SARS-CoV-2 is the virus that causes coronavirus disease (COVID-19) which has reached pandemic levels resulting in significant morbidity and mortality affecting every inhabited continent. The large ...number of patients requiring intensive care threatens to overwhelm healthcare systems globally. Likewise, there is a compelling need for a COVID-19 disease severity test to prioritize care and resources for patients at elevated risk of mortality. Here, an integrated point-of-care COVID-19 Severity Score and clinical decision support system is presented using biomarker measurements of C-reactive protein (CRP), N-terminus pro B type natriuretic peptide (NT-proBNP), myoglobin (MYO), D-dimer, procalcitonin (PCT), creatine kinase-myocardial band (CK-MB), and cardiac troponin I (cTnI). The COVID-19 Severity Score combines multiplex biomarker measurements and risk factors in a statistical learning algorithm to predict mortality. The COVID-19 Severity Score was trained and evaluated using data from 160 hospitalized COVID-19 patients from Wuhan, China. Our analysis finds that COVID-19 Severity Scores were significantly higher for the group that died
versus
the group that was discharged with median (interquartile range) scores of 59 (40-83) and 9 (6-17), respectively, and area under the curve of 0.94 (95% CI 0.89-0.99). Although this analysis represents patients with cardiac comorbidities (hypertension), the inclusion of biomarkers from other pathophysiologies implicated in COVID-19 (
e.g.
, D-dimer for thrombotic events, CRP for infection or inflammation, and PCT for bacterial co-infection and sepsis) may improve future predictions for a more general population. These promising initial models pave the way for a point-of-care COVID-19 Severity Score system to impact patient care after further validation with externally collected clinical data. Clinical decision support tools for COVID-19 have strong potential to empower healthcare providers to save lives by prioritizing critical care in patients at high risk for adverse outcomes.
The COVID-19 Severity Score combines multiplex biomarker measurements and risk factors in a statistical learning algorithm to predict mortality.
The combination of point-of-care (POC) medical microdevices and machine learning has the potential transform the practice of medicine. In this area, scalable lab-on-a-chip (LOC) devices have many ...advantages over standard laboratory methods, including faster analysis, reduced cost, lower power consumption, and higher levels of integration and automation. Despite significant advances in LOC technologies over the years, several remaining obstacles are preventing clinical implementation and market penetration of these novel medical microdevices. Similarly, while machine learning has seen explosive growth in recent years and promises to shift the practice of medicine toward data-intensive and evidence-based decision making, its uptake has been hindered due to the lack of integration between clinical measurements and disease determinations. In this Account, we describe recent developments in the programmable bio-nanochip (p-BNC) system, a biosensor platform with the capacity for learning. The p-BNC is a “platform to digitize biology” in which small quantities of patient sample generate immunofluorescent signal on agarose bead sensors that is optically extracted and converted to antigen concentrations. The platform comprises disposable microfluidic cartridges, a portable analyzer, automated data analysis software, and intuitive mobile health interfaces. The single-use cartridges are fully integrated, self-contained microfluidic devices containing aqueous buffers conveniently embedded for POC use. A novel fluid delivery method was developed to provide accurate and repeatable flow rates via actuation of the cartridge’s blister packs. A portable analyzer instrument was designed to integrate fluid delivery, optical detection, image analysis, and user interface, representing a universal system for acquiring, processing, and managing clinical data while overcoming many of the challenges facing the widespread clinical adoption of LOC technologies. We demonstrate the p-BNC’s flexibility through the completion of multiplex assays within the single-use disposable cartridges for three clinical applications: prostate cancer, ovarian cancer, and acute myocardial infarction. Toward the goal of creating “sensors that learn”, we have developed and describe here the Cardiac ScoreCard, a clinical decision support system for a spectrum of cardiovascular disease. The Cardiac ScoreCard approach comprises a comprehensive biomarker panel and risk factor information in a predictive model capable of assessing early risk and late-stage disease progression for heart attack and heart failure patients. These marker-driven tests have the potential to radically reduce costs, decrease wait times, and introduce new options for patients needing regular health monitoring. Further, these efforts demonstrate the clinical utility of fusing data from information-rich biomarkers and the Internet of Things (IoT) using predictive analytics to generate single-index assessments for wellness/illness status. By promoting disease prevention and personalized wellness management, tools of this nature have the potential to improve health care exponentially.
We are beginning a new era of
-integrated biosensors powered by recent innovations in embedded electronics, cloud computing, and artificial intelligence (AI). Universal and AI-based in vitro ...diagnostics (IVDs) have the potential to exponentially improve healthcare decision making in the coming years. This perspective covers current trends and challenges in translating Smart Diagnostics. We identify essential elements of Smart Diagnostics platforms through the lens of a clinically validated platform for digitizing biology and its ability to learn disease signatures. This platform for biochemical analyses uses a compact instrument to perform multiclass and multiplex measurements using fully integrated microfluidic cartridges compatible with the point of care. Image analysis
by transforming fluorescence signals into inputs for learning disease/health signatures. The result is an intuitive
reported to the patients and/or providers. This AI-linked universal diagnostic system has been validated through a series of large clinical studies and used to identify signatures for early disease detection and disease severity in several applications, including cardiovascular diseases, COVID-19, and oral cancer. The utility of this Smart Diagnostics platform may extend to multiple cell-based oncology tests via cross-reactive biomarkers spanning oral, colorectal, lung, bladder, esophageal, and cervical cancers, and is well-positioned to improve patient care, management, and outcomes through deployment of this resilient and scalable technology. Lastly, we provide a future perspective on the direction and trajectory of Smart Diagnostics and the transformative effects they will have on health care.
