This study examined whether it was feasible to launch electronic health record (EHR)-integrated ambient scribe technology across an entire large academic health system at the same time. Ambient scribing uses artificial intelligence to listen to clinician–patient conversations and automatically generate clinical documentation within the EHR.

On January 15, 2025, the technology was made available to more than 2,400 clinicians working in ambulatory clinics and emergency departments. The researchers monitored how frequently the tool was used, how much technical support was needed, and how clinicians evaluated their experience.

By March 31, 2025, 20.1 percent of visit notes included ambient scribing, and 1,223 clinicians had used the tool. Among 209 clinicians who responded to a survey (22.1 percent of those surveyed), 90.9 percent said they would be disappointed if they lost access to the technology, and 84.7 percent reported a positive training experience.

The findings indicate that a simultaneous, enterprise-wide rollout combined with a low-barrier training approach allowed clinicians to gain immediate access to the tool while keeping support demands manageable. Overall, the study demonstrates that large-scale implementation of EHR-integrated ambient scribing is feasible and can be successfully adopted across a health system.

Figure 1.

Number of ambient scribing users after enterprise-wide rollout.

Decision aids are tools that help patients and clinicians make healthcare decisions together, improving patient knowledge, reducing regret, and encouraging meaningful discussion. However, many clinicians do not use these tools because of time limits, difficulty matching aids to patient needs, leaving the electronic health record (EHR) to access them, and manual data entry.

This study explored clinician needs to design an EHR-integrated app called DEAN (Decision Aid Navigator), built on the SMART on FHIR platform. DEAN identifies decision aids relevant to a patient’s conditions, current treatments, and demographics, and helps document shared decision-making discussions.

Researchers interviewed 13 clinicians from four academic medical centers while showing a prototype of DEAN. Analysis of the interviews revealed three key needs: (1) streamlined functionality to reduce workflow burden, (2) clinician skills to use the app and decision aids effectively, and (3) trust that the app suggests pre-vetted decision aids. Clinicians agreed that EHR integration was essential for adoption.

The study concludes that improving tools like DEAN and integrating them into the EHR can help clinicians use decision aids more efficiently, supporting shared decision-making and potentially increasing patient-centered care.

Figure 1.��The 5 rights of clinical decision support (adapted from []) .

]]> /valiant/2026/01/28/large-scale-integration-of-omics-and-electronic-health-records-to-identify-potential-risk-protein-biomarkers-and-therapeutic-drugs-for-cancer-prevention/ Wed, 28 Jan 2026 15:23:57 +0000 /valiant/?p=5649 Li, Qing; Song, Qingyuan; Chen, Zhishan; Choi, Jung-yoon; Moreno, Victor R.; Ping, Jie; Wen, Wanqing; Li, Chao; Shu, Xiang; Yan, Jun; Shu, Xiaoou; Cai, Qiuyin; Long, Jirong; Huyghe, Jeroen R.; Pai, Rish K.; Gruber, Stephen Bernard; Yang, Yaohua; Casey, Graham R.; Wang, Xusheng; Toriola, Adetunji T.; Li, Li; Singh, Bhuminder; Lau, Ken S.; Zhou, Li; Zhang, Zichen; Wu, Chong; Peters, Ulrike; Zheng, Wei; Long, Quan; Yin, Zhijun; & Guo, Xingyi. (2026).��.��American Journal of Human Genetics,��113(1), 41–56.��

Finding the right proteins to target and the drugs that act on them is essential for preventing cancer. In this study, we combined and closely analyzed data from large genome-wide association studies covering six common cancers: breast, colorectal, lung, ovarian, pancreatic, and prostate cancer. We identified 710 genetic variants that are independently linked to cancer risk. By connecting these variants to protein quantitative trait loci using blood-based proteomics data from more than 75,000 people, we found 365 proteins associated with cancer risk.

