Browsing by Subject "disease severity"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Automated Assessment of Psychiatric Patients Using Medical Notes
    (2022-12) Wang, Shuo; Miled, Zina Ben; King, Brain; Lee, John
    Psychiatric patients require continuous monitoring on par with their severity status. Unfortunately, current assessment instruments are often time-consuming. The present thesis introduces several passive digital markers (PDMs) that can help reduce this burden by automating the assessment using medical notes. The methodology leverages medical notes already annotated according to the General Assessment of Functioning (GAF) scale to develop a disease severity PDM for schizophrenia, bipolar type I or mixed bipolar and non-psychotic patients. Topic words that are representative of three disease severity levels (severe impairment, serious impairment, moderate to no impairment) are identified and the top 50 words from each severity level are used to summarize the raw text of the medical notes. The summary of the text is processed by a classifier that generates a disease severity level. Two classifiers are considered: BERT PDM and Clinical BERT PDM. The evaluation of these classifiers showed that the BERT PDM delivered the best performance. The PDMs developed using the BERT PDM can assign medical notes from each encounter to a severe impairment level with a positive predictive value higher than 0.84. These PDMs are generalizable and their development was facilitated by the availability of a substantial number of medical notes from multiple institutions that were annotated by several health care providers. The methodology introduced in the present thesis can support the automated monitoring of the progression of the disease severity for psychiatric patients by digitally processing the medical note produced at each encounter without additional burden on the health care system. Applying the same methodology to other diseases is possible subject to availability of the necessary data.
  • Thumbnail Image
    Item
    Predictors of Disease Severity in Children at Riley Hospital with Multisystem Inflammatory Syndrome in Children (MIS-C)
    (2021-07-30) Collins, Angela J.; Rao, Megana; Khaitan, Alka K.; Bhumbra, Samina S.
    AUTHORS: Angela J. Collins, MPH, BS(1); Megana Rao, BS(1); Alka K. Khaitan, MD(2); Samina S. Bhumbra, MD(2) AFFILIATIONS: (1) Indiana University School of Medicine. (2) Ryan White Center for Pediatric Infectious Disease and Global Health, Department of Pediatrics, Indiana University School of Medicine, Indianapolis, Indiana. ABSTRACT: BACKGROUND & OBJECTIVE: Multisystem Inflammatory Syndrome in Children (MIS-C) is a novel condition temporally associated post-SARS-CoV-2-infection. The associated inflammation injures various organs (mainly cardiac and gastrointestinal) and can cause ventricular dysfunction and/or coronary aneurysms, potentially leading to death. This project assessed how lab trends may predict disease outcomes of MIS-C patients at Riley Hospital for Children (RHC). METHODS: Five lab values (intake procalcitonin, platelet count nadir, absolute lymphocyte count nadir, sodium nadir, troponin-I peak, CRP peak) were assessed as potential predictors of MIS-C severity. Patient demographics (age, sex, race, ethnicity), prior medical history (chronic conditions, obesity), and clinical presentation (days of fever prior to admission) were also assessed as potential predictors of MIS-C severity and lab peaks/nadirs. Indicators of MIS-C severity included PICU admission, length of hospital stay, left ventricular ejection fraction (EF), and abnormal coronary artery findings on echocardiogram. Chi-Square, ANOVA, linear regression, and logistic regression models were completed in SAS9.4 to assess for correlation (α=0.05). RESULTS: 66 MIS-C patients, aged 9 months to 18 years (mean=8.7 years), were admitted to RHC May 2020-April 2021. 61% were male (n=41). All patients presented with fever. Average length of stay at RHC was 5.9 days. 47% (n=31) were admitted directly to the PICU and 15% (n=10) were transferred to the PICU during their hospital course. Race predicted sodium nadir (p=0.0363), ethnicity predicted intake procalcitonin (p=0.0007), and obesity predicted CRP peak (p=0.0055). Age predicted abnormal EF (p=0.0206) and abnormal coronary outcome on echocardiogram (p=0.0365). Sex and obesity also predicted abnormal coronary outcome on echocardiogram (p=0.0182 and p=0.0478, respectively). Troponin-I peak predicted abnormal EF (p=0.0035) and CRP peak predicted days of hospital stay (p=0.0096). CONCLUSION & IMPACT: CRP peak is predictive of days of hospital stay and may inform hospital course. Analysis of additional lab values may reveal additional predictors of disease severity to inform clinical care.