Publications by authors named "S F Nowakowski"
Purpose: Performance status (PS), an essential indicator of patients' functional abilities, is often documented in clinical notes of patients with cancer. The use of natural language processing (NLP) in extracting PS from electronic medical records (EMRs) has shown promise in enhancing clinical decision-making, patient monitoring, and research studies. We designed and validated a multi-institute NLP pipeline to automatically extract performance status from free-text patient notes.
View Article and Find Full Text PDFArticle Synopsis
- Knotted proteins are important structural components in some protein families, leading researchers to explore their roles and characteristics using the UniProt database and AlphaFold's predictions.
- A machine learning model was successfully developed to predict knotted structures based solely on amino acid sequences, showing high accuracy (92%) on unpredicted proteins.
- The study identified 17 families of potentially knotted proteins, discovered three new families containing both knotted and unknotted proteins, and confirmed that many knotted proteins maintain their topology across sequences with low similarity, while unknotted proteins generally represent nonfunctional fragments.
Article Synopsis
- - The study focused on understanding how sleep disturbances in COPD patients affect quality of life and predict mortality risk using data from the Veterans Health Administration.
- - Researchers identified five unique clusters of COPD patients based on factors like age, comorbidity, and specific sleep metrics, revealing that mortality risk varied significantly among these groups.
- - Results showed a clear link between total sleep time and sleep efficiency with overall mortality, emphasizing the importance of objective sleep data for identifying mortality risk in COPD patients.
Menstruating individuals experience an increased risk for sleep and affective disorders, attributed in part to monthly oscillations in sex hormones. Emotional functioning and sleep continuity worsens during the perimenstrual phase of the menstrual cycle. This study examined the interactive effects of sleep, menstrual phase, and emotion in healthy women.
View Article and Find Full Text PDFArticle Synopsis
- * The study utilized deep neural networks to analyze resting Doppler arterial waveforms from DM patients to predict all-cause mortality, major adverse cardiac events (MACE), and limb events (MALE) over five years.
- * Results indicated that patients in the highest prediction quartile (based on their arterial waveforms) had significantly increased risk for death, MACE, and MALE, highlighting the usefulness of this AI-based approach in clinical settings.