Impact of HbA1c Measurement on Hospital Readmission Rates: Analysis of 70,000 Clinical Database Patient Records

By Beata Strack, J. Deshazo, Chris Gennings, J. L. Olmo, Sebastián Ventura, Krzysztof Jozef Cios, J. Clore. 2014

425 citations recorded by the source corpus.

Management of hyperglycemia in hospitalized patients has a significant bearing on outcome, in terms of both morbidity and mortality. However, there are few national assessments of diabetes care during hospitalization which could serve as a baseline for change. This analysis of a large clinical database (74 million unique encounters corresponding to 17 million unique patients) was undertaken to provide such an assessment and to find future directions which might lead to improvements in patient safety. Almost 70,000 inpatient diabetes encounters were identified with sufficient detail for analysis. Multivariable logistic regression was used to fit the relationship between the measurement of HbA1c and early readmission while controlling for covariates such as demographics, severity and type of the disease, and type of admission. Results show that the measurement of HbA1c was performed infrequently (18.4%) in the inpatient setting. The statistical model suggests that the relationship between the probability of readmission and the HbA1c measurement depends on the primary diagnosis. The data suggest further that the greater attention to diabetes reflected in HbA1c determination may improve patient outcomes and lower cost of inpatient care.

Subfields: Endocrinology, Diabetes and Metabolism

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Scalable Fair Clustering (2019, background): “The dataset 3 represents 10 years of clinical care at 130 US hospitals and in particular represent the information and outcome of patients pertaining to diabetes Strack et al. (2014).”
Data Shapley: Equitable Valuation of Data for Machine Learning (2019, methodology): “In this experiment, we use a balanced subset of the hospital readmission data set (Strack et al., 2014) Fig 5(b) shows that the most valuable groups are also the most important ones for model’s performance.”
A survey on datasets for fairness‐aware machine learning (2021, background): “The diabetes 17 dataset (Strack et al., 2014) described the clinical care at 130 US hospitals and integrated delivery networks from 1999 to 2008.”
Machine Unlearning for Random Forests (2020, background): “• Diabetes (Strack et al., 2014; Dua & Graff, 2019) consists of 101,766 instances of patient and hospital readmission outcomes (46,902 readmitted) characterized by 55 attributes.”
Understanding Black-box Predictions via Influence Functions (2017, methodology): “This involves min- 5The network had 7 sets of convolutional layers with tanh(·) non-linearities, modeled after the all-convolutional network from (Springenberg et al., 2014).”
Fair Algorithms for Clustering (2019, background): “(3) diabetes [53] with 101,766 points, extracted from diabetes patient records.”
On the Privacy Risks of Model Explanations (2019, methodology): “oints below 0.5 are displayed there are 8, mostly for small class sizes. 6.1.2 Diabetic Hospital. The dataset contains data on diabetic patients from 130 US hospitals and integrated delivery networks [33]. We use the modified version described in Koh and Liang[16] where each patient has 127 features”
Privacy Risks of Explaining Machine Learning Models (2019, methodology): “oints below 0.5 are displayed there are 8, mostly for small class sizes. 6.1.2 Diabetic Hospital. The dataset contains data on diabetic patients from 130 US hospitals and integrated delivery networks [33]. We use the modified version described in Koh and Liang[16] where each patient has 127 features”
DART: Data Addition and Removal Trees (2020, positive): “• Diabetes (Strack, DeShazo et al. 2014; Dua and Graff 2019) consists of 101,766 instances of patient and hospital readmission outcomes (46,902 readmitted) characterized by 55 attributes.”
Finding Influential Training Samples for Gradient Boosted Decision Trees (2018, positive): “…evaluation are: (1) Adult Data Set ( Adult , (dat, 1996)), (2) Amazon Employee Access Challenge dataset ( Amazon , (dat, 2013)), (3) the KDD Cup 2009 Upselling dataset ( Upselling , (dat, 2009)) and, for the domain mismatch experiment, (4) the Hospital Read-mission dataset (Strack et al., 2014).”