Further analysis showed that 101 of these proteins are very likely to play a direct role in cancer development, including 74 that have not been reported before. Among them, 36 proteins appear to be potentially druggable, meaning they could be targeted by existing or future medications. To explore real-world effects, we analyzed more than 3.5 million electronic health records and carried out emulated clinical trials comparing 11 commonly used drugs across 290 scenarios. We identified three drugs that were associated with a lower risk of colorectal cancer, including caffeine compared with paroxetine, haloperidol compared with prochlorperazine, and trazodone hydrochloride compared with paroxetine. In contrast, caffeine was linked to a higher cancer risk when compared with finasteride for colorectal cancer and fluoxetine for breast cancer.

A combined analysis across studies identified six drugs that were significantly associated with cancer risk. One of these, acetazolamide, was associated with a reduced risk of colorectal cancer. Overall, this study uncovers previously unknown protein biomarkers and potential drug targets across six major cancer types and highlights several already approved drugs that may have promise for cancer prevention.

Figure 1��Overview of the analytical framework

(A) An illustration depicting the identification of proteins associated with the risk of the six major cancers: breast, lung, colorectal, ovarian, pancreatic, and prostate. Population-based proteomics data (for pQTLs) and GWAS data resources (for identifying lead variants) utilized in this study are shown on the left. Meta-analyses of��cis-pQTLs from ARIC and deCODE, conducted through the SOMAscan platform, were combined with pQTL results from the UKB-PPP to identify potential risk proteins, as depicted in the middle images. Colocalization analyses between GWAS summary statistics and��cis-pQTLs were performed to identify cancer risk proteins with high confidence, as illustrated on the right.

(B) The proteins with evidence of colocalization annotated based on drug-protein information from four databases: DrugBank, ChEMBL, TTD, and Open Targets.

(C) The framework for evaluating the effects of drugs approved for indications on cancer risk. The inverse probability of treatment weighting (IPTW) framework was utilized to construct emulations of treated-control drug trials based on millions of patients’ electronic health records stored at VUMC SD (left). In these emulations, the Cox proportional hazard model was conducted for each trial to assess the hazard ratio (HR) of cancer risk between the treated focal drug and the control drug (right).

]]> /valiant/2025/11/23/study-protocol-for-the-design-implementation-and-evaluation-of-the-stratify-clinical-decision-support-tool-for-emergency-department-disposition-of-patients-with-heart-failure/ Sun, 23 Nov 2025 17:00:00 +0000 /valiant/?p=5436 Kripalani, Sunil B., Stolldorf, Deonni P., Sachs, Anna L., Barrett, Jennifer B., Anders, Shilo H., Novak, Laurie Lovett., Liu, Dandan., Miller, Joseph B., Kea, Bory., Schlotterbeck, Isaac., & Storrow, Alan B. (2025).��.��Implementation Science Communications,��6(1), 107.��

Clinicians in the emergency department (ED) often have to make difficult, time-sensitive decisions with limited information.��Clinical decision support (CDS)��tools built into the electronic health record can help by providing evidence-based guidance, but in practice these tools are not widely used in the ED because of many workflow and implementation barriers. One area where CDS tools could be especially useful is in caring for patients with��acute exacerbation of heart failure (AHF)—a common and expensive condition that often leads to hospital admission, even when some patients may actually be safe to go home.

To address this, we developed��STRATIFY, a validated��risk prediction model��that identifies AHF patients who are at low risk for serious problems in the next 30 days and may be good candidates for discharge from the ED. This article describes a multi-center study focused on bringing STRATIFY into real-world clinical practice using a CDS tool.

The study has three main goals:

1. create a CDS-based implementation process for STRATIFY that is shaped by input from stakeholders such as clinicians, patients, and caregivers;
2. develop new statistical methods to solve data problems that arise when using predictive models in real time in the ED, such as how to handle missing information without compromising risk estimates; and
3. test both the implementation and effectiveness of the STRATIFY CDS atseven EDs, examining how well it supports decisions about admitting or discharging AHF patients.

