Articles tagged with Electronic Medical Records
Researchers have launched a new multimodal medical dataset, Observer, capturing anonymized, real-time interactions between patients and clinicians. The dataset links video, audio, transcripts, and electronic health records to study subtleties like body language and environmental factors affecting care.
The team created a specialized two-dimensional thin film dielectric designed to replace traditional heat-generating components in integrated circuit chips. This breakthrough aims to reduce the significant energy cost and heat produced by high-performance computing necessary for AI.
Experts weighed in on the current state of artificial intelligence (AI) in cancer care, noting both its potential for improving efficiency and its challenges. Many expressed excitement over AI's possibilities for helping support an overburdened oncology workforce and accelerating the pursuit of new cures.
Local-stage colorectal cancer incidence among US adults ages 45-49 increased by 50% between 2021 and 2022, with a steep rise in 2019-2022. Screening rates also increased during this period, driven by recommendations to start screening at age 45.
Researchers developed an AI model that converts fragmented electronic health records into readable narratives, enabling artificial intelligence to make sense of complex patient histories. The Multimodal Embedding Model for EHR (MEME) transformed tabular health data into 'pseudonotes' that mirror clinical documentation, achieving superi...
A University of Cambridge report argues that menstrual tracking app data is a valuable resource for advertisers but poses significant privacy and safety risks to users. The report calls for better governance of the industry to protect user data and urges public health bodies to launch alternative apps.
Researchers found significant disparities in behavioral flag incidence among racially and socioeconomically marginalized pediatric patients. Black or African American patients younger than 8 years were disproportionately affected.
A comprehensive review explores the evolution and application of electronic health records (EHRs) in medical research over the past 25 years. The study highlights significant advancements in data analysis, artificial intelligence, and precision medicine, while also discussing challenges such as data security and privacy.
A recent study found that patients who left emergency departments before being medically advised had higher rates of readmission, mortality, and increased costs. The COVID-19 pandemic led to a 53.6% increase in such cases, primarily due to concerns about infection, long wait times, and dissatisfaction with care.
A study found that standard medical reports are often difficult for patients to understand, leading to increased worry. In contrast, patient-centered pathology reports provide clear and concise information, improving patient comprehension and reducing anxiety.
Researchers found a strong link between depression and menstrual pain in a new study published in Briefings in Bioinformatics. Depression may be a cause of dysmenorrhea, rather than a consequence, according to the findings.
A new study by UCLA Health reveals that standard medical record surveillance methods miss youth with suicidal thoughts and behaviors in children, boys, and Black and Hispanic youths. Machine learning algorithms improved detection rates when incorporating additional data from visit notes.
The American College of Surgeons Geriatric Surgery Verification program reduces surgical death rates by nearly half and increases the percentage of patients with documented care preferences. Implementing the program also enables hospitals to improve patient-centered care and reduce costs.
A new study found a significant sex bias in pain management at emergency departments, with female patients consistently receiving fewer pain medication prescriptions compared to male patients. Female patients also spend more time in the emergency department and have their pain scores less frequently recorded.
A new study found that an electronic health record (EHR)-based nudge intervention significantly decreased low-value axillary surgery in older women with clinically node-negative, HR+/HER2− breast cancer. The user-friendly intervention could be beneficial for other practice settings or patient populations.
Text messaging and bulk ordering can significantly increase mammogram completion rates for breast cancer screening outreach. The study found that these interventions are effective in improving adherence to recommended screening guidelines.
A study by UCLA researchers found that nearly 20% of patients with serious illnesses listed as alive in their medical records were actually deceased according to California data. This discrepancy led to hundreds of wasteful follow-up outreach efforts, straining resources and healthcare workers' time.
The special supplement examines the impacts of EHR transitions on patient care, data integrity, and security. It highlights the need for medical institutions to understand the difficulties of transitioning to new systems to maximize success and inform decisions.
A synoptic report improved the completeness of pretreatment CT reports in patients with advanced ovarian cancer. Involvement of surgically established unresectable or challenging-to-resect disease sites was mentioned in all disease-specific synoptic reports, compared to 37% of simple structured reports.
A recent commentary highlights a potential hidden source of bias in electronic health records, which can impact clinical trials. Embedded pragmatic clinical trials rely heavily on EHRs for data collection, excluding people from underrepresented groups due to lack of access or inaccurate data collection.
