Development of a personalized diagnostic model for kidney stone disease tailored to acute care by integrating large clinical, demographics and laboratory data: the diagnostic acute care algorithm - kidney stones (DACA-KS)

Abstract

Background: Kidney stone (KS) disease has high, increasing prevalence in the United States and poses a massive economic burden. Diagnostics algorithms of KS only use a few variables with a limited sensitivity and specificity. In this study, we tested a big data approach to infer and validate a 'multi-domain' personalized diagnostic acute care algorithm for KS (DACA-KS), merging demographic, vital signs, clinical, and laboratory information.

Methods: We utilized a large, single-center database of patients admitted to acute care units in a large tertiary care hospital. Patients diagnosed with KS were compared to groups of patients with acute abdominal/flank/groin pain, genitourinary diseases, and other conditions. We analyzed multiple information domains (several thousands of variables) using a collection of statistical and machine learning models with feature selectors. We compared sensitivity, specificity and area under the receiver operating characteristic (AUROC) of our approach with the STONE score, using cross-validation.

Results: Thirty eight thousand five hundred and ninety-seven distinct adult patients were admitted to critical care between 2001 and 2012, of which 217 were diagnosed with KS, and 7446 with acute pain (non-KS). The multi-domain approach using logistic regression yielded an AUROC of 0.86 and a sensitivity/specificity of 0.81/0.82 in cross-validation. Increase in performance was obtained by fitting a super-learner, at the price of lower interpretability. We discussed in detail comorbidity and lab marker variables independently associated with KS (e.g. blood chloride, candidiasis, sleep disorders).

Conclusions: Although external validation is warranted, DACA-KS could be integrated into electronic health systems; the algorithm has the potential used as an effective tool to help nurses and healthcare personnel during triage or clinicians making a diagnosis, streamlining patients' management in acute care.

Keywords: Big data analysis; Diagnostic algorithm; Kidney stones.

Fig. 1

Distributions of age categories by gender, CCI and BMI in KS, GUD, OTH and ALP groups

Fig. 2

Prevalence of the top-10 most frequent ICD-9 diagnoses in KS, GUD, OTH and ALP groups

Fig. 3

Model comparison via AUROC. Legend: Left panels: kidney stone (KS) formers vs. other genitourinary diseases (GUD); middle panels: KS vs. other non-genitourinary (OTH) conditions; right panels: KS vs. acute localized pain (ALP) in the abdomen, back, flank, or groin. Top panels: logistic regression models upon stepwise feature selection, fit on selected input domains; Bottom panels: comparison of machine learning techniques on the full input set. Curves shown are averaged over 10-fold cross-validation, i.e. using the test sets

Fig. 4

Decision tree for the diagnosis of KS patients vs. ALP patients Legend: Each leaf node contains the predicted class (1 if KS, 0 if ALP) and the numbers between parentheses indicate total number of instances (first number) reaching the leaf, and the number of those instances that are misclassified (second number).