Identifying acute illness phenotypes via deep temporal interpolation and clustering network on physiologic signatures

• Published in: Scientific reports 2024-04, Vol.14 (1), p.8442-8442, Article 8442
• Main Authors: Ren, Yuanfang, Li, Yanjun, Loftus, Tyler J., Balch, Jeremy, Abbott, Kenneth L., Ruppert, Matthew M., Guan, Ziyuan, Shickel, Benjamin, Rashidi, Parisa, Ozrazgat-Baslanti, Tezcan, Bihorac, Azra
• Format: Article
• Language: English
• Subjects: 692/700; 692/700/478; Acuity; Acute Disease; Biomarkers; Clinical outcomes; Cluster Analysis; Decision making; Genotype & phenotype; Humanities and Social Sciences; Humans; Hypotension; Mortality; multidisciplinary; Organ Dysfunction Scores; Phenotype; Phenotypes; Phenotyping; Science; Science (multidisciplinary); Sepsis
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-59047-x

Using clustering analysis for early vital signs, unique patient phenotypes with distinct pathophysiological signatures and clinical outcomes may be revealed and support early clinical decision-making. Phenotyping using early vital signs has proven challenging, as vital signs are typically sampled sporadically. We proposed a novel, deep temporal interpolation and clustering network to simultaneously extract latent representations from irregularly sampled vital signs and derive phenotypes. Four distinct clusters were identified. Phenotype A (18%) had the greatest prevalence of comorbid disease with increased prevalence of prolonged respiratory insufficiency, acute kidney injury, sepsis, and long-term (3-year) mortality. Phenotypes B (33%) and C (31%) had a diffuse pattern of mild organ dysfunction. Phenotype B’s favorable short-term clinical outcomes were tempered by the second highest rate of long-term mortality. Phenotype C had favorable clinical outcomes. Phenotype D (17%) exhibited early and persistent hypotension, high incidence of early surgery, and substantial biomarker incidence of inflammation. Despite early and severe illness, phenotype D had the second lowest long-term mortality. After comparing the sequential organ failure assessment scores, the clustering results did not simply provide a recapitulation of previous acuity assessments. This tool may impact triage decisions and have significant implications for clinical decision-support under time constraints and uncertainty.