e.g. mhealth
Search Results (1 to 4 of 4 Results)
Download search results: CSV END BibTex RIS
Skip search results from other journals and go to results- 2 JMIR Medical Informatics
- 1 JMIR Aging
- 1 Journal of Medical Internet Research
- 0 Medicine 2.0
- 0 Interactive Journal of Medical Research
- 0 iProceedings
- 0 JMIR Research Protocols
- 0 JMIR Human Factors
- 0 JMIR Public Health and Surveillance
- 0 JMIR mHealth and uHealth
- 0 JMIR Serious Games
- 0 JMIR Mental Health
- 0 JMIR Rehabilitation and Assistive Technologies
- 0 JMIR Preprints
- 0 JMIR Bioinformatics and Biotechnology
- 0 JMIR Medical Education
- 0 JMIR Cancer
- 0 JMIR Challenges
- 0 JMIR Diabetes
- 0 JMIR Biomedical Engineering
- 0 JMIR Data
- 0 JMIR Cardio
- 0 JMIR Formative Research
- 0 Journal of Participatory Medicine
- 0 JMIR Dermatology
- 0 JMIR Pediatrics and Parenting
- 0 JMIR Perioperative Medicine
- 0 JMIR Nursing
- 0 JMIRx Med
- 0 JMIRx Bio
- 0 JMIR Infodemiology
- 0 Transfer Hub (manuscript eXchange)
- 0 JMIR AI
- 0 JMIR Neurotechnology
- 0 Asian/Pacific Island Nursing Journal
- 0 Online Journal of Public Health Informatics
- 0 JMIR XR and Spatial Computing (JMXR)
Practical Applications of Large Language Models for Health Care Professionals and Scientists
Particularly with complex tasks, the “Chain of Thought Prompting” technique can yield improved results [6]. This technique enhances the reasoning capabilities of LLMs by breaking down multistep problems into a series of intermediate reasoning steps. For generating suitable prompts, it is also feasible to integrate the LLM by providing the program with relevant instructions and subsequently request feedback to iteratively refine the desired prompt.
JMIR Med Inform 2024;12:e58478
Download Citation: END BibTex RIS
In the subset of studies in which outcomes have been measured and reported, studies that have compared a prompting to a no prompting condition generally have demonstrated some advantage to using prompts [11]. For example, a recent experimental study tested a smartphone app that prompted water drinking and found significantly better performance in the prompted than in the unprompted condition [25].
JMIR Aging 2024;7:e56055
Download Citation: END BibTex RIS
Few-shot prompting is a technique that provides the model with a few examples of input-output pairs, while zero-shot prompting does not provide any examples [3,18]. By contrasting these strategies, we aim to shed light on the most efficient and effective ways to leverage prompt engineering in clinical NLP. Finally, we propose a prompt engineering framework to build and deploy zero-shot NLP models for the clinical domain.
JMIR Med Inform 2024;12:e55318
Download Citation: END BibTex RIS
Go back to the top of the page Skip and go to footer section