | Frontiers in Digital Health |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fdgth.2024.1366967/full |
| _version_ | 1797215891031588864 |
|---|---|
| author | Oscar A. Garcia Valencia Charat Thongprayoon Jing Miao Supawadee Suppadungsuk Supawadee Suppadungsuk Pajaree Krisanapan Pajaree Krisanapan Pajaree Krisanapan Iasmina M. Craici Caroline C. Jadlowiec Shennen A. Mao Michael A. Mao Napat Leeaphorn Pooja Budhiraja Wisit Cheungpasitporn |
| author_facet | Oscar A. Garcia Valencia Charat Thongprayoon Jing Miao Supawadee Suppadungsuk Supawadee Suppadungsuk Pajaree Krisanapan Pajaree Krisanapan Pajaree Krisanapan Iasmina M. Craici Caroline C. Jadlowiec Shennen A. Mao Michael A. Mao Napat Leeaphorn Pooja Budhiraja Wisit Cheungpasitporn |
| author_sort | Oscar A. Garcia Valencia |
| collection | DOAJ |
| description | BackgroundAddressing disparities in living kidney donation requires making information accessible across literacy levels, especially important given that the average American adult reads at an 8th-grade level. This study evaluated the effectiveness of ChatGPT, an advanced AI language model, in simplifying living kidney donation information to an 8th-grade reading level or below.MethodsWe used ChatGPT versions 3.5 and 4.0 to modify 27 questions and answers from Donate Life America, a key resource on living kidney donation. We measured the readability of both original and modified texts using the Flesch-Kincaid formula. A paired t-test was conducted to assess changes in readability levels, and a statistical comparison between the two ChatGPT versions was performed.ResultsOriginally, the FAQs had an average reading level of 9.6 ± 1.9. Post-modification, ChatGPT 3.5 achieved an average readability level of 7.72 ± 1.85, while ChatGPT 4.0 reached 4.30 ± 1.71, both with a p-value <0.001 indicating significant reduction. ChatGPT 3.5 made 59.26% of answers readable below 8th-grade level, whereas ChatGPT 4.0 did so for 96.30% of the texts. The grade level range for modified answers was 3.4–11.3 for ChatGPT 3.5 and 1–8.1 for ChatGPT 4.0.ConclusionBoth ChatGPT 3.5 and 4.0 effectively lowered the readability grade levels of complex medical information, with ChatGPT 4.0 being more effective. This suggests ChatGPT's potential role in promoting diversity and equity in living kidney donation, indicating scope for further refinement in making medical information more accessible. |
| first_indexed | 2024-04-24T11:37:16Z |
| format | Article |
| id | doaj.art-6520b381b40f4039ae3668b58bb98ba5 |
| institution | Directory Open Access Journal |
| issn | 2673-253X |
| language | English |
| last_indexed | 2024-04-24T11:37:16Z |
| publishDate | 2024-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Digital Health |
| spelling | doaj.art-6520b381b40f4039ae3668b58bb98ba52024-04-10T04:41:05ZengFrontiers Media S.A.Frontiers in Digital Health2673-253X2024-04-01610.3389/fdgth.2024.13669671366967Empowering inclusivity: improving readability of living kidney donation information with ChatGPTOscar A. Garcia Valencia0Charat Thongprayoon1Jing Miao2Supawadee Suppadungsuk3Supawadee Suppadungsuk4Pajaree Krisanapan5Pajaree Krisanapan6Pajaree Krisanapan7Iasmina M. Craici8Caroline C. Jadlowiec9Shennen A. Mao10Michael A. Mao11Napat Leeaphorn12Pooja Budhiraja13Wisit Cheungpasitporn14Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN, United StatesDivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN, United StatesDivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN, United StatesDivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN, United StatesChakri Naruebodindra Medical Institute, Faculty of Medicine Ramathibodi Hospital, Mahidol University, Samut Prakan, ThailandDivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN, United StatesDivision of Nephrology, Department of Internal Medicine, Faculty of Medicine, Thammasat University, Pathum Thani, ThailandDivision of Nephrology, Department of Internal Medicine, Thammasat University Hospital, Pathum Thani, ThailandDivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN, United StatesDivision of Transplant Surgery, Department of Surgery, Mayo Clinic, Phoenix, AZ, United StatesDivision of Transplant Surgery, Department of Transplant, Mayo Clinic, Jacksonville, FL, United StatesDivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Jacksonville, FL, United StatesDivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Jacksonville, FL, United StatesDivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Phoenix, AZ, United StatesDivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN, United StatesBackgroundAddressing disparities