Barriers and Opportunities Regarding Implementation of a Machine Learning-Based Acute Heart Failure Risk Stratification Tool in the Emergency Department.

Hospital admissions for patients with acute heart failure (AHF) remain high. There is an opportunity to improve alignment between patient risk and admission decision. We recently developed a machine learning (ML)-based model that stratifies emergency department (ED) patients with AHF based on predicted risk of a 30-day severe adverse event. Prior to deploying the algorithm and paired clinical decision support, we sought to understand barriers and opportunities regarding successful implementation. We conducted semi-structured interviews with eight front-line ED providers and surveyed 67 ED providers. Audio-recorded interviews were transcribed and analyzed using thematic analysis, and we had a 65% response rate to the survey. Providers wanted decision support to be streamlined into workflows with minimal disruptions. Most providers wanted assistance primarily with ED disposition decisions, and secondarily with medical management and post-discharge follow-up care. Receiving feedback on patient outcomes after risk tool use was seen as an opportunity to increase acceptance, and few providers (<10%) had significant hesitations with using an ML-based tool after education on its use. Engagement with key front-line users on optimal design of the algorithm and decision support may contribute to broader uptake, acceptance, and adoption of recommendations for clinical decisions.

Simultaneous quantitation of five triazole anti-fungal agents by paper spray-mass spectrometry.

Background Invasive fungal disease is a life-threatening condition that can be challenging to treat due to pathogen resistance, drug toxicity, and therapeutic failure secondary to suboptimal drug concentrations. Frequent therapeutic drug monitoring (TDM) is required for some anti-fungal agents to overcome these issues. Unfortunately, TDM at the institutional level is difficult, and samples are often sent to a commercial reference laboratory for analysis. To address this gap, the first paper spray-mass spectrometry assay for the simultaneous quantitation of five triazoles was developed. Methods Calibration curves for fluconazole, posaconazole, itraconazole, hydroxyitraconazole, and voriconazole were created utilizing plasma-based calibrants and four stable isotopic internal standards. No sample preparation was needed. Plasma samples were spotted on a paper substrate in pre-manufactured plastic cartridges, and the dried plasma spots were analyzed directly utilizing paper spray-mass spectrometry (paper spray MS/MS). All experiments were performed on a Thermo Scientific TSQ Vantage triple quadrupole mass spectrometer. Results The calibration curves for the five anti-fungal agents showed good linearity (R2 = 0.98-1.00). The measured assay ranges (lower limit of quantification [LLOQ]-upper limit of quantitation [ULOQ]) for fluconazole, posaconazole, itraconazole, hydroxyitraconazole, and voriconazole were 0.5-50 µg/mL, 0.1-10 µg/mL, 0.1-10 µg/mL, 0.1-10 µg/mL, and 0.1-10 µg/mL, respectively. The inter- and intra-day accuracy and precision were less than 25% over the respective ranges. Conclusions We developed the first rapid paper spray-MS/MS assay for simultaneous quantitation of five triazole anti-fungal agents in plasma. The method may be a powerful tool for near-point-of-care TDM aimed at improving patient care by reducing the turnaround time and for use in clinical research.

Clinical utility of an ultrasensitive urinary free cortisol assay by tandem mass spectrometry.

BACKGROUND: 24 h urinary free cortisol measurement is a clinically important first-line screening test for Cushing's syndrome (CS). Tandem mass spectrometry (LC-MS/MS) assays have superior sensitivity and specificity compared to immunoassays. Our goal was to improve and validate a LC-MS/MS method to measure urinary free cortisol in both adult and pediatric patients and to characterize its clinical diagnostic performance of CS by chart review. METHODS: We improved a LC-MS/MS method previously reported for urinary free cortisol to be able to measure urinary and salivary cortisol in the same batch for increased efficiency. The sample preparation was by liquid-liquid extraction using dichloromethane followed by stepwise washing with acidic, basic and neutral solutions. The assay's analytical performance was characterized, and a retrospective patient chart review was conducted to evaluate the assay's clinical performance in diagnosing CS. RESULTS: The LC-MS/MS assay demonstrated enhanced sensitivity and was linear within an analytical measurement range of 10-10,000 ng/dL. Assay accuracy was satisfactory as determined by spike and recovery studies and highly correlated with a reference LC-MS/MS method. The assay's clinical diagnostic sensitivity and specificity in detecting CS was 96% and 91%, respectively, when compared to a urinary cortisol excretion of at least 50 µg/24 h. CONCLUSIONS: The improved LC-MS/MS method is both sensitive and specific with enhanced analytical performance and clinical diagnostic utility to screen for CS. The clinical diagnostic sensitivity and specificity were superior based on retrospective patient chart review.

Clinical utility of an ultrasensitive late night salivary cortisol assay by tandem mass spectrometry.

BACKGROUND: Late night salivary cortisol measurement is a clinically important and convenient screening test for Cushing's syndrome. Tandem mass spectrometry (LC-MS/MS) assays have superior sensitivity and specificity compared to immunoassays. Our goal was to improve a LC-MS/MS method to measure salivary cortisol in both adult and pediatric patients and to characterize its analytical performance by method validation and clinical performance by chart review. METHODS: We improved a LC-MS/MS method originally developed for urine cortisol to measure low level salivary cortisol. The sample preparation was by liquid-liquid extraction using dichloromethane followed by stepwise washing with acidic, basic and neutral solutions. The assay's analytical performance was characterized and retrospective patient chart review was conducted to evaluate the assay's clinical diagnostic performance. RESULTS: The LC-MS/MS assay showed enhanced functional sensitivity of 10 ng/dL for salivary cortisol and was linear within an analytical measurement range of 10-10,000 ng/dL. Assay accuracy was within 84-120% as determined by recovery studies and correlation with a reference method. Data from healthy adult volunteers was compiled to establish the reference interval for late night salivary cortisol. Patient chart review determined subjects with diagnosis of Cushing's syndrome or disease, and assay's clinical diagnostic sensitivity of 100% and specificity of 92% when the cutoff value was 70 ng/dL. CONCLUSIONS: The improved LC-MS/MS method is sensitive and specific with enhanced analytical performance and clinical diagnostic utility for screening Cushing's syndrome. The assay may have broad clinical application due to its high sensitivity and wide dynamic range.