Department of Pediatrics, Section of Critical Care Medicine, University of Colorado School of Medicine and Children's Hospital Colorado, Aurora, CO.
Department of Pediatrics, Section of Critical Care, University of Arkansas for Medical Sciences and Arkansas Children's, Little Rock, AR.
Pediatr Crit Care Med. 2022 Apr 1;23(4):e189-e198. doi: 10.1097/PCC.0000000000002909. Epub 2022 Mar 7.
To identify postdischarge outcome phenotypes and risk factors for poor outcomes using insurance claims data.
Retrospective cohort study.
Single quaternary center.
Children without preexisting tracheostomy who required greater than or equal to 3 days of invasive mechanical ventilation, survived the hospitalization, and had postdischarge insurance eligibility in Colorado's All Payer Claims Database.
None.
We used unsupervised machine learning to identify functional outcome phenotypes based on claims data representative of postdischarge morbidities. We assessed health trajectory by comparing change in the number of insurance claims between quarters 1 and 4 of the postdischarge year. Regression analyses identified variables associated with unfavorable outcomes. The 381 subjects had median age 3.3 years (interquartile range, 0.9-12 yr), and 147 (39%) had a complex chronic condition. Primary diagnoses were respiratory (41%), injury (23%), and neurologic (11%). We identified three phenotypes: lower morbidity (n = 300), higher morbidity (n = 62), and 1-year nonsurvivors (n = 19). Complex chronic conditions most strongly predicted the nonsurvivor phenotype. Longer PICU stays and tracheostomy placement most strongly predicted the higher morbidity phenotype. Patients with high but improving postdischarge resource use were differentiated by high illness severity and long PICU stays. Patients with persistently high or increasing resource use were differentiated by complex chronic conditions and tracheostomy placement.
New morbidities are common after prolonged mechanical ventilation. Identifying phenotypes at high risk of postdischarge morbidity may facilitate prognostic enrichment in clinical trials.
利用保险索赔数据确定出院后结局表型和不良结局的危险因素。
回顾性队列研究。
单四级中心。
无预先存在的气管造口术且需要大于或等于 3 天的有创机械通气，住院期间存活且在科罗拉多州所有支付者索赔数据库中有出院后保险资格的儿童。
无。
我们使用无监督机器学习方法根据出院后发病率的保险索赔数据确定功能结局表型。我们通过比较出院后年度的第 1 季度和第 4 季度之间保险索赔数量的变化来评估健康轨迹。回归分析确定了与不良结局相关的变量。381 名患者的中位年龄为 3.3 岁（四分位距，0.9-12 岁），147 名（39%）患有复杂的慢性疾病。主要诊断为呼吸系统（41%）、损伤（23%）和神经系统（11%）。我们确定了三种表型：低发病率（n = 300）、高发病率（n = 62）和 1 年非幸存者（n = 19）。复杂的慢性疾病最强烈地预测了非幸存者表型。较长的 PICU 住院时间和气管造口术的放置最强烈地预测了较高发病率的表型。高但改善的出院后资源利用的患者通过高疾病严重程度和长 PICU 住院时间来区分。持续高或增加的资源利用的患者通过复杂的慢性疾病和气管造口术的放置来区分。
长时间机械通气后新发病是常见的。确定具有高出院后发病率风险的表型可能有助于临床试验中的预后富集。
