Development, Evaluation, and Multisite Deployment of a Machine Learning Decision Tree Algorithm To Optimize Urinalysis Parameters for Predicting Urine Culture Positivity.

PittUDT, a recursive partitioning decision tree algorithm for predicting urine culture (UC) positivity based on macroscopic and microscopic urinalysis (UA) parameters, was developed in support of a broader system-wide diagnostic stewardship initiative to increase appropriateness of UC testing. Reflex algorithm training utilized results from 19,511 paired UA and UC cases (26.8% UC positive); the average patient age was 57.4 years, and 70% of samples were from female patients. Receiver operating characteristic (ROC) analysis identified urine white blood cells (WBCs), leukocyte esterase, and bacteria as the best predictors of UC positivity, with areas under the ROC curve of 0.79, 0.78, and 0.77, respectively. Using the held-out test data set (9,773 cases; 26.3% UC positive), the PittUDT algorithm met the prespecified target of a negative predictive value above 90% and resulted in a 30 to 60% total negative proportion (true-negative plus false-negative predictions). These data show that a supervised rule-based machine learning algorithm trained on paired UA and UC data has adequate predictive ability for triaging urine specimens by identifying low-risk urine specimens, which are unlikely to grow pathogenic organisms, with a false-negative proportion under 5%. The decision tree approach also generates human-readable rules that can be easily implemented across multiple hospital sites and settings. Our work demonstrates how a data-driven approach can be used to optimize UA parameters for predicting UC positivity in a reflex protocol, with the intent of improving antimicrobial stewardship and UC utilization, a potential avenue for cost savings.

Fluid Flow Model for Predicting the Intrusion Rate of Subsurface Contaminant Vapors into Buildings.

A new method is presented for calculating a building-specific subslab to indoor air attenuation factor for use in assessing subsurface vapor intrusion to indoor air. The technique includes (1) subslab gas extraction with flow and vacuum measurements and mathematical modeling to characterize the bulk average vertical gas conductivity of the floor slab, (2) monitoring of the ambient pressure gradient across the floor slab with a micromanometer, (3) calculating the volumetric flow of soil gas into the building ( Qsoil), and (4) dividing Qsoil by the building ventilation rate ( Qbuilding) to calculate a building-specific attenuation factor. Sample calculations using order statistics from 121 individual tests are comparable to the U.S. Environmental Protection Agency empirical attenuation factors for residential buildings and the U.S. Navy empirical attenuation factors for commercial/industrial buildings. A case study of a commercial building shows encouraging agreement between the attenuation factors calculated via this method and via conventional subslab and indoor air sampling.

Mathematical analysis and flux-based radius of influence for radon/VOC vapor intrusion mitigation systems.

Volatile organic compounds (VOCs) and radon progeny pose potential health risks to occupants of certain buildings via subsurface vapor intrusion (VI) to indoor air. VI mitigation is usually performed using systems that extract gas from below the building, and the system performance is typically evaluated by measuring the distribution of applied vacuum below the floor. This article provides a new approach to assessing the radius of influence (ROI) for subslab venting systems based on mass flux instead of static vacuum distribution and includes an analyses of 121 pneumatic tests performed at 65 different suction points in 16 different buildings. The mathematical model represents a two-layer system with horizontal radial flow through transmissive material below the floor slab and vertical flow through discontinuities in the floor slab (which is simplified to approximate an equivalent porous medium). The analysis includes comparisons of the flux-based ROI to values calculated using the two-layer model for 1) vacuum, 2) velocity, and 3) travel time, which may be useful as alternative performance metrics for mitigation systems.

Incidence and Management of Therapeutic Monoclonal Antibody Interference in Monoclonal Gammopathy Monitoring.

BACKGROUND: The treatment of multiple myeloma (MM) has been revolutionized by the introduction of therapeutic monoclonal antibodies (tmAbs). Daratumumab, a human IgG1/κ tmAb against CD38 on plasma cells, has improved overall survival in refractory MM and was recently approved as a frontline therapy for MM. Work on tmAb interference with serum protein electrophoresis (SPE) during MM monitoring has failed to provide information for laboratories on incidence of interference and effective methods of managing the interference at a practicable level. We aimed to evaluate daratumumab and elotuzumab interference in a large academic hospital setting and implement immediate solutions. METHODS: We identified and chart reviewed all cases of possible daratumumab interference by electrophoretic pattern (120 of 1317 total cases over 3 months). We retrospectively reviewed SPE cases in our laboratory to assess clinical implications of tmAb interference before the laboratory was aware of tmAb treatment. We supplemented samples with daratumumab and elotuzumab to determine the limits of detection and run free light chain analysis. RESULTS: Approximately 9% (120 of 1317) of tested cases have an SPE and/or immunofixation electrophoresis (IFE) pattern consistent with daratumumab, but only approximately 47% (56) of these cases were associated with daratumumab therapy. Presence of daratumumab led to physician misinterpretation of SPE/IFE results. Limits of daratumumab detection varied with total serum gammaglobulin concentrations, but serum free light chain analysis was unaffected. CONCLUSIONS: Clinical laboratories currently rely on interference identification by electrophoretic pattern, which may be insufficient and is inefficient. Critical tools in preventing misinterpretation efficiently include physician education, pharmacy notifications, separate order codes, and interpretive comments.