Detecting drug diversion in health-system data using machine learning and advanced analytics.

PURPOSE: The theft of drugs from healthcare facilities, also known as drug diversion, occurs frequently but is often undetected. This paper describes a research study to develop and test novel drug diversion detection methods. Improved diversion detection and reduction in diversion improves patient safety, limits harm to the person diverting, reduces the public health impact of substance use disorder, and mitigates significant liability risk to pharmacists and their organizations. METHODS: Ten acute care inpatient hospitals across 4 independent health systems extracted 2 datasets from various health information technology systems. Both datasets were consolidated, normalized, classified, and sampled to provide a harmonious dataset for analysis. Supervised machine learning methods were iteratively used on the initial sample dataset to train algorithms to classify medication movement transactions as involving a low or high risk of diversion. Thereafter, the resulting machine learning model classified the risk of diversion in a historical dataset capturing 8 to 24 months of history that included 27.9 million medication movement transactions by 19,037 nursing, 1,047 pharmacy, and 712 anesthesia clinicians and that included 22 known, blinded diversion cases to measure when the model would have detected the diversion compared to when the diversion was actually detected by existing methods. RESULTS: The machine learning model had 96.3% accuracy, 95.9% specificity, and 96.6% sensitivity in detecting transactions involving a high risk of diversion using the initial sample dataset. In subsequent testing using the much larger historical dataset, the analytics detected known diversion cases (n = 22) in blinded data faster than existing detection methods (a mean of 160 days and a median of 74 days faster; range, 7-579 days faster). CONCLUSION: The study showed that (1) consolidated datasets and (2) supervised machine learning can detect known diversion cases faster than existing detection methods. Users of the technology also noted improved investigation efficiency.

Predictors of time to return to play and re-injury following hamstring injury with and without intramuscular tendon involvement in adult professional footballers: A retrospective cohort study.

OBJECTIVES: In one English Premier League football club over four seasons, 1) describe the number of hamstring strain injuries (HSI) sustained using the British Athletics Muscle Injury Classification (BAMIC); 2) determine if intramuscular tendon HSI influenced the time to return to play (TTRTP) and reinjury rate; 3) determine the predictors of TTRTP and reinjury. DESIGN: Retrospective cohort design. METHODS: All first team players who sustained a HSI between 2014 and 2018 were included. Players underwent an MRI scan that was graded by a Radiologist using the BAMIC (0a-4) criteria. TTRTP, reinjury rate and information on suspected predictors were recorded. RESULTS: Thirty-five HSI experienced by 24 players (age = 26 ±â€¯4 years) were recorded over the 4 seasons. There was a difference in TTRTP between grades 1a and 2c (P = 0.007), but not between 2b and 2c (P = 0.845). Grade of HSI (P ≤ 0.001) and removal of the player (P < 0.001) were predictors of TTRTP, with each increase in grade resulting in an additional 3 days of TTRTP, and being removed, an additional 11 days. Grade and all other predictors did not influence reinjury rate, albeit higher odds were evident for previous HSI, experiencing the HSI during sprinting, passing a ball or stretching, and reported increase days of pain during walking. CONCLUSIONS: HSIs extending into the intramuscular tendon (2b cf. 2c) did not influence TTRTP or re-injury, albeit TTRTP was affected by the BAMIC grade and if the player was removed from activity.

Discovery of a Novel DNA Gyrase-Targeting Antibiotic through the Chemical Perturbation of Streptomyces venezuelae Sporulation.

Common approaches to antibiotic discovery include small-molecule screens for growth inhibition in target pathogens and screens for inhibitors of purified enzymes. These approaches have a shared intent of seeking to directly target a vital Achilles heel in a pathogen of interest. Here, we report the first screen against a sporulation pathway in a non-pathogenic bacterium as a means of discovering novel antibiotics-this effort has resulted in two important discoveries. First, we show that the sporulation program of Streptomyces venezuelae is exquisitely sensitive to numerous forms of DNA damage. Second, we have identified a DNA gyrase inhibitor. This molecule, EN-7, is active against pathogenic species that are resistant to ciprofloxacin and other clinically important antibiotics. We suggest that this strategy could be applied to other morphogenetic pathways in prokaryotes or eukaryotes as a means of identifying novel chemical matter having scientific and clinical utility.

