Balancing accuracy and user satisfaction: the role of prompt engineering in AI-driven healthcare solutions
IntroductionThe rapid evolution of the Internet of Things (IoT) and Artificial Intelligence (AI) has opened new possibilities for public healthcare. Effective integration of these technologies is essential to ensure precise and efficient healthcare delivery. This study explores the application of Io...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-02-01
|
| Series: | Frontiers in Artificial Intelligence |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frai.2025.1517918/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849717247663144960 |
|---|---|
| author | Mini Han Wang Mini Han Wang Mini Han Wang Mini Han Wang Mini Han Wang Xudong Jiang Xudong Jiang Xudong Jiang Xudong Jiang Peijin Zeng Peijin Zeng Peijin Zeng Xinyue Li Kelvin Kam-Lung Chong Guanghui Hou Xiaoxiao Fang Yang Yu Xiangrong Yu Junbin Fang Yi Pan |
| author_facet | Mini Han Wang Mini Han Wang Mini Han Wang Mini Han Wang Mini Han Wang Xudong Jiang Xudong Jiang Xudong Jiang Xudong Jiang Peijin Zeng Peijin Zeng Peijin Zeng Xinyue Li Kelvin Kam-Lung Chong Guanghui Hou Xiaoxiao Fang Yang Yu Xiangrong Yu Junbin Fang Yi Pan |
| author_sort | Mini Han Wang |
| collection | DOAJ |
| description | IntroductionThe rapid evolution of the Internet of Things (IoT) and Artificial Intelligence (AI) has opened new possibilities for public healthcare. Effective integration of these technologies is essential to ensure precise and efficient healthcare delivery. This study explores the application of IoT-enabled, AI-driven systems for detecting and managing Dry Eye Disease (DED), emphasizing the use of prompt engineering to enhance system performance.MethodsA specialized prompt mechanism was developed utilizing OpenAI GPT-4.0 and ERNIE Bot-4.0 APIs to assess the urgency of medical attention based on 5,747 simulated patient complaints. A Bidirectional Encoder Representations from Transformers (BERT) machine learning model was employed for text classification to differentiate urgent from non-urgent cases. User satisfaction was evaluated through composite scores derived from Service Experiences (SE) and Medical Quality (MQ) assessments.ResultsThe comparison between prompted and non-prompted queries revealed a significant accuracy increase from 80.1% to 99.6%. However, this improvement was accompanied by a notable rise in response time, resulting in a decrease in SE scores (95.5 to 84.7) but a substantial increase in MQ satisfaction (73.4 to 96.7). These findings indicate a trade-off between accuracy and user satisfaction.DiscussionThe study highlights the critical role of prompt engineering in improving AI-based healthcare services. While enhanced accuracy is achievable, careful attention must be given to balancing response time and user satisfaction. Future research should optimize prompt structures, explore dynamic prompting approaches, and prioritize real-time evaluations to address the identified challenges and maximize the potential of IoT-integrated AI systems in medical applications. |
| format | Article |
| id | doaj-art-e14f9d786b8e400ea8b9cedc060aedb8 |
| institution | DOAJ |
| issn | 2624-8212 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Artificial Intelligence |
| spelling | doaj-art-e14f9d786b8e400ea8b9cedc060aedb82025-08-20T03:12:43ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122025-02-01810.3389/frai.2025.15179181517918Balancing accuracy and user satisfaction: the role of prompt engineering in AI-driven healthcare solutionsMini Han Wang0Mini Han Wang1Mini Han Wang2Mini Han Wang3Mini Han Wang4Xudong Jiang5Xudong Jiang6Xudong Jiang7Xudong Jiang8Peijin Zeng9Peijin Zeng10Peijin Zeng11Xinyue Li12Kelvin Kam-Lung Chong13Guanghui Hou14Xiaoxiao Fang15Yang Yu16Xiangrong Yu17Junbin Fang18Yi Pan19Zhuhai People's Hospital (The Affiliated Hospital of Beijing Institute of Technology, Zhuhai Clinical Medical College of Jinan University), Zhuhai, ChinaDepartment of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Kowloon, Hong Kong SAR, ChinaFaculty of Data Science, City University of Macau, Taipa, Macao SAR, ChinaZhuhai Institute of Advanced Technology Chinese Academy of Sciences, Zhuhai, ChinaDigital Medicine and Artificial Intelligence Association, Macau, Macao SAR, ChinaZhuhai Institute of Advanced Technology Chinese Academy of Sciences, Zhuhai, ChinaDigital Medicine and Artificial Intelligence Association, Macau, Macao SAR, ChinaBeijing Normal University - Hong Kong Baptist University United International College, Zhuhai, ChinaPerspective Technology Group, Zhuhai, ChinaZhuhai Institute of Advanced Technology Chinese Academy of Sciences, Zhuhai, ChinaDigital Medicine and Artificial Intelligence Association, Macau, Macao SAR, ChinaPerspective Technology Group, Zhuhai, ChinaSchool of Optometry & Ophthalmology, Tianjin Medical University, Tianjin, ChinaDepartment of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Kowloon, Hong Kong SAR, ChinaZhuhai Aier Eye Hospital, Zhuhai, ChinaZhuhai Aier Eye Hospital, Zhuhai, ChinaZhuhai Aier Eye Hospital, Zhuhai, ChinaZhuhai People's Hospital (The Affiliated Hospital of Beijing Institute of Technology, Zhuhai Clinical Medical College of Jinan University), Zhuhai, China0Department