Regenstrief Institute researchers are using EHR data to advance measurement of chronic disease burdens, including diabetes and cardiovascular disease. They will discuss leveraging EHR data to improve clinician care and support targeted interventions for patients with chronic illnesses.
Axillary lymphadenopathy after a COVID-19 vaccine booster dose resolves at a mean of 102 days. Findings support follow-up intervals of at least 12 weeks to avoid delaying screening mammography for suspected vaccine-related lymphadenopathy.
Researchers at NYU Grossman School of Medicine found that automated systems with alert banners increased MRA therapy prescriptions for heart failure patients by 30%. The system aims to improve care and reduce costs by streamlining medical information in one place. The study tested two notification types, finding that banner-like alerts...
A new study found that Black and Hispanic stroke survivors in the US are less likely to receive treatment for common complications, despite improved overall stroke survival rates. Researchers analyzed electronic health records from 2002 to 2022 and matched patients based on 41 factors to minimize biases.
Researchers identified 7 key symptoms of long COVID, including heart issues and joint pain, in a study of 52,461 patients. The findings could help healthcare providers diagnose and treat the condition more effectively.
A diabetes screening program in an urban emergency department found high rates of undiagnosed prediabetes and type 2 diabetes among racial and ethnic minority individuals and low-income patients. The study suggests that targeted outreach to those with higher hemoglobin A1c levels may be more cost-effective.
Researchers found that acknowledging physicians' efforts with letters and certificates improved tobacco cessation e-referral rates after a January 2022 rollout. Providing access to accurate EHR data can also enhance clinical outcomes in vulnerable populations.
A new study from the Mid-Atlantic Permanente Research Institute highlights nationwide health disparities in COVID-19 testing, hospitalization rates, and death. Black and Hispanic men were more likely to be hospitalized and die from COVID-19 compared to their white counterparts.
A recent study by UCF Associate Professor Varadraj Gurupur created an algorithm to predict and measure the incompleteness of electronic health records. The analysis found that missing information is a significant issue, with varying levels of incompleteness per year and no clear pattern of where it occurs.
An AI-based model has been developed to assist radiologists in detecting and identifying leadless implanted electronic devices (LLIEDs) on chest X-ray images. The model achieved high detection and classification accuracy, even with suboptimal image quality, and showed promise for real-world deployment.
A new automated screening tool can accurately identify patients at high risk of developing progressive scarring of the lungs, a condition called idiopathic pulmonary fibrosis (IPF). The tool uses machine-learning algorithms to analyze patient electronic health records and detects IPF risk automatically.
Researchers developed a universal screening tool for IPF that can alert primary care physicians to its possible presence, enabling earlier diagnosis and treatment. The Zero-burden Co-Morbidity Risk Score for IPF (ZCoR-IPF) algorithm uses existing patient records to identify patients at risk of developing the disease.
A new study analyzed point-of-sale data from nearly 17,000 patients in New York's medical cannabis program to understand patient preferences for products and dosing. The researchers found considerable variability in product choice and dosing levels across different conditions, highlighting the need for clear clinical guidelines.
The recently updated ICPC-3 guide provides health professionals with a better understanding of patient functioning and its impact on primary healthcare. By implementing ICPC-3, clinicians can improve data documentation, enhance information exchange, and ultimately provide more effective care to patients.
Researchers developed an EHR-embedded card study to replace traditional paper-based methods in clinic-based research. The digital tool increased efficiency and reduced labor costs, as each participant's responses were linked to clinic and patient data.
Despite electronic health records, gaps in communication between primary care physicians and specialist physicians persist. The study found that 22% of PCPs report sending clinical information to specialists at the time of referral, and less than 35% receive information back after consultation.
Clinicians perceive electronic health records as a barrier to patient engagement, maintaining less eye contact and feeling less personal during visits. However, most patients report a positive experience with EHR use, indicating sufficient clinician-patient interaction.
A quality improvement project at Dartmouth Cancer Center increased serious illness conversations between patients and providers from 0% to 70%, reflecting the importance of early discussions on prognosis and treatment options. The project's success was attributed to standardized work, an engaged interdisciplinary team, and system-level...
The Avoidable Transfer Scale identifies potentially avoidable hospitalizations in nursing home residents based on EHR data. The tool enables nursing homes to focus on trends and process improvements, benefiting residents and reducing healthcare costs.
FeRh, a metal with antiferromagnetic and ferromagnetic phases, has its phase transition kinetics measured using ultrafast techniques. The study reveals new insights into the ultrafast dynamics of magnetic materials.
