A fully interpretable machine learning model for increasing the effectiveness of urine screening.

OBJECTIVES: This article addresses the need for effective screening methods to identify negative urine samples before urine culture, reducing the workload, cost, and release time of results in the microbiology laboratory. We try to overcome the limitations of current solutions, which are either too simple, limiting effectiveness (1 or 2 parameters), or too complex, limiting interpretation, trust, and real-world implementation ("black box" machine learning models). METHODS: The study analyzed 15,312 samples from 10,534 patients with clinical features and the Sysmex Uf-1000i automated analyzer data. Decision tree (DT) models with or without lookahead strategy were used, as they offer a transparent set of logical rules that can be easily understood by medical professionals and implemented into automated analyzers. RESULTS: The best model achieved a sensitivity of 94.5% and classified negative samples based on age, bacteria, mucus, and 2 scattering parameters. The model reduced the workload by an additional 16% compared to the current procedure in the laboratory, with an estimated financial impact of €40,000/y considering 15,000 samples/y. Identified logical rules have a scientific rationale matched to existing knowledge in the literature. CONCLUSIONS: Overall, this study provides an effective and interpretable screening method for urine culture in microbiology laboratories, using data from the Sysmex UF-1000i automated analyzer. Unlike other machine learning models, our model is interpretable, generating trust and enabling real-world implementation.

Image Analysis of Circulating Tumor Cells and Leukocytes Predicts Survival and Metastatic Pattern in Breast Cancer Patients.

BACKGROUND: The purpose of the present work was to test whether quantitative image analysis of circulating cells can provide useful clinical information targeting bone metastasis (BM) and overall survival (OS >30 months) in metastatic breast cancer (MBC). METHODS: Starting from cell images of epithelial circulating tumor cells (eCTC) and leukocytes (CD45pos) obtained with DEPArray, we identified the most significant features and applied single-variable and multi-variable methods, screening all combinations of four machine-learning approaches (Naïve Bayes, Logistic regression, Decision Trees, Random Forest). RESULTS: Best predictive features were circularity (OS) and diameter (BM), in both eCTC and CD45pos. Median difference in OS was 15 vs. 43 (months), p = 0.03 for eCTC and 19 vs. 36, p = 0.16 for CD45pos. Prediction for BM showed low accuracy (64%, 53%) but strong positive predictive value PPV (79%, 91%) for eCTC and CD45, respectively. Best machine learning model was Naïve Bayes, showing 46 vs 11 (months), p <0.0001 for eCTC; 12.5 vs. 45, p = 0.0004 for CD45pos and 11 vs. 45, p = 0.0003 for eCTC + CD45pos. BM prediction reached 91% accuracy with eCTC, 84% with CD45pos and 91% with combined model. CONCLUSIONS: Quantitative image analysis and machine learning models were effective methods to predict survival and metastatic pattern, with both eCTC and CD45pos containing significant and complementary information.

Application of an Artificial Intelligence Algorithm to Prognostically Stratify Grade II Gliomas.

(1) Background: Recently, it has been shown that the extent of resection (EOR) and molecular classification of low-grade gliomas (LGGs) are endowed with prognostic significance. However, a prognostic stratification of patients able to give specific weight to the single parameters able to predict prognosis is still missing. Here, we adopt classic statistics and an artificial intelligence algorithm to define a multiparametric prognostic stratification of grade II glioma patients. (2) Methods: 241 adults who underwent surgery for a supratentorial LGG were included. Clinical, neuroradiological, surgical, histopathological and molecular data were assessed for their ability to predict overall survival (OS), progression-free survival (PFS), and malignant progression-free survival (MPFS). Finally, a decision-tree algorithm was employed to stratify patients. (3) Results: Classic statistics confirmed EOR, pre-operative- and post-operative tumor volumes, Ki67, and the molecular classification as independent predictors of OS, PFS, and MPFS. The decision tree approach provided an algorithm capable of identifying prognostic factors and defining both the cut-off levels and the hierarchy to be used in order to delineate specific prognostic classes with high positive predictive value. Key results were the superior role of EOR on that of molecular class, the importance of second surgery, and the role of different prognostic factors within the three molecular classes. (4) Conclusions: This study proposes a stratification of LGG patients based on the different combinations of clinical, molecular, and imaging data, adopting a supervised non-parametric learning method. If validated in independent case studies, the clinical utility of this innovative stratification approach might be proved.