MEDICAL EXPRESS - HEALTH INFORMATICS

1. Early detection model for pancreatic necrosis improves patient outcomes

   A new prediction model for infected pancreatic necrosis (IPN) in patients with acute pancreatitis (AP) offers a groundbreaking approach to improving patient outcomes. Developed by a team of researchers across eight Chinese hospitals, the model harnesses five early clinical indicators—respiratory rate, temperature, serum glucose, calcium, and blood urea nitrogen (BUN)—to identify high-risk patients within 24 hours of hospital admission.

2. AI model achieves high accuracy in skin cancer detection

   Led by Aliyu Tetengi Ibrahim and his team at Ahmadu Bello University, a study published in Data Science and Management on November 2, 2024, introduces an innovative AI model that could revolutionize the way dermatologists detect skin cancer.

3. AI tool analyzes medical charts for ADHD follow-up care

   Stanford Medicine researchers have built an artificial intelligence tool that can read thousands of doctors' notes in electronic medical records and detect trends, providing information that physicians and researchers hope will improve care.

4. Machine learning uncovers three osteosarcoma subtypes for targeted treatment

   Researchers have been able to identify at least three distinct subtypes of a rare type of bone cancer for the first time, which could transform clinical trials and patient care.

5. More is not always better: Hospitals can reduce number of hand hygiene observations without affecting data quality

   Hand hygiene (HH) monitoring in hospitals could be reduced significantly, allowing infection preventionists to redirect efforts toward quality improvement and patient safety initiatives, according to a study published in the American Journal of Infection Control.

6. Leveraging AI to assist clinicians with physical exams

   Physical examinations are important diagnostic tools that can reveal critical insights into a patient's health, but complex conditions may be overlooked if a clinician lacks specialized training in that area. While previous research has investigated using large language models (LLMs) as tools to aid in providing diagnoses, their use in physical exams remains untapped.

7. Leading AI chatbots show dementia-like cognitive decline in tests, raising questions about their future in medicine

   Almost all leading large language models or "chatbots" show signs of mild cognitive impairment in tests widely used to spot early signs of dementia, finds a study in the Christmas issue of the BMJ.

8. AI performs well in identifying infantile epileptic spasms

   Deep learning analysis can be used to detect epileptic spasms (ES) from smartphone home videos of young children, according to a study presented at the annual meeting of the American Epilepsy Society, held from Dec. 6 to 10 in Los Angeles.

9. AI-based 'aging clocks' use blood markers to predict health and lifespan

   Researchers at the Institute of Psychiatry, Psychology & Neuroscience (IoPPN) at King's College London have conducted a comprehensive study to evaluate artificial intelligence-based aging clocks, which predict health and lifespan using data from blood.

10. App helps alleviate mental health symptoms in bereaved parents

    A new study shows that an app can help parents who are mourning the loss of a child. Parents who used the app for three months reported reduced symptoms of prolonged grief and post-traumatic stress, and also had fewer negative thoughts. Some parents thought the app should be offered early in the mourning process.

11. New recommendations to increase transparency and tackle potential bias in medical AI technologies

    Patients will be better able to benefit from innovations in medical artificial intelligence (AI) if a new set of internationally-agreed recommendations are followed.

12. Two studies evaluate development of artificial intelligence tools for health care

    Reinforcement Learning, an artificial intelligence approach, has the potential to guide physicians in designing sequential treatment strategies for better patient outcomes but requires significant improvements before it can be applied in clinical settings, finds a new study by Weill Cornell Medicine and Rockefeller University researchers.

13. Imaging company gave its patients' X-rays, CT scans to an AI company without patient consent. How did it happen?

    Australia's biggest radiology provider, I-MED, has provided de-identified patient data to an artificial intelligence company without explicit patient consent, Crikey reported recently. The data were images such as X-rays and CT scans, which were used to train AI.

14. PREVENT equations classify 15 million at elevated risk for heart failure

    The Predicting Risk of Cardiovascular Disease EVENTs (PREVENT) equations classify 15.0 million U.S. adults as having an elevated risk for heart failure, according to a research letter published online Dec. 17 in the Annals of Internal Medicine.

15. Researchers examine the legal and ethical aspects of AI in radiology

    Bart Custers and Eduard Fosch-Villaronga from eLaw–Center for Law and Digital Technologies have contributed a chapter to the volume "AI Implementation in Radiology: Challenges and Opportunities in Clinical Practice."

