20 Most of the variables included in the model were selected from among those routinely measured in patients referred for BME, on the basis of their known association with MDS. The clinical and laboratory variables listed in Table 1 (age, sex, Hb, MCV, WBC, PLT, neutrophil and monocyte counts, serum glucose and creatinine) were entered as explanatory variables into a logistic GBM, 18, 19 with case (MDS patients) or control (patient with MDS excluded) status as outcome, using the R package gbm. A Web app has been developed that would help a clinician diagnose, and especially rule out, MDS noninvasively, without BM examination, in ≈86% of patients. 16, 17 Here, we have improved the method using the new GBM, more variables, and many more patients. The model was improved by increasing the number of studied individuals, adding more variables, and using a more appropriate model, the gradient-boosted model (GBM). Approximately 50% of the patients could be classified as either pMDS or pnMDS. 15 We performed internal validation with a new set of patients.
Using a logistic regression model, we were able to classify patients into 1 of 3 categories: probable MDS (pMDS), probably not MDS (pnMDS), and indeterminate.
In our previous work, we introduced a formula that incorporated 6 clinical variables (age, sex, hemoglobin, mean corpuscular volume, white blood cells, and platelets ). We have developed an algorithm to help in the diagnosis or exclusion of MDS based on demographic, clinical, and laboratory parameters that would obviate, in many patients, the need for a BM examination. Future work will add peripheral blood cytogenetics/genetics, EUMDS-based prospective validation, and prognostication. A Web-based app was developed physicians could use it to exclude or predict MDS noninvasively in most patients without a BM examination. The discriminating variables: age, sex, hemoglobin, white blood cells, platelets, mean corpuscular volume, neutrophils, monocytes, glucose, and creatinine. The diagnosis of the remaining patients (0.68 ≤ GBM < 0.82) is indeterminate. GBM ≥ 0.82 provided a positive predictive value of 0.88, that is, MDS.
A GBM score (range, 0-1) of less than 0.68 (GBM < 0.68) resulted in a negative predictive value of 0.94, that is, MDS was excluded. MDS is predicted/excluded accurately in 86% of patients with unexplained anemia. Model stability was assessed by repeating its fit using different randomly chosen groups of 502 EUMDS cases. Area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were used to evaluate the models, and performance was validated using 100 times fivefold cross-validation. Gradient-boosted models (GBMs) were used to predict/exclude MDS using demographic, clinical, and laboratory variables. A sample of 502 MDS patients from the European MDS (EUMDS) registry (n > 2600) was combined with 502 controls (all BM proven). Alt+Right returns you to the header file.We present a noninvasive Web-based app to help exclude or diagnose myelodysplastic syndrome (MDS), a bone marrow (BM) disorder with cytopenias and leukemic risk, diagnosed by BM examination. Immediately after the create, Alt+Left returns you to the source file. Use the Navigate commands of Visual Assist to jump between the header file and source file after Create Declaration. You must expose or add default parameters manually. Use copy and paste to move the declaration to a different file.Ĭreate Declaration does not expose default parameters if they are commented or not specified in the implementation. If an appropriate header file for a declaration cannot be found, the declaration is placed in the source file. While the caret is over a method definition, select Create Declaration from the VAssistX menu (Alt+X, R, C) or the Quick Action and Refactoring menu (Shift+Alt+Q).Ī declaration is placed in an appropriate header file near declarations of neighboring methods. The declaration is placed in a header file, and parameters in the declaration and implementation are consistent.
#Visual assist x automatic addition of params code#