Browsing by Author "King, Nicholas"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Current state of cardiac troponin testing in Duchenne muscular dystrophy cardiomyopathy: review and recommendations from the Parent Project Muscular Dystrophy expert panel
    (BMJ, 2021) Spurney, Christopher F.; Ascheim, Deborah; Charnas, Lawrence; Cripe, Linda; Hor, Kan; King, Nicholas; Kinnett, Kathi; McNally, Elizabeth M.; Sauer, John-Michael; Sweeney, Lee; Villa, Chet; Markham, Larry W.; Pediatrics, School of Medicine
    Cardiac disease is now the leading cause of death in Duchenne muscular dystrophy (DMD). Clinical evaluations over time have demonstrated asymptomatic cardiac troponin elevations and acute elevations are associated with symptoms and cardiac dysfunction in DMD. Clinicians require a better understanding of the relationship of symptoms, troponin levels and progression of cardiac disease in DMD. As clinical trials begin to assess novel cardiac therapeutics in DMD, troponin levels in DMD are important for safety monitoring and outcome measures. The Parent Project Muscular Dystrophy convened an expert panel of cardiologists, scientists, and regulatory and industry specialists on 16 December 2019 in Silver Spring, Maryland and reviewed published and unpublished data from their institutions. The panel recommended retrospective troponin data analyses, prospective longitudinal troponin collection using high-sensitivity cardiac troponin I assays, inclusion of troponin in future clinical trial outcomes and future development of clinical guidelines for monitoring and treating troponin elevations in DMD.
  • Thumbnail Image
    Item
    Predicting misdiagnosed adult-onset type 1 diabetes using machine learning
    (Elsevier, 2022) Cheheltani, Rabee; King, Nicholas; Lee, Suyin; North, Benjamin; Kovarik, Danny; Evans-Molina, Carmella; Leavitt, Nadejda; Dutta, Sanjoy; Pediatrics, School of Medicine
    Aims: It is now understood that almost half of newly diagnosed cases of type 1 diabetes are adult-onset. However, type 1 and type 2 diabetes are difficult to initially distinguish clinically in adults, potentially leading to ineffective care. In this study a machine learning model was developed to identify type 1 diabetes patients misdiagnosed as type 2 diabetes. Methods: In this retrospective study, a machine learning model was developed to identify misdiagnosed type 1 diabetes patients from a population of patients with a prior type 2 diabetes diagnosis. Using Ambulatory Electronic Medical Records (AEMR), features capturing relevant information on age, demographics, risk factors, symptoms, treatments, procedures, vitals, or lab results were extracted from patients' medical history. Results: The model identified age, BMI/weight, therapy history, and HbA1c/blood glucose values among top predictors of misdiagnosis. Model precision at low levels of recall (10 %) was 17 %, compared to <1 % incidence rate of misdiagnosis at the time of the first type 2 diabetes encounter in AEMR. Conclusions: This algorithm shows potential for being translated into screening guidelines or a clinical decision support tool embedded directly in an EMR system to reduce misdiagnosis of adult-onset type 1 diabetes and implement effective care at the outset.