MEDICAL EXPRESS - HEALTH INFORMATICS

1. Team develops computational approach to redesign antibodies for broader effectiveness against viral pandemics

   In a new development for addressing future viral pandemics, a multi-institutional team involving Lawrence Livermore National Laboratory (LLNL) researchers has successfully combined an artificial intelligence (AI)-backed platform with supercomputing to redesign and restore the effectiveness of antibodies whose ability to fight viruses has been compromised by viral evolution.

2. Biomarkers + patient-reported outcomes up prediction of interstitial cystitis

   The integration of biomarkers and patient-reported outcomes (PROs) improves prediction of interstitial cystitis (IC)/bladder pain syndrome, according to a study published online April 24 in Urology.

3. Using AI and social media to track depression in communities could offer more reliable assessments than surveys

   A study that used artificial intelligence (AI) and social media posts to assess the rates of depression and anxiety in nearly half of American counties found that the AI-generated measurements produced more reliable assessments than population surveys.

4. AI may help physicians detect abnormal heart rhythms earlier

   An artificial intelligence program developed by investigators in the Smidt Heart Institute and their Cedars-Sinai colleagues can detect a type of abnormal heart rhythm that can go unnoticed during medical appointments, according to a new study.

5. Researchers use foundation models to discover new cancer imaging biomarkers

   Researchers at Mass General Brigham have harnessed the technology behind foundation models, which power tools like ChatGPT, to discover new cancer imaging biomarkers that could transform how patterns are identified from radiological images. Improved identification of such patterns can greatly impact the early detection and treatment of cancer.

6. AI predicts tumor-killing cells with high accuracy, study shows

   Using artificial intelligence, Ludwig Cancer Research scientists have developed a powerful predictive model for identifying the most potent cancer-killing immune cells for use in cancer immunotherapies.

7. Study finds AI is as good as a physician at prioritizing which patients need to be seen first

   Emergency departments nationwide are overcrowded and overtaxed, but a new study suggests artificial intelligence (AI) could one day help prioritize which patients need treatment most urgently.

8. Study identifies signifiers of severe COVID-19 disease and death

   Why do some people with COVID-19 experience little more than a sniffle while others end up on a ventilator? And among critically ill patients, why do some eventually recover while others do not?

9. Measuring differential privacy could balance meaningful analytics and health care data security

   In industries such as health care, where data generation grows by 47% each year, information collected within electronic health records could help inform more efficient care operations or more accurate diagnoses. However, personal health data is highly protected and largely goes untouched by analysts and researchers.

10. Online patient portal usage increasing, study shows

    More people are using online patient portals to view their information while in the emergency room, but access is challenging for members of medically underserved communities and the elderly, UT Southwestern Medical Center researchers and national colleagues found in a new study.

11. Benefit of thick liquids in Alzheimer disease and dysphagia unclear

    For hospitalized patients with Alzheimer disease and related dementias (ADRD) and dysphagia, those receiving thick liquids are less likely to be intubated but have no difference in hospital mortality compared with those receiving thin liquids, according to a study published online May 6 in JAMA Internal Medicine.

12. Text message outreach can help increase mammogram completion rates

    Text messaging women after initial outreach for breast cancer screening increases mammogram completion rates, according to a study published online May 6 in JAMA Internal Medicine.

13. Women and Black patients less likely to receive catheter-based treatment for pulmonary embolism

    New data from the REAL-PE analysis investigated catheter-based pulmonary embolism (PE) treatment, showing women and Black people were less frequently treated with minimally invasive therapy compared to men or non-Black patients. The late-breaking results were presented today at the Society for Cardiovascular Angiography & Interventions (SCAI) 2024 Scientific Sessions.

14. Study shows ChatGPT can be helpful for Black women's self-education about HIV, PrEP

    The artificial intelligence (AI) chatbot called ChatGPT is a powerful way for Black women to educate themselves about HIV prevention, as it provides reliable and culturally sensitive information, according to a study in The Journal of the Association of Nurses in AIDS Care.

15. Gene expression and bioinformatics tools to optimize cancer therapy

    In the field of biomedical research and genomics, the advancement of bioinformatics technologies and tools is opening new frontiers in the understanding of diseases and their diagnosis and treatment. In particular, differential gene expression analysis (DGE) is emerging as a crucial technique to investigate the molecular mechanisms underlying diseases.