Background
The COVID-19 pandemic began in early 2021 and placed significant strains on health care systems worldwide. There remains a compelling need to analyze factors that are predictive for ...patients at elevated risk of morbidity and mortality.
Objective
The goal of this retrospective study of patients who tested positive with COVID-19 and were treated at NYU (New York University) Langone Health was to identify clinical markers predictive of disease severity in order to assist in clinical decision triage and to provide additional biological insights into disease progression.
Methods
The clinical activity of 3740 patients at NYU Langone Hospital was obtained between January and August 2020; patient data were deidentified. Models were trained on clinical data during different parts of their hospital stay to predict three clinical outcomes: deceased, ventilated, or admitted to the intensive care unit (ICU).
Results
The XGBoost (eXtreme Gradient Boosting) model that was trained on clinical data from the final 24 hours excelled at predicting mortality (area under the curve AUC=0.92; specificity=86%; and sensitivity=85%). Respiration rate was the most important feature, followed by SpO2 (peripheral oxygen saturation) and being aged 75 years and over. Performance of this model to predict the deceased outcome extended 5 days prior, with AUC=0.81, specificity=70%, and sensitivity=75%. When only using clinical data from the first 24 hours, AUCs of 0.79, 0.80, and 0.77 were obtained for deceased, ventilated, or ICU-admitted outcomes, respectively. Although respiration rate and SpO2 levels offered the highest feature importance, other canonical markers, including diabetic history, age, and temperature, offered minimal gain. When lab values were incorporated, prediction of mortality benefited the most from blood urea nitrogen and lactate dehydrogenase (LDH). Features that were predictive of morbidity included LDH, calcium, glucose, and C-reactive protein.
Conclusions
Together, this work summarizes efforts to systematically examine the importance of a wide range of features across different endpoint outcomes and at different hospitalization time points.
Current noninvasive liver tests are surrogates for fibrosis and lack ability to directly measure liver function. HepQuant tests measure liver function and physiology through hepatic uptake of stable ...cholate isotopes. HepQuant SHUNT (V1.0) involves oral and intravenous dosing and six blood samples over 90 min. We developed simplified test versions: SHUNT V2.0 (oral and intravenous dosing, two blood samples over 60 min) and DuO (oral dosing only, two blood samples over 60 min). The aim of this study was to evaluate equivalency of the simplified tests to the original SHUNT test. Data from three studies comprising 930 SHUNT tests were retrospectively analysed by each method. Equivalence was evaluated in terms of proportion of tests in which the difference between methods was less than any clinically meaningful difference and additionally by two one-sided t-test and bioequivalence methods. DuO and SHUNT V2.0 were equivalent to the original SHUNT test for Disease Severity Index, with >99% and >96% of tests falling within equivalence bounds. DuO and SHUNT V2.0 met equivalency criteria by two one-sided t-tests and bioequivalence. DuO and SHUNT V2.0 are easier to administer, are less invasive than the original SHUNT test and have potential to be more accepted by patients and providers.
Current noninvasive liver tests measure fibrosis, inflammation, or steatosis and do not measure function. The HepQuant platform of noninvasive tests uniquely assesses both liver function and ...physiology through the hepatic uptake of stable isotopes of cholate. However, the prototypical HepQuant SHUNT test (SHUNT V1.0) is cumbersome to administer, requiring intravenous and oral administration of cholate and six peripheral venous blood samples over 90 min. To alleviate the burden of test administration, we explored whether an oral only (DuO) version, and other simplified versions, of the test could provide reproducible measurements of liver function. DuO requires only oral dosing and two blood samples over 60 min. The simplified SHUNT test versions were SHUNT V1.1 (oral and IV dosing but four blood samples) and SHUNT V2.0 (oral and IV dosing but only two blood samples over 60 min). In this paper, we describe the reproducibility of DuO and the simplified SHUNT tests relative to that of SHUNT V1.0; equivalency is described in a separate paper. Data from two studies comprising 236 SHUNT tests in 94 subjects were analyzed retrospectively by each method. All simplified methods were highly reproducible across test parameters with intraclass correlation coefficients >0.93 for test parameters Disease Severity Index (DSI) and Hepatic Reserve. DuO and SHUNT V2.0 improved reproducibility in measuring portal‐systemic shunting (SHUNT%). These simplified tests, particularly DuO and SHUNT V2.0, are easier to administer and less invasive, thus, having the potential to be more widely accepted by care providers administering the test and by patients receiving the test.