A Chemical Inhibitor of Cell Growth Reduces Cell Size in Bacillus subtilis.

Bacteria exhibit complex responses to biologically active small molecules. These responses include reductions in transcriptional and translational efficiency, alterations in metabolic flux, and in some cases, dramatic changes in growth and morphology. Here, we describe Min-1, a novel small molecule that inhibits growth of Gram-positive bacteria by targeting the cell envelope. Subinhibitory levels of Min-1 inhibits sporulation in Streptomyces venezuelae and reduces growth rate and cell length in Bacillus subtilis. The effect of Min-1 on B. subtilis cell length is significant at high growth rates sustained by nutrient-rich media but drops off when growth rate is reduced during growth on less energy-rich carbon sources. In each medium, Min-1 has no impact on the proportion of cells containing FtsZ-rings, suggesting that Min-1 reduces the mass at which FtsZ assembly is initiated. The effect of Min-1 on size is independent of UDP-glucose, which couples cell division to carbon availability, and the alarmone ppGpp, which reduces cell size via its impact on fatty acid synthesis. Min-1 activates the LiaRS stress response, which is sensitive to disruptions in the lipid II cycle and the cell membrane, and also compromises cell membrane integrity. Therefore, this novel synthetic molecule inhibits growth at high concentrations and induces a short-cell phenotype at subinhibitory concentrations that is independent of known systems that influence cell length, highlighting the complex interactions between small molecules and cell morphology.

Streptomyces: a screening tool for bacterial cell division inhibitors.

Cell division is essential for spore formation but not for viability in the filamentous streptomycetes bacteria. Failure to complete cell division instead blocks spore formation, a phenotype that can be visualized by the absence of gray (in Streptomyces coelicolor) and green (in Streptomyces venezuelae) spore-associated pigmentation. Despite the lack of essentiality, the streptomycetes divisome is similar to that of other prokaryotes. Therefore, the chemical inhibitors of sporulation in model streptomycetes may interfere with the cell division in rod-shaped bacteria as well. To test this, we investigated 196 compounds that inhibit sporulation in S. coelicolor. We show that 19 of these compounds cause filamentous growth in Bacillus subtilis, consistent with impaired cell division. One of the compounds is a DNA-damaging agent and inhibits cell division by activating the SOS response. The remaining 18 act independently of known stress responses and may therefore act on the divisome or on divisome positioning and stability. Three of the compounds (Fil-1, Fil-2, and Fil-3) confer distinct cell division defects on B. subtilis. They also block B. subtilis sporulation, which is mechanistically unrelated to the sporulation pathway of streptomycetes but is also dependent on the divisome. We discuss ways in which these differing phenotypes can be used in screens for cell division inhibitors.

Miniaturised centrifugal solid phase extraction platforms for in-field sampling, pre-concentration and spectrometric detection of organic pollutants in aqueous samples.

Great variations in pollutant concentrations are observed in the environment and pre-concentration is often required to detect trace contaminants in water samples. This paper presents a novel solid phase-extraction device integrated onto a centrifugal microfluidic platform for rapid on-site pre-concentration and screening of organic contaminants in aqueous samples. In-column fluorescence and absorbance measurements are obtained directly from an analyte trapped on the top of a solid phase extraction microcolumn. Results are presented for the representative fluorophore fluorescein and the polycyclic aromatic hydrocarbon anthracene. An absolute detection limit of 20 ng was obtained for anthracene using a simple light emitting diode for fluorescence excitation. One of the main advantages of this device is that only a simple motor is needed to induce liquid flow, making simultaneous on-site extraction and measurement of multiple samples easy while minimizing sample losses and contamination.