A predictive algorithm using clinical and laboratory parameters may assist in ruling out and in diagnosing MDS.

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. A sample of 502 MDS patients from the European MDS (EUMDS) registry (n > 2600) was combined with 502 controls (all BM proven). Gradient-boosted models (GBMs) were used to predict/exclude MDS using demographic, clinical, and laboratory variables. 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. Model stability was assessed by repeating its fit using different randomly chosen groups of 502 EUMDS cases. AUC was 0.96 (95% confidence interval, 0.95-0.97). MDS is predicted/excluded accurately in 86% of patients with unexplained anemia. 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. GBM ≥ 0.82 provided a positive predictive value of 0.88, that is, MDS. The diagnosis of the remaining patients (0.68 ≤ GBM < 0.82) is indeterminate. The discriminating variables: age, sex, hemoglobin, white blood cells, platelets, mean corpuscular volume, neutrophils, monocytes, glucose, and creatinine. A Web-based app was developed; physicians could use it to exclude or predict MDS noninvasively in most patients without a BM examination. Future work will add peripheral blood cytogenetics/genetics, EUMDS-based prospective validation, and prognostication.

A game theoretic approach reveals that discretizing clinical information can reduce antibiotic misuse.

The overuse of antibiotics is exacerbating the antibiotic resistance crisis. Since this problem is a classic common-goods dilemma, it naturally lends itself to a game-theoretic analysis. Hence, we designed a model wherein physicians weigh whether antibiotics should be prescribed, given that antibiotic usage depletes its future effectiveness. The physicians' decisions rely on the probability of a bacterial infection before definitive laboratory results are available. We show that the physicians' equilibrium decision rule of antibiotic prescription is not socially optimal. However, we prove that discretizing the information provided to physicians can mitigate the gap between their equilibrium decisions and the social optimum of antibiotic prescription. Despite this problem's complexity, the effectiveness of the discretization solely depends on the type of information available to the physician to determine the nature of infection. This is demonstrated on theoretic distributions and a clinical dataset. Our results provide a game-theory based guide for optimal output of current and future decision support systems of antibiotic prescription.

Predicting Antibiotic Resistance in Hospitalized Patients by Applying Machine Learning to Electronic Medical Records.

BACKGROUND: Computerized decision support systems are becoming increasingly prevalent with advances in data collection and machine learning (ML) algorithms. However, they are scarcely used for empiric antibiotic therapy. Here, we predict the antibiotic resistance profiles of bacterial infections of hospitalized patients using ML algorithms applied to patients' electronic medical records (EMRs). METHODS: The data included antibiotic resistance results of bacterial cultures from hospitalized patients, alongside their EMRs. Five antibiotics were examined: ceftazidime (n = 2942), gentamicin (n = 4360), imipenem (n = 2235), ofloxacin (n = 3117), and sulfamethoxazole-trimethoprim (n = 3544). We applied lasso logistic regression, neural networks, gradient boosted trees, and an ensemble that combined all 3 algorithms, to predict antibiotic resistance. Variable influence was gauged by permutation tests and Shapely Additive Explanations analysis. RESULTS: The ensemble outperformed the separate models and produced accurate predictions on test set data. When no knowledge regarding the infecting bacterial species was assumed, the ensemble yielded area under the receiver-operating characteristic (auROC) scores of 0.73-0.79 for different antibiotics. Including information regarding the bacterial species improved the auROCs to 0.8-0.88. Variables' effects on predictions were assessed and found to be consistent with previously identified risk factors for antibiotic resistance. CONCLUSIONS: We demonstrate the potential of ML to predict antibiotic resistance of bacterial infections of hospitalized patients. Moreover, we show that rapidly gained information regarding the infecting bacterial species can improve predictions substantially. Clinicians should consider the implementation of such systems to aid correct empiric therapy and to potentially reduce antibiotic misuse.

Revealing antibiotic cross-resistance patterns in hospitalized patients through Bayesian network modelling.

OBJECTIVES: Microbial resistance exhibits dependency patterns between different antibiotics, termed cross-resistance and collateral sensitivity. These patterns differ between experimental and clinical settings. It is unclear whether the differences result from biological reasons or from confounding, biasing results found in clinical settings. We set out to elucidate the underlying dependency patterns between resistance to different antibiotics from clinical data, while accounting for patient characteristics and previous antibiotic usage. METHODS: Additive Bayesian network modelling was employed to simultaneously estimate relationships between variables in a dataset of bacterial cultures derived from hospitalized patients and tested for resistance to multiple antibiotics. Data contained resistance results, patient demographics and previous antibiotic usage, for five bacterial species: Escherichia coli (n = 1054), Klebsiella pneumoniae (n = 664), Pseudomonas aeruginosa (n = 571), CoNS (n = 495) and Proteus mirabilis (n = 415). RESULTS: All links between resistance to the various antibiotics were positive. Multiple direct links between resistance of antibiotics from different classes were observed across bacterial species. For example, resistance to gentamicin in E. coli was directly linked with resistance to ciprofloxacin (OR = 8.39, 95% credible interval 5.58-13.30) and sulfamethoxazole/trimethoprim (OR = 2.95, 95% credible interval 1.97-4.51). In addition, resistance to various antibiotics was directly linked with previous antibiotic usage. CONCLUSIONS: Robust relationships among resistance to antibiotics belonging to different classes, as well as resistance being linked to having taken antibiotics of a different class, exist even when taking into account multiple covariate dependencies. These relationships could help inform choices of antibiotic treatment in clinical settings.