Search Articles

View query in Help articles search

Search Results (1 to 10 of 13 Results)

Download search results: CSV END BibTex RIS


Prompt Framework for Extracting Scale-Related Knowledge Entities from Chinese Medical Literature: Development and Evaluation Study

Prompt Framework for Extracting Scale-Related Knowledge Entities from Chinese Medical Literature: Development and Evaluation Study

Given the importance of task-oriented prompt design and the linguistic complexities of Chinese medical literature, there is an urgent need to develop a specialized framework for medical scale–related knowledge extraction. In this study, we propose Med Scale NER, a task-oriented prompt framework tailored for named entity recognition (NER) of medical scales in Chinese medical literature.

Jie Hao, Zhenli Chen, Qinglong Peng, Liang Zhao, Wanqing Zhao, Shan Cong, Junlian Li, Jiao Li, Qing Qian, Haixia Sun

J Med Internet Res 2025;27:e67033

Role of Tailored Timing and Frequency Prompts on the Efficacy of an Internet-Delivered Stress Recovery Intervention for Health Care Workers: Randomized Controlled Trial

Role of Tailored Timing and Frequency Prompts on the Efficacy of an Internet-Delivered Stress Recovery Intervention for Health Care Workers: Randomized Controlled Trial

When participants indicated that supplementary prompts would be necessary, they were asked about preferences of prompt frequency (ie, once a week, twice a week, every workday, or every workday twice a day) and timing (before noon, sometime in the morning or afternoon, sometime in the evening). Participants in the SG did not schedule a plan for the tailored prompts and did not receive them. Description of the program modules.

Auguste Nomeikaite, Odeta Gelezelyte, Maria Böttche, Gerhard Andersson, Evaldas Kazlauskas

JMIR Ment Health 2025;12:e62782

The Ability of ChatGPT in Paraphrasing Texts and Reducing Plagiarism: A Descriptive Analysis

The Ability of ChatGPT in Paraphrasing Texts and Reducing Plagiarism: A Descriptive Analysis

This indicates that the specific prompt provided to Chat GPT does not significantly influence its paraphrasing capability. In addition, this outcome might be the consequence of the bot’s strong ability to understand our true intentions when issuing commands, or it might be because our command words were brief or similar to one another. However, further investigation into the effect of different prompts and their impact on plagiarism is warranted to explore this aspect in more detail.

Soheil Hassanipour, Sandeep Nayak, Ali Bozorgi, Mohammad-Hossein Keivanlou, Tirth Dave, Abdulhadi Alotaibi, Farahnaz Joukar, Parinaz Mellatdoust, Arash Bakhshi, Dona Kuriyakose, Lakshmi D Polisetty, Mallika Chimpiri, Ehsan Amini-Salehi

JMIR Med Educ 2024;10:e53308

Tailored Prompting to Improve Adherence to Image-Based Dietary Assessment: Mixed Methods Study

Tailored Prompting to Improve Adherence to Image-Based Dietary Assessment: Mixed Methods Study

Prompt setting and order were fixed effects within the model—order was included to account for uneven sizes in the 6 different orders. Participants were accounted for as random effects (random intercept model), accounting for repeat observations under each prompt setting and correlation of participant responses across conditions. P values for the fixed effect of prompt setting order were obtained using the Wald type 3 test.

Lachlan Lee, Rosemary Hall, James Stanley, Jeremy Krebs

JMIR Mhealth Uhealth 2024;12:e52074

An Empirical Evaluation of Prompting Strategies for Large Language Models in Zero-Shot Clinical Natural Language Processing: Algorithm Development and Validation Study

An Empirical Evaluation of Prompting Strategies for Large Language Models in Zero-Shot Clinical Natural Language Processing: Algorithm Development and Validation Study

In the prompt designing step (step 2), a prompt was designed for the task using one of the prompt types (eg, simple prefix prompt, simple cloze prompt, heuristic prompt, chain of thought prompt, question prompt, and anticipatory prompt). We also optionally performed few-shot prompting by providing some examples along with the prompt. The LLMs and the evaluation metrics for the experiment setup were then configured.

Sonish Sivarajkumar, Mark Kelley, Alyssa Samolyk-Mazzanti, Shyam Visweswaran, Yanshan Wang

JMIR Med Inform 2024;12:e55318

Long-Term Effectiveness of a Multi-Strategy Choice Architecture Intervention in Increasing Healthy Food Choices of High-School Students From Online Canteens (Click & Crunch High Schools): Cluster Randomized Controlled Trial

Long-Term Effectiveness of a Multi-Strategy Choice Architecture Intervention in Increasing Healthy Food Choices of High-School Students From Online Canteens (Click & Crunch High Schools): Cluster Randomized Controlled Trial

The summary included a pie graph displaying the proportion of items in their order that was “everyday,” “occasional,” and “should not be sold,” and a tailored message based on the proportion of “everyday” items in the order (eg, if When “occasional” or “should not be sold” hot food items were chosen they included a prompt to add a fruit or vegetable snack and water.

Tessa Delaney, Jacklyn Jackson, Christophe Lecathelinais, Tara Clinton-McHarg, Hannah Lamont, Sze Lin Yoong, Luke Wolfenden, Rachel Sutherland, Rebecca Wyse

J Med Internet Res 2024;26:e51108

The Effect of Explicit Suicide Language in Engagement With a Suicide Prevention Search Page Help-Seeking Prompt: Nonrandomized Trial

The Effect of Explicit Suicide Language in Engagement With a Suicide Prevention Search Page Help-Seeking Prompt: Nonrandomized Trial

In this case, a help-seeking prompt refers to any media encouraging service use. For example, a person may prompt an individual to see their general practitioner (GP) for their mental health, a description on an app store may prompt them to download a suicide prevention app, signage at frequently used locations may point them toward a phone booth, or text on an internet search page may encourage them to call a hotline.

Sandersan Onie, Susanne Oliver Armstrong, Natasha Josifovski, Patrick Berlinquette, Nicola Livingstone, Sarah Holland, Coco Finemore, Nyree Gale, Emma Elder, George Laggis, Cassandra Heffernan, Adam Theobald, Michelle Torok, Fiona Shand, Mark Larsen

JMIR Ment Health 2024;11:e50283

Exploring Whether the Electronic Optimization of Routine Health Assessments Can Increase Testing for Sexually Transmitted Infections and Provider Acceptability at an Aboriginal Community Controlled Health Service: Mixed Methods Evaluation

Exploring Whether the Electronic Optimization of Routine Health Assessments Can Increase Testing for Sexually Transmitted Infections and Provider Acceptability at an Aboriginal Community Controlled Health Service: Mixed Methods Evaluation

A core component was the addition to the EMR of an electronic prompt and an automated pathology set. The prompt was attached to the health assessment template completed by general practitioners (GPs) and triggered for all patients in the target age range, advising the GP to query sexual activity since the patient’s last test because guidelines recommend STI screening after a change in partner or otherwise annually [38].

Heather McCormack, Handan Wand, Christy E Newman, Christopher Bourne, Catherine Kennedy, Rebecca Guy

JMIR Med Inform 2023;11:e51387

Prompt Engineering as an Important Emerging Skill for Medical Professionals: Tutorial

Prompt Engineering as an Important Emerging Skill for Medical Professionals: Tutorial

Thus, a new, essential skill has emerged: prompt engineering. Prompt engineering is a relatively new field of research that refers to the practice of designing, refining, and implementing prompts or instructions that guide the output of LLMs to help in various tasks. It is essentially the practice of effectively interacting with AI systems to optimize their benefits.

Bertalan Meskó

J Med Internet Res 2023;25:e50638