of Optoelectronic Engineering, Jinan University, Shenzhen, China1Key Laboratory of Intelligent Bioinformatics, Shenzhen Institute of Advanced Technology, Shenzhen, ChinaIntroductionThe rapid evolution of the Internet of Things (IoT) and Artificial Intelligence (AI) has opened new possibilities for public healthcare. Effective integration of these technologies is essential to ensure precise and efficient healthcare delivery. This study explores the application of IoT-enabled, AI-driven systems for detecting and managing Dry Eye Disease (DED), emphasizing the use of prompt engineering to enhance system performance.MethodsA specialized prompt mechanism was developed utilizing OpenAI GPT-4.0 and ERNIE Bot-4.0 APIs to assess the urgency of medical attention based on 5,747 simulated patient complaints. A Bidirectional Encoder Representations from Transformers (BERT) machine learning model was employed for text classification to differentiate urgent from non-urgent cases. User satisfaction was evaluated through composite scores derived from Service Experiences (SE) and Medical Quality (MQ) assessments.ResultsThe comparison between prompted and non-prompted queries revealed a significant accuracy increase from 80.1% to 99.6%. However, this improvement was accompanied by a notable rise in response time, resulting in a decrease in SE scores (95.5 to 84.7) but a substantial increase in MQ satisfaction (73.4 to 96.7). These findings indicate a trade-off between accuracy and user satisfaction.DiscussionThe study highlights the critical role of prompt engineering in improving AI-based healthcare services. While enhanced accuracy is achievable, careful attention must be given to balancing response time and user satisfaction. Future research should optimize prompt structures, explore dynamic prompting approaches, and prioritize real-time evaluations to address the identified challenges and maximize the potential of IoT-integrated AI systems in medical applications.https://www.frontiersin.org/articles/10.3389/frai.2025.1517918/fullinternet of things (IoT)artificial intelligence (AI)dry eye disease (DED)prompt engineeringhealthcare virtual assistantgenerative pre-trained transformer-4 (GPT-4) |
| spellingShingle | Mini Han Wang Mini Han Wang Mini Han Wang Mini Han Wang Mini Han Wang Xudong Jiang Xudong Jiang Xudong Jiang Xudong Jiang Peijin Zeng Peijin Zeng Peijin Zeng Xinyue Li Kelvin Kam-Lung Chong Guanghui Hou Xiaoxiao Fang Yang Yu Xiangrong Yu Junbin Fang Yi Pan Balancing accuracy and user satisfaction: the role of prompt engineering in AI-driven healthcare solutions Frontiers in Artificial Intelligence internet of things (IoT) artificial intelligence (AI) dry eye disease (DED) prompt engineering healthcare virtual assistant generative pre-trained transformer-4 (GPT-4) |
| title | Balancing accuracy and user satisfaction: the role of prompt engineering in AI-driven healthcare solutions |
| title_full | Balancing accuracy and user satisfaction: the role of prompt engineering in AI-driven healthcare solutions |
| title_fullStr | Balancing accuracy and user satisfaction: the role of prompt engineering in AI-driven healthcare solutions |
| title_full_unstemmed | Balancing accuracy and user satisfaction: the role of prompt engineering in AI-driven healthcare solutions |
| title_short | Balancing accuracy and user satisfaction: the role of prompt engineering in AI-driven healthcare solutions |
| title_sort | balancing accuracy and user satisfaction the role of prompt engineering in ai driven healthcare solutions |
| topic | internet of things (IoT) artificial intelligence (AI) dry eye disease (DED) prompt engineering healthcare virtual assistant generative pre-trained transformer-4 (GPT-4) |
| url | https://www.frontiersin.org/articles/10.3389/frai.2025.1517918/full |
| work_keys_str_mv | AT minihanwang balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT minihanwang balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT minihanwang balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT minihanwang balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT minihanwang balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT xudongjiang balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT xudongjiang balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT xudongjiang balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT xudongjiang balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT peijinzeng balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT peijinzeng balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT peijinzeng balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT xinyueli balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT kelvinkamlungchong balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT guanghuihou balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT xiaoxiaofang balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT yangyu balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT xiangrongyu balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT junbinfang balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions AT yipan balancingaccuracyandusersatisfactiontheroleofpromptengineeringinaidrivenhealthcaresolutions |