To do this, the study uses a��multi-level implementation strategy��tailored to each site. This includes surveys, on-site visits, virtual interviews, small-group discussions with patients and caregivers, and��iterative user-centered design��to refine the STRATIFY tool. Effectiveness will be evaluated using an��interrupted time-series design, measuring changes in ED decisions (admission vs. discharge) and monitoring for any adverse outcomes. The study will also assess how acceptable, usable, and sustainable the STRATIFY CDS is, using surveys and electronic health record data.

Overall, this work aims to demonstrate how a thoughtfully designed, stakeholder-informed CDS process can help close the gap between research evidence and everyday clinical practice in the emergency department.

Fig.��1

Summary schema of study

]]> /valiant/2025/06/20/behavior-shifts-in-patient-portal-usage-during-and-after-policy-changes-around-test-result-delivery-and-notification/ Fri, 20 Jun 2025 18:24:54 +0000 /valiant/?p=4562 Suresh, Uday; Steitz, Bryan D.; Rosenbloom, S. Trent; Griffith, Kevin N.; Ancker, Jessica S. AMIA … Annual Symposium proceedings. AMIA Symposium (2024): 1089-1098. ��

Because of the 21st Century Cures Act, many hospitals and clinics now release test results to patients through online portals as soon as they are available. To understand how this change affected the way patients use these portals, we looked at electronic health record data before and after the policy went into effect, as well as after a later change that required patients to opt in to get notifications about new test results.��

We found that once the Cures Act policy was put in place, more patients took action after viewing their test results—specifically, 4.5% more scheduled a new��appointment��and 4.5% more sent messages to their doctors. Later, when automatic notifications were turned off, 2.1% more patients scheduled appointments, but 0.8% fewer used telemedicine.��

Our study shows that these policy changes led to real shifts in how patients respond to their test results—something that affects both patients’ efforts to get more information and the workload for clinicians.��

��

Figure 1a, 1b, 1c.��

Proportions of patients scheduling new appointments after accessing their test results prior to their clinician or after their clinician across the time periods of Cures Act compliance and the notification policy change. Plot 1a shows the proportion of all patients scheduling new appointments. Plots 1b and 1c show the proportion of patients scheduling new appointments who reviewed their results prior to their clinician and after their clinician, respectively.��

��

��

This study uses a method based on��probabilistic independence��to help uncover the hidden, patient-specific causes—or “sources”—of disease using data from electronic health records (EHRs). In this approach, each disease source is treated as an��unobserved root cause��in a network that influences various observed medical variables like lab tests, medications, billing codes, and demographics. The effects of each source—its��signature—are the patterns these causes leave behind in the data.��

By analyzing a large dataset of over 269,000 patient records and 9,195 variables, the model was able to infer 2,000 potential disease sources and their unique signatures. To test the method, the researchers used it to explore the causes of��benign vs. malignant pulmonary nodules��(small spots in the lungs) in more than 13,000 cases. The model successfully identified 92% of known malignant causes and 30% of benign ones listed in an external reference. It also uncovered several likely causes not included in the reference list, but supported by other medical literature.��

In many cases, the model could��decompose��a general diagnosis into more specific patterns related to disease progression or treatment. For example, a common malignant cause could be broken down into five or more detailed sub-patterns. Interestingly, the model also flagged many patients who may have had��undiagnosed cancer, based on their data patterns.��

These findings show that even from noisy, incomplete, and irregular health records, it’s possible to extract meaningful,��patient-specific causes of disease. This could eventually help clinicians better understand complex cases and make more precise treatment decisions tailored to individual patients.��

��

Fig. 1.��A hypothetical causal graph and structured derived from it. a) The causal graph inferred from observing the����(solid circles) over many records. The����are inferred latent sources (dotted circles). Colors of the nodes����indicate the degree to which a unit change in source����affects them. They are arbitrary here for illustration, except for��, which cannot be affected by��. b) Causal effects of source����collected into a bar-graph signature c) Causal model of����using latent sources����as inputs. d) Statistical model of��using observations����as inputs. Color intensity of inputs represent their hypothetical importance values for the prediction in a single instance. For the causal model, the inputs are mutually independent root nodes, and therefore can be interpreted as the causal sources of��, which may suggest treatment approaches that address the specific causes for this patient, and which may be manipulated to investigate different counterfactual scenarios. For the statistical model, the importance values remain entangled and cannot be interpreted this way.��

