1. Augmented intelligence to predict 30-day mortality in patients with cancer
- Author
-
Shreenath Sridharan, Sibel Blau, Ajeet Gajra, Kelly A Miller, John Showalter, Marjorie E Zettler, Amy W. Valley, John Frownfelter, and Swetha S Venkateshwaran
- Subjects
Adult ,Male ,Cancer Research ,Decision tool ,medicine.medical_specialty ,Palliative care ,Adolescent ,Psychological intervention ,Health records ,Risk Assessment ,Machine Learning ,Young Adult ,03 medical and health sciences ,0302 clinical medicine ,Artificial Intelligence ,Neoplasms ,medicine ,Electronic Health Records ,Humans ,In patient ,030212 general & internal medicine ,Socioeconomic status ,Aged ,Aged, 80 and over ,business.industry ,Reproducibility of Results ,Cancer ,General Medicine ,Middle Aged ,Decision Support Systems, Clinical ,medicine.disease ,Socioeconomic Factors ,Oncology ,30 day mortality ,030220 oncology & carcinogenesis ,Emergency medicine ,Female ,business ,Algorithms - Abstract
Aim: An augmented intelligence tool to predict short-term mortality risk among patients with cancer could help identify those in need of actionable interventions or palliative care services. Patients & methods: An algorithm to predict 30-day mortality risk was developed using socioeconomic and clinical data from patients in a large community hematology/oncology practice. Patients were scored weekly; algorithm performance was assessed using dates of death in patients’ electronic health records. Results: For patients scored as highest risk for 30-day mortality, the event rate was 4.9% (vs 0.7% in patients scored as low risk; a 7.4-times greater risk). Conclusion: The development and validation of a decision tool to accurately identify patients with cancer who are at risk for short-term mortality is feasible.
- Published
- 2021
- Full Text
- View/download PDF