A new $2.4 million NIH award supports efforts to improve data sharing between dental and medical records, reducing delays in treatment decisions and improving patient health outcomes.
The study found that standing orders significantly raised guideline adherence for patients on intermediate FN risk regimens but did not change the FN rate among patients on chemotherapy at any risk level. Prophylactic CSF use rates were substantially below guidelines for both high-risk and low-risk regimens.
A new study by USC researchers found a significant link between exposure to fine particles (PM2.5) and nitrogen dioxide (NO2) and increased risk of severe COVID-19 outcomes. Long-term PM2.5 exposure was associated with a higher risk of mortality from COVID-19.
A new Regenstrief Institute study evaluates commercially available matching methodologies against real-world gold standard data to identify opportunities for improving match accuracy. The study found that referential patient matching demonstrates greater sensitivity and accuracy than traditional probabilistic approach.
Researchers analyzed health records of nearly half a million patients post-heart attack and found that depression was associated with a nearly 50% higher stroke risk compared to those without depression. The study highlights the need for greater attention to mental health in research and practice.
A LSU Health New Orleans study reports a nearly 70% decrease in morphine milligram equivalent (MME) per discharge opioid prescriptions for patients who underwent common lower extremity surgical procedures. The study also found a significant decline in new opioid prescriptions, from 50% in 2013 to 19.3% in 2018.
Researchers developed an AI program that accurately identified patients at risk of serious illness due to blood infections, with an accuracy rate of 82%. The technology has the potential to serve as an early warning system for doctors, enabling them to rank patients based on their risk level.
Researchers developed EDS-HAT, an AI-powered system combining machine learning and whole genome sequencing to detect clusters of similar infections in real-time. The system identified 99 clusters of infections and prevented potential transmissions in 65.7% of cases, saving the hospital $692,500.
Rice University computer scientists have discovered an inexpensive way to implement rigorous personal data privacy in large databases for machine learning. Using locality sensitive hashing, their RACE method creates small summaries of enormous databases while scaling for high-dimensional data.
A study by Intermountain Healthcare found that notifying pharmacies of discontinued prescriptions can prevent almost 200 safety events over two months. By using a CancelRX functionality in their electronic medical record system, the team was able to avoid these events and ensure patients only receive correct medications.
A researcher at MUSC has developed an AI algorithm that analyzes clinical notes to identify patients at risk of suicide. The algorithm achieved accuracy rates of around 98.5% when trained on electronic health records, and nearly 80% when validated against existing predictive models.
Women using hormonal contraceptives face a 2-fold higher risk of developing glaucoma compared to non-users. Women with more than four prescriptions for hormonal contraceptives in the past two years had an even higher risk.
The Regenstrief tEMR platform provides a realistic virtual patient care experience, enabling early exposure to EMRs and promoting interprofessional collaboration. Over 11,800 students have accessed the system, enhancing their skills in health IT environments.
A new algorithm developed by USC engineers can think and learn like a doctor, suggesting the best diagnostic strategies by mining electronic healthcare records. This could lead to faster, better, and more efficient diagnoses and treatments, complementing human doctors' judgment.
A study compared ICD-10 codes with manual EMR review for capturing COVID-19 symptoms, finding both effective methods. The research aims to improve diagnosis and treatment of respiratory symptoms associated with SARS-CoV-2 infection.
A team of researchers linked genetic information with electronic medical records to identify the impact of genetic epilepsies on affected children's lives. They found associations between specific genes and clinical features, such as seizures and intellectual disability.
A new study found that electronic medical records (EMRs) enhance the education of nephrology fellows, providing efficient access to patient lab and x-ray results. However, EMR data entry time demands contribute to work-hour violations, frustration, and burnout among fellows.
Researchers at Massachusetts General Hospital developed an algorithm to track patients' medical records over time in EHRs to predict disease likelihood. The strategy connects information on medications and diagnoses, revealing accurate disease markers that can be interpreted by clinicians.
A nationwide integrated health system study found hydroxychloroquine did not reduce the risk of ventilation or death, but was associated with longer hospital stays. The study included data from 807 hospitalized patients and analyzed outcomes for COVID-19 treatment with hydroxychloroquine.
A national decline in primary care visits was observed between 2008-2015, with a 20% reduction in visits. However, the decline was accompanied by longer, more comprehensive visits and increased use of non-face-to-face care.