Search Articles

View query in Help articles search

Search Results (1 to 10 of 469 Results)

Download search results: CSV END BibTex RIS


A Risk Prediction Model (CMC-AKIX) for Postoperative Acute Kidney Injury Using Machine Learning: Algorithm Development and Validation

A Risk Prediction Model (CMC-AKIX) for Postoperative Acute Kidney Injury Using Machine Learning: Algorithm Development and Validation

By doing so, we systematically observed and elucidated the strengths and limitations of each model, using a large, well-curated dataset. We observed that certain methods were more affected by the imbalanced dataset, including the decision tree classifier, random forest, and naïve Bayes. We aim to offer insights into the selection of different algorithms for applications in clinical studies. This study has several limitations.

Ji Won Min, Jae-Hong Min, Se-Hyun Chang, Byung Ha Chung, Eun Sil Koh, Young Soo Kim, Hyung Wook Kim, Tae Hyun Ban, Seok Joon Shin, In Young Choi, Hye Eun Yoon

J Med Internet Res 2025;27:e62853

Development and Validation of a Machine Learning Model for Early Prediction of Delirium in Intensive Care Units Using Continuous Physiological Data: Retrospective Study

Development and Validation of a Machine Learning Model for Early Prediction of Delirium in Intensive Care Units Using Continuous Physiological Data: Retrospective Study

In addition, we analyzed correlations so that we could intuitively examine the relationship between each variable we considered and the outcome. The AUROC, sensitivity, positive predictive value, and accuracy at a threshold were measured to compare the performance of different models. Data processing was performed using Python version 3.6.13. The machine learning model was developed and validated using the Py Caret library version 2.3.10.

Chanmin Park, Changho Han, Su Kyeong Jang, Hyungjun Kim, Sora Kim, Byung Hee Kang, Kyoungwon Jung, Dukyong Yoon

J Med Internet Res 2025;27:e59520

User-Centered Prototype Design of a Health Care Robot for Treating Type 2 Diabetes in the Community Pharmacy: Development and Usability Study

User-Centered Prototype Design of a Health Care Robot for Treating Type 2 Diabetes in the Community Pharmacy: Development and Usability Study

In addition, according to the Technology and Acceptance Model [30], the perceived ease of use should be considered as a whole and should take into account the user-friendliness of the interface so that the user can experience the clearest and easiest process. In the interface development, to make it easiest for older adults to operate, each screen will display a maximum of two main options, with options clearly framed to reduce the likelihood of users being unsure of their choices.

Ching-Ju Chiu, Lin-Chun Hua, Jung-Hsien Chiang, Chieh-Ying Chou

JMIR Hum Factors 2025;12:e48226

Enhancing Patient Outcome Prediction Through Deep Learning With Sequential Diagnosis Codes From Structured Electronic Health Record Data: Systematic Review

Enhancing Patient Outcome Prediction Through Deep Learning With Sequential Diagnosis Codes From Structured Electronic Health Record Data: Systematic Review

Several studies have shown that diagnosis codes alone cannot provide the best predictive performance compared to models incorporating multiple features, such as medications, procedures, laboratory test results, demographic data, and so on [82,88,101,108]. Moreover, a study that applied BERT for EHRs has highlighted that combining diagnosis codes with factors such as age, segment, and position lead to improved precision scores compared to relying solely on diagnosis codes [55].

Tuankasfee Hama, Mohanad M Alsaleh, Freya Allery, Jung Won Choi, Christopher Tomlinson, Honghan Wu, Alvina Lai, Nikolas Pontikos, Johan H Thygesen

J Med Internet Res 2025;27:e57358

Caregiving Artificial Intelligence Chatbot for Older Adults and Their Preferences, Well-Being, and Social Connectivity: Mixed-Method Study

Caregiving Artificial Intelligence Chatbot for Older Adults and Their Preferences, Well-Being, and Social Connectivity: Mixed-Method Study

I would say I went more in person before the pandemic, more so before the pandemic. Yeah, and we’ve all changed our habits I think since then.” (Christine) “...it’s radio. Sometimes you can, it just gives out the full like the visual kind of like a video version of the news as well. So, it just depends on what you want, you know, like, you can ask ABC news.”

Brooke H Wolfe, Yoo Jung Oh, Hyesun Choung, Xiaoran Cui, Joshua Weinzapfel, R Amanda Cooper, Hae-Na Lee, Rebecca Lehto

J Med Internet Res 2025;27:e65776