16. Optimized model predicts mental resilience in college students

    A new model developed to predict mental resilience in college students could have significant implications for how universities address the growing mental health challenges facing this demographic.

17. Emotional cognition analysis enables near-perfect Parkinson's detection

    A joint research team from the University of Canberra and Kuwait College of Science and Technology has achieved groundbreaking detection of Parkinson's disease with near-perfect accuracy, simply by analyzing brain responses to emotional situations like watching video clips or images.

18. AI tool analyzes placentas at birth for faster detection of neonatal and maternal problems

    A newly developed tool that harnesses computer vision and artificial intelligence (AI) may help clinicians rapidly evaluate placentas at birth, potentially improving neonatal and maternal care, according to new research from scientists at Northwestern Medicine and Penn State.

19. AI-powered blood test can spot earliest sign of breast cancer

    A new screening method that combines laser analysis with a type of AI is the first of its kind to identify patients in the earliest stage of breast cancer, a study suggests.

20. Clinicians' phones a cybersecurity risk, says study

    A new study led by Dr. Tafheem Wani, a La Trobe lecturer in Digital Health Information Management, showed that clinicians' phones (and other digital devices) contained sensitive patient information, which was not often protected by antivirus software and passcodes.

21. New home testing protocol could reduce the number of women recalled for clinician-collected cervical sampling

    A new protocol for the analysis of self-collected cervical samples could reduce the need for follow-up clinician screening for many women, and result in more rapid referral for gynecology assessment for others. This could improve cervical cancer screening procedures in the NHS.

22. Machine learning model predicts breast cancer treatment response

    A machine learning (ML) model incorporating both clinical and genomic factors outperformed models based solely on either clinical or genomic data in predicting which patients with hormone receptor (HR)-positive, HER2-negative metastatic breast cancer would have better outcomes from adding CDK4/6 inhibitors to endocrine therapy as first-line treatment, according to results presented at the San Antonio Breast Cancer Symposium (SABCS), held December 10–13, 2024.

23. AI's role in cancer research: Review highlights advantages and limitations

    Significant advancements in understanding the molecular and cellular mechanisms of tumor progression have been made, yet challenges remain. Traditional imaging techniques like MRI, CT, and mammography are limited by the need for professional curation, which is time-consuming.

24. AI enhances mammography for better breast cancer risk prediction

    The future of breast cancer screening and risk-reducing strategies is being shaped by artificial intelligence (AI), according to a review article published on December 12 in the journal Trends in Cancer.

25. AI-based tool offers exciting advancement in pancreatic cancer diagnostics

    Researchers have successfully developed a deep learning model that classifies pancreatic ductal adenocarcinoma (PDAC), the most common form of pancreatic cancer, into molecular subtypes using histopathology images. This approach achieves high accuracy and offers a rapid, cost-effective alternative to current methods that rely on expensive molecular assays.

26. A blood test may be a more reliable indicator of liver disease than asking how much a person drinks

    A new study finds that a blood test may be a more reliable indicator of liver disease than asking how much a person drinks.

27. App creates time-lapse videos of the body for telemedicine

    A new app developed by Cornell researchers helps users record highly accurate time-lapse videos of body parts—a surprisingly difficult task and an unmet need in remote medicine and telehealth applications.

28. Study shows deep learning model accurately diagnoses COPD

    Using just one inhalation lung CT scan, a deep learning model can accurately diagnose and stage chronic obstructive pulmonary disease (COPD), according to a study published in Radiology: Cardiothoracic Imaging.

29. Proteomics and AI unite for a new era in medicine and health care

    Children's Medical Research Institute (CMRI) scientists are part of an ambitious new program that aims to use a combination of proteomics and AI to contribute to a new era of medicine and intelligent health care. To succeed, an international consortium mobilizing hundreds of cutting-edge expert teams from academia, government and industrial health sectors will be required.

30. COMET trial finds active monitoring is a viable option for some patients with low-risk DCIS

    Among patients with hormone receptor (HR)-positive, HER2-negative, low-risk ductal carcinoma in situ (DCIS), those who underwent active monitoring had similar two-year invasive ipsilateral breast cancer recurrence rates as those who underwent guideline-concordant treatment, according to results from the COMET clinical trial presented at the San Antonio Breast Cancer Symposium (SABCS), held December 10–13, 2024.