A pooled multi-national validation study of a machine learning, high-sensitivity troponin-based multi-proteomic model to predict the presence of obstructive coronary artery disease

Background

Undetected obstructive coronary artery disease (oCAD) is a global health problem associated with significant morbidity and mortality. A need exists for an accurate and easily accessible diagnostic test for oCAD. Using machine learning, a multi-biomarker blood diagnostic test for oCAD based on high-sensitivity cardiac troponin-I (hs-cTnI) has been developed.

Purpose

To validate the performance of a previously developed, algorithmically weighted, multiple protein diagnostic panel to diagnose oCAD in a pooled multi-national cohort and to compare the diagnostic panel's performance to predict oCAD to hs-cTnI alone.

Methods

Three clinical factors (sex, age, and previous coronary percutaneous intervention) and three biomarkers (hs-cTnI, Adiponectin, and Kidney Injury Molecule-1) were combined. hs-cTnI blood samples were assayed on the Siemens Atellica and Abbott Diagnostics ARCHITECT immunoassay platforms. Adiponectin and Kidney Injury Molecule-1 were measured with a multiplex assay on blood samples via the Luminex 100/200 xMAP platform. Individual data from a total of 924 patients with a mixture of acute and lesser acute presentations from three centers were pooled (Table 1). oCAD was defined as >50% coronary obstruction in at least one coronary artery (for the University Hospital Hamburg-Eppendorf cohort) or >70% coronary obstruction in at least one coronary artery (for the other two cohorts). The multiple biomarker diagnostic panel's performance to predict oCAD was also compared to hs-cTnI alone.

Results

The multiple protein panel had an area under the receiver-operating characteristic curve of 0.80 (95% CI, 0.77, 0.83, p<0.001) for the presence of oCAD (Figure 1). At optimal cutoff, the score had 74% sensitivity, 72% specificity, and a positive predictive value of 81% for oCAD. The multiple biomarker panel had a diagnostic odds ratio of 7.48 (95% CI 5.55, 10.09, p<0.001). In comparison, in patients without an acute MI, hs-cTnI alone had an area under the receiver-operating characteristic curve of 0.63 (95% CI, 0.60, 0.67, p<0.001)) for oCAD (Figure 1).

Conclusions

In this multinational pooled cohort, a previously described novel machine learning, multiple biomarker panel provided high accuracy to diagnose patients for oCAD.

Funding Acknowledgement

Type of funding sources: Private company. Main funding source(s): Prevencio, Inc. Table 1. Pooled Variable DataFigure 1. ROC for HART CADhs and hs-cTnI

99.6% spin-flip efficiency in the presence of a strong Siberian snake

We recently studied the spin-flipping efficiency of an rf-dipole magnet using a 120-MeV horizontally polarized proton beam stored in the Indiana University Cyclotron Facility Cooler Ring, which contained a nearly full Siberian snake. We flipped the spin by ramping the rf dipole's frequency through an rf-induced depolarizing resonance. By adiabatically turning on the rf dipole, we minimized the beam loss. After optimizing the frequency ramp parameters, we used 100 multiple spin flips to measure a spin-flip efficiency of 99.63+/-0.05%. This result indicates that spin flipping should be possible in very-high-energy polarized storage rings, where Siberian snakes are certainly needed and only dipole rf-flipper magnets are practical.

Tuberculous peritonitis--do not miss it

Incidence of tuberculosis is sharply rising in the United States, and tuberculous peritonitis is often diagnosed late in the course of the disease, resulting in undue patient morbidity and mortality.

PURPOSE

Purpose of this study was to better identify which clinical, laboratory, radiologic, and invasive procedures were most useful in diagnosing tuberculous peritonitis.

METHODS

All cases of tuberculous peritonitis diagnosed between 1982 and 1994 were reviewed retrospectively to discern which laboratory, radiographic, and procedural tests were helpful in diagnosing the condition.

RESULTS

Twenty-eight cases of tuberculous peritonitis were diagnosed during the studied period. Two patients were not diagnosed until autopsy. Patients from all socioeconomic classes and multiple races ranged in age from 3 to 69 (mean, 29.5) years. Most patients presented with a chronic wasting illness, mild abdominal pain, and fever. Purified protein derivative was only positive in 5 of 16 patients. Chest radiographs were suggestive of pulmonary tuberculosis (TB) in five patients. Ultrasound examination of the abdomen was helpful in five patients, and computed tomographic scan was suspicious in 16 of 17 patients. Sputum for acid fast bacillus (AFB) smear was positive in 3 of 14 patients, and paracentesis for AFB smear was positive in 1 of 8 patients. Routine blood work was not helpful. Laparoscopy was diagnostic in five of seven patients. Laparotomy and tissue biopsy of characteristic tissue for AFB smear and culture was diagnostic in 20 of 20 patients. Once diagnosed, all patients responded rapidly to empiric antituberculous medical therapy, except one patient with miliary TB who died shortly after diagnosis. A trend in earlier diagnosis was noted in recent years and is felt to be the result of an elevated index of suspicion.

CONCLUSIONS

TB peritonitis may be fatal but is medically cured if diagnosed in a timely fashion. It is essential that the clinician suspect the disease in appropriate patients. Tests frequently associated with TB such as chest radiograph and purified protein derivative are not sensitive in detection of TB peritonitis. Computed tomographic scan is the most useful radiographic study. Mini laparotomy with tissue biopsy for smear and culture is the most sensitive and specific diagnostic procedure.