Development of a risk prediction model of potentially avoidable readmission for patients hospitalised with community-acquired pneumonia: study protocol and population

Abstract

Introduction30-day readmission rate is considered an adverse outcome reflecting suboptimal quality of care during index hospitalisation for community-acquired pneumonia (CAP). However, potentially avoidable readmission would be a more relevant metric than all-cause readmission for tracking quality of hospital care for CAP. The objectives of this study are (1) to estimate potentially avoidable 30-day readmission rate and (2) to develop a risk prediction model intended to identify potentially avoidable readmissions for CAP.Methods and analysisThe study population consists of consecutive patients admitted in two hospitals from the community or nursing home setting with pneumonia. To qualify for inclusion, patients must have a primary or secondary discharge diagnosis code of pneumonia. Data sources include routinely collected administrative claims data as part of diagnosis-related group prospective payment system and structured chart reviews. The main outcome measure is potentially avoidable readmission within 30 days of discharge from index hospitalisation. The likelihood that a readmission is potentially avoidable will be quantified using latent class analysis based on independent structured reviews performed by four panellists. We will use a two-stage approach to develop a claims data-based model intended to identify potentially avoidable readmissions. The first stage implies deriving a clinical model based on data collected through retrospective chart review only. In the second stage, the predictors comprising the medical record model will be translated into International Classification of Diseases, 10th revision discharge diagnosis codes in order to obtain a claim data-based risk model.The study sample consists of 1150 hospital stays with a diagnosis of CAP. 30-day index hospital readmission rate is 17.5%.Ethics and disseminationThe protocol was reviewed by the Comité de Protection des Personnes Sud Est V (IRB#6705). Efforts will be made to release the primary study results within 6 months of data collection completion.Trial registration numberClinicalTrials.gov Registry (NCT02833259).

Relationship Between Start of Feeding and Functional Outcome in Aspiration Pneumonia: A Retrospective Cohort Study

“…Mounayar reported that the readmission rate for community-acquired pneumonia was 17.5%, which was lower than our result [ 14 ]. One reason for this may be the higher readmission rate at our hospital, which is an acute care facility.…”

Machine learning methods to predict 30-day hospital readmission outcome among US adults with pneumonia: analysis of the national readmission database

“…The study cohort was defined using both demographics and clinical-related criteria from prior work involving readmission analysis in a pneumonia setting [6,25,26]. The study cohort included all adult patients (aged ≥ 18 years) who had an index (first) hospitalization from January 1, 2016, through November 31, 2016, with a principal inpatient diagnosis of pneumonia using the International Classification of Diseases, Tenth Revision, codes (J10.0, J10.1, J10.8, J11.0, J11.1, J11.8, J12.0, J12.1, J12.2, J12.3, J12.8, J12.9, J13, J14, J15.x, J16.0, J16.8, J17.0, J17.1, J17.2, J17.3, J17.8, J18.0, J18.1, J18.2, J18.8, J18.9, J69.0, B01.2, B20.6, B25.0, B59) [27,28] between January 1, 2016, and November 30, 2016.…”

“…From all available data elements recorded in the NRD data and based on prior NRD studies involving readmission analysis [6,12], a total of 61 clinically pertinent variables were included for ML model development, including (1) demographics (age, and sex); (2) socioeconomic status (race, expected primary payer, and median household income); (3) healthcare use indicator (number of diagnoses recorded, number of procedures recorded, number of external causes recorded, indicator of emergency service, and indicator of operating room use); (4) comorbid conditions included conditions in the Elixhauser Comorbidity Index [30], and other pneumoniarelated conditions operationalized based on literatures [6,26,31]; (5) composite score (NRD's severity measures classified by the 3M All-Patient Refined Diagnosis-Related Group (DRG) severity score), and Elixhauser comorbidity index score [30]); (6) admission/discharge specific factors (discharge month, resident status, and discharge disposition); (7) hospital-level characteristics (control/ownership of hospital, size of hospital, teaching status of hospital, and hospital urban/rural location). Specifically, baseline comorbid conditions were identified based on AHRQ HCUP Elixhauser Comorbidity Software using ICD-10-CM diagnosis codes [32].…”

Current Trends in Readmission Prediction: An Overview of Approaches

“…Most patient-specific models focused on heart conditions [ 55 – 72 ]. The remaining studies worked on readmission among patients with diabetes [ 73 – 79 ], psychiatric conditions [ 80 – 83 ], TJA [ 84 , 85 ], COPD [ 86 , 87 ], CABG [ 88 , 89 ], and pneumonia [ 90 ].

Fig.

…”

“…Even with the emergence of the ML algorithm, 29 out of 36 articles adopted traditional statistical methods. Among these studies, ~ 90% used LR either as a baseline [ 56 , 58 , 60 , 62 – 64 , 68 , 73 , 74 , 76 – 78 , 83 , 85 – 87 ] or the main model in prediction [ 60 , 69 , 71 , 82 , 88 – 90 ], and 3 studies derived their own risk scores on the basis of LR variable coefficients [ 61 , 66 , 84 ]. In the remaining 3 papers, the prognosis of readmission was carried out with Cox regression survival analysis.…”