in living kidney donation requires making information accessible across literacy levels, especially important given that the average American adult reads at an 8th-grade level. This study evaluated the effectiveness of ChatGPT, an advanced AI language model, in simplifying living kidney donation information to an 8th-grade reading level or below.MethodsWe used ChatGPT versions 3.5 and 4.0 to modify 27 questions and answers from Donate Life America, a key resource on living kidney donation. We measured the readability of both original and modified texts using the Flesch-Kincaid formula. A paired t-test was conducted to assess changes in readability levels, and a statistical comparison between the two ChatGPT versions was performed.ResultsOriginally, the FAQs had an average reading level of 9.6 ± 1.9. Post-modification, ChatGPT 3.5 achieved an average readability level of 7.72 ± 1.85, while ChatGPT 4.0 reached 4.30 ± 1.71, both with a p-value <0.001 indicating significant reduction. ChatGPT 3.5 made 59.26% of answers readable below 8th-grade level, whereas ChatGPT 4.0 did so for 96.30% of the texts. The grade level range for modified answers was 3.4–11.3 for ChatGPT 3.5 and 1–8.1 for ChatGPT 4.0.ConclusionBoth ChatGPT 3.5 and 4.0 effectively lowered the readability grade levels of complex medical information, with ChatGPT 4.0 being more effective. This suggests ChatGPT's potential role in promoting diversity and equity in living kidney donation, indicating scope for further refinement in making medical information more accessible.https://www.frontiersin.org/articles/10.3389/fdgth.2024.1366967/fullliving kidney donationdisparityhealth literacyinclusivityChatGPT |
| spellingShingle | Oscar A. Garcia Valencia Charat Thongprayoon Jing Miao Supawadee Suppadungsuk Supawadee Suppadungsuk Pajaree Krisanapan Pajaree Krisanapan Pajaree Krisanapan Iasmina M. Craici Caroline C. Jadlowiec Shennen A. Mao Michael A. Mao Napat Leeaphorn Pooja Budhiraja Wisit Cheungpasitporn Empowering inclusivity: improving readability of living kidney donation information with ChatGPT Frontiers in Digital Health living kidney donation disparity health literacy inclusivity ChatGPT |
| title | Empowering inclusivity: improving readability of living kidney donation information with ChatGPT |
| title_full | Empowering inclusivity: improving readability of living kidney donation information with ChatGPT |
| title_fullStr | Empowering inclusivity: improving readability of living kidney donation information with ChatGPT |
| title_full_unstemmed | Empowering inclusivity: improving readability of living kidney donation information with ChatGPT |
| title_short | Empowering inclusivity: improving readability of living kidney donation information with ChatGPT |
| title_sort | empowering inclusivity improving readability of living kidney donation information with chatgpt |
| topic | living kidney donation disparity health literacy inclusivity ChatGPT |
| url | https://www.frontiersin.org/articles/10.3389/fdgth.2024.1366967/full |
| work_keys_str_mv | AT oscaragarciavalencia empoweringinclusivityimprovingreadabilityoflivingkidneydonationinformationwithchatgpt AT charatthongprayoon empoweringinclusivityimprovingreadabilityoflivingkidneydonationinformationwithchatgpt AT jingmiao empoweringinclusivityimprovingreadabilityoflivingkidneydonationinformationwithchatgpt AT supawadeesuppadungsuk empoweringinclusivityimprovingreadabilityoflivingkidneydonationinformationwithchatgpt AT supawadeesuppadungsuk empoweringinclusivityimprovingreadabilityoflivingkidneydonationinformationwithchatgpt AT pajareekrisanapan empoweringinclusivityimprovingreadabilityoflivingkidneydonationinformationwithchatgpt AT pajareekrisanapan empoweringinclusivityimprovingreadabilityoflivingkidneydonationinformationwithchatgpt AT pajareekrisanapan empoweringinclusivityimprovingreadabilityoflivingkidneydonationinformationwithchatgpt AT iasminamcraici empoweringinclusivityimprovingreadabilityoflivingkidneydonationinformationwithchatgpt AT carolinecjadlowiec empoweringinclusivityimprovingreadabilityoflivingkidneydonationinformationwithchatgpt AT shennenamao empoweringinclusivityimprovingreadabilityoflivingkidneydonationinformationwithchatgpt AT michaelamao empoweringinclusivityimprovingreadabilityoflivingkidneydonationinformationwithchatgpt AT napatleeaphorn empoweringinclusivityimprovingreadabilityoflivingkidneydonationinformationwithchatgpt AT poojabudhiraja empoweringinclusivityimprovingreadabilityoflivingkidneydonationinformationwithchatgpt AT wisitcheungpasitporn empoweringinclusivityimprovingreadabilityoflivingkidneydonationinformationwithchatgpt |