16. ChatGPT found to display lower concern for child development 'warning signs' than physicians

    Artificial intelligence (AI) tool ChatGPT displayed lower concern than physicians in 36% of potential developmental delays, according to a new study. The research will be presented at the Pediatric Academic Societies (PAS) 2024 Meeting, held May 2–6 in Toronto.

17. Banking behavior could be used to detect early Alzheimer's, finds new research

    Alzheimer's Disease can be detected years in advance of a clinical diagnosis by monitoring how people manage their finances, according to new research.

18. More efficient ways to monitor patient vital signs developed in NHS hospitals

    Investigators have published the findings of a four-year study looking at how often hospital patients should have their vital signs monitored by staff.

19. AI can tell if a patient battling cancer needs mental health support

    Researchers at UBC and BC Cancer have developed a new artificial intelligence (AI) model that can accurately predict if a person receiving cancer care will require mental health services during their treatment journey.

20. Four state-of-the-art AI search engines for histopathology images may not be ready for clinical use

    Four proposed state-of-the art image search engines for automating search and retrieval of digital histopathology slides were found to be of inadequate performance for routine clinical care, new research suggests.

21. Machine learning tool identifies rare, undiagnosed immune disorders through patients' electronic health records

    Researchers say a machine learning tool can identify many patients with rare, undiagnosed diseases years earlier than current methods, potentially improving outcomes and reducing cost and morbidity. The findings, led by researchers at UCLA Health, are described in Science Translational Medicine.

22. Study finds ChatGPT fails at heart risk assessment

    Despite ChatGPT's reported ability to pass medical exams, new research indicates it would be unwise to rely on it for some health assessments, such as whether a patient with chest pain needs to be hospitalized.

23. With huge patient dataset, AI accurately predicts treatment outcomes

    Scientists have designed a new artificial intelligence model that emulates randomized clinical trials to determine the treatment options most effective at preventing stroke in people with heart disease.

24. Mobility may have dose-response relationship with ICU patient outcomes

    More out-of-bed mobility interventions for critically ill patients were associated with shorter mechanical ventilation duration and hospital stays, suggesting a dose-response relationship between daily mobility and patient outcomes, according to a study published in the American Journal of Critical Care.

25. AI experts explore ethical use of video technology to support patients at risk of falls

    Video-enabled glasses have the potential to support patients at risk of falls by allowing medical staff to monitor how they move around their homes and their community. However, with privacy concerns at the forefront of this new technology, academics at Northumbria University have carried out a cutting-edge study into the ethical use of AI to ensure video footage can be obscured to ensure patient privacy.

26. Cardiologists train large AI model to assess heart structure, function

    Artificial intelligence experts at Cedars-Sinai and the Smidt Heart Institute created a dataset with more than 1 million echocardiograms, or cardiac ultrasound videos, and their corresponding clinical interpretations. Using this database, they created EchoCLIP, a powerful machine learning algorithm that can "interpret" echocardiogram images and assess key findings.

27. Deep-learning decoding for a noninvasive brain-computer interface

    Brain-computer interfaces (BCIs) have the potential to make life easier for people with motor or speech disorders, allowing them to manipulate prosthetic limbs and employ computers, among other uses. In addition, healthy and impaired people alike could enjoy BCI-based gaming.

28. Study gauges effectiveness of COVID-19 burden mitigation policies

    In a new study published in JAMA Network Open, researchers have created a dataset and data visualization dashboard to evaluate the effectiveness of state and territory-level policies enacted to reduce the severity of COVID-19's impact on older people served by home health care agencies and nursing homes.

29. GPT-4, Google Gemini fall short in breast imaging classification, study finds

    Use of publicly available large language models (LLMs) resulted in changes in breast imaging reports classification that could have a negative effect on patient management, according to a new international study published in the journal Radiology. The study findings underscore the need to regulate these LLMs in scenarios that require high-level medical reasoning, researchers said.

30. AI algorithms can determine how well newborns nurse, study shows

    A modified pacifier and AI algorithms to analyze the data it produces could determine if newborns are learning the proper mechanics of nursing, a recent study shows.