IMPORTANCE: Some cigarette smokers may not be ready to quit immediately but may be willing to reduce cigarette consumption with the goal of quitting. OBJECTIVE: To determine the efficacy and safety ...of varenicline for increasing smoking abstinence rates through smoking reduction. DESIGN, SETTING, AND PARTICIPANTS: Randomized, double-blind, placebo-controlled, multinational clinical trial with a 24-week treatment period and 28-week follow-up conducted between July 2011 and July 2013 at 61 centers in 10 countries. The 1510 participants were cigarette smokers who were not willing or able to quit smoking within the next month but willing to reduce smoking and make a quit attempt within the next 3 months. Participants were recruited through advertising. INTERVENTIONS: Twenty-four weeks of varenicline titrated to 1 mg twice daily or placebo with a reduction target of 50% or more in number of cigarettes smoked by 4 weeks, 75% or more by 8 weeks, and a quit attempt by 12 weeks. MAIN OUTCOMES AND MEASURES: Primary efficacy end point was carbon monoxide–confirmed self-reported abstinence during weeks 15 through 24. Secondary outcomes were carbon monoxide–confirmed self-reported abstinence for weeks 21 through 24 and weeks 21 through 52. RESULTS: The varenicline group (n = 760) had significantly higher continuous abstinence rates during weeks 15 through 24 vs the placebo group (n = 750) (32.1% for the varenicline group vs 6.9% for the placebo group; risk difference (RD), 25.2% 95% CI, 21.4%-29.0%; relative risk (RR), 4.6 95% CI, 3.5-6.1). The varenicline group had significantly higher continuous abstinence rates vs the placebo group during weeks 21 through 24 (37.8% for the varenicline group vs 12.5% for the placebo group; RD, 25.2% 95% CI, 21.1%-29.4%; RR, 3.0 95% CI, 2.4-3.7) and weeks 21 through 52 (27.0% for the varenicline group vs 9.9% for the placebo group; RD, 17.1% 95% CI, 13.3%-20.9%; RR, 2.7 95% CI, 2.1-3.5). Serious adverse events occurred in 3.7% of the varenicline group and 2.2% of the placebo group (P = .07). CONCLUSIONS AND RELEVANCE: Among cigarette smokers not willing or able to quit within the next month but willing to reduce cigarette consumption and make a quit attempt at 3 months, use of varenicline for 24 weeks compared with placebo significantly increased smoking cessation rates at the end of treatment, and also at 1 year. Varenicline offers a treatment option for smokers whose needs are not addressed by clinical guidelines recommending abrupt smoking cessation. TRIAL REGISTRATION: clinicaltrials.gov Identifier: NCT01370356
LINKED CONTENT
This article is linked to Hassanein et al papers. To view these articles, visit https://doi.org/10.1111/apt.18054 and https://doi.org/10.1111/apt.18113
The cover image is based on the Original Article Liver function and portal‐systemic shunting quantified by the oral cholate challenge test and risk for large oesophageal varices by Tarek Hassanein et ...al., https://doi.org/10.1111/apt.18054
HepQuant tests quantify liver function from clearance of deuterium‐ and 13C‐labeled cholates administered either intravenously and orally (SHUNT) or orally (DuO). Hepatic impairment studies have ...relied on clinical or laboratory criteria like Child‐Pugh classification to categorize the degree of hepatic dysfunction. We compared HepQuant tests with Child‐Pugh classification in predicting the pharmacokinetics of ampreloxetine. Twenty‐one subjects with hepatic impairment (8 Child‐Pugh A, 7 Child‐Pugh B, and 6 Child‐Pugh C), and 10 age‐ and sex‐matched controls were studied. The pharmacokinetics of ampreloxetine were measured after oral administration of a single dose of 10 mg. Disease severity index (DSI), portal‐systemic shunting (SHUNT%), hepatic reserve, and hepatic filtration rates (HFRs) were measured from serum samples obtained after intravenous administration of 24‐13C‐cholate and oral administration of 2,2,4,4‐2Hcholate. Ampreloxetine plasma exposure (AUC0‐inf) was similar to controls in Child‐Pugh A, increased 1.7‐fold in subjects with Child‐Pugh B, and 2.5‐fold in subjects with Child‐Pugh C and correlated with both Child‐Pugh score and HepQuant parameters. The variability observed in ampreloxetine exposure (AUC0‐inf) in subjects with moderate (Child‐Pugh B) and severe hepatic impairment (Child‐Pugh C) was explained by HepQuant parameters. Multivariable regression models demonstrated that DSI, SHUNT%, and Hepatic Reserve from SHUNT and DuO were superior predictors of ampreloxetine exposure (AUC0‐inf) compared to Child‐Pugh score. HepQuant DSI, SHUNT%, and hepatic reserve were more useful predictors of drug exposure than Child‐Pugh class for ampreloxetine and thus may better optimize dose recommendations in patients with liver disease. The simple‐to‐administer, oral‐only DuO version of the HepQuant test could enhance clinical utility.