��

Suresh, Uday; Ancker, Jessica; Salmi, Liz; Diamond, Lisa; Rosenbloom, Trent; Steitz, Bryan. ��BMJ Oncology, vol. 4, no. 1, 2025, e000432,��.��

��

In recent years, more and more cancer patients have been using patient portals, which are online platforms where patients can access their health information, communicate with doctors, and manage their care. This review looks at studies published between January 2018 and April 2024 to understand how cancer patients and their caregivers are using these portals, and how the use of these tools affects their care. The review focuses on three main areas: trends in how and why patients with cancer use portals, the specific features of portals that are most helpful in cancer care, and how portal use is linked to cancer-related health outcomes.��

The review identified 278 studies, and 82 of them met the criteria to be included in the analysis. The studies explored various aspects, including challenges in access to portals, the increased use of telemedicine through portals, and how patients can easily access their health information. The findings suggest that patient portals are becoming a key tool in helping cancer patients manage their care, though there are still some issues that prevent everyone from using them equally. While the use of portals has grown significantly, there’s still room for improvement in how they support cancer patients, with a clear need for the tools to continue evolving to meet their changing needs.��

This study developed and validated a machine learning model to predict 72-hour return visit admissions (RVA) to the hospital after an emergency department (ED) discharge. Using data from over 135,000 patients across three urban EDs, researchers tested various algorithms, including advanced methods like DICE and XGBoost, comparing them to an existing clinical risk score. The best model combined DICE and logistic regression, achieving strong predictive accuracy (AUC 0.87 in development data and 0.75 in validation data).��

Clinicians reviewed cases identified by the model to understand its strengths and weaknesses. While the model performed well overall, its accuracy varied by diagnosis and some patient groups, limiting immediate clinical usefulness. Insights from this study suggest ways to refine predictions and improve the model’s practical application in enhancing care quality and preventing adverse outcomes.��

Fig 1. Inclusion Criteria (Development Site). WCM: Weill Cornell Medicine. LMH: Lower Manhattan Hospital. ��

This scoping review systematically examines the relationship between extreme weather events (EWEs) and adverse health outcomes in short-stay patients undergoing post-acute care (PAC) and long-stay residents in nursing homes (NHs). The review included 10 retrospective cohort studies, primarily focused on hurricanes in the Southern United States, with one study addressing flood risk in North Dakota. The studies mainly investigated the effects of hurricanes on long-stay NH residents and their associations with increased 30- and 90-day mortality rates, unplanned hospitalizations, and changes in cognitive impairment.

The findings showed a consistent association between hurricane exposure and elevated mortality risks within 30 and 90 days, especially for long-stay NH residents and those in hospice care. Short-stay PAC patients also experienced higher hospitalization rates following hurricane exposure. The review highlights the need for future research to evaluate the impact of other types of EWEs beyond hurricanes, across broader geographic areas, and with a focus on longer-term health outcomes, associated costs, and potential disparities affecting vulnerable NH populations as climate-related EWEs become more frequent and severe.

A comprehensive two-part study utilizing electronic medical records from ������ý���� Medical Center investigated health conditions in individuals with Down syndrome (DS), particularly those with congenital heart disease (CHD). The first part of the study examined a large cohort of DS individuals, revealing a higher prevalence of specific health issues such as heart failure, pulmonary heart disease, and hypothyroidism compared to controls and those with other intellectual and developmental disabilities. The second part focused on DS patients with CHD, identifying conditions like congestive heart failure and valvular heart disease that increased the likelihood of surgical interventions. These findings highlight the complex health profiles of individuals with DS, suggesting the need for tailored medical approaches to better manage their multiple health challenges.