An Artificial Intelligence Derived Blood Test to Diagnose Kawasaki Disease.

OBJECTIVE: To develop a highly sensitive and specific blood biomarker panel that identifies febrile children with Kawasaki disease (KD). METHODS: We tested blood samples from a single-center cohort of KD (n = 50) and control febrile children (n = 100) to develop a biomarker panel from 11 candidates selected by their assay clinical availability. We used machine learning with least absolute shrinkage and selection operator regression to identify 11 blood markers with values incorporated into a model, which provided a binary predictive risk score for KD determined with Youden's index. We further reduced the model using least angle regression. RESULTS: Using 10-fold cross-validation with least absolute shrinkage and selection operator regression on these 11 readouts plus patient age resulted in an area under the receiver operating characteristic curve of 0.94 (95% confidence interval [CI]: 0.90-0.98; P <.01). Using Youden's index, which provided an optimal cut off for a binary predictive risk score, 88 of 97 KD-negative patients were diagnosed negative, and 47 of 50 KD-positive patients were positive, yielding a sensitivity of 0.94 (95% CI: 0.87-1.0) and specificity of 0.91 (95% CI: 0.85-0.96). Least angle regression reduced the final panel to 3 biomarkers: C-reactive protein, NT-proB-type natriuretic peptide, and thyroid hormone uptake. The predictive model then provided an area under the receiver operating characteristic curve of 0.92 (95% CI: 0.87-0.96; P <.001) along with sensitivity and specificity at 86% each. CONCLUSIONS: Machine learning identified a highly accurate diagnostic model for KD. The reduced model employs 3 biomarkers currently approved by regulatory bodies and performed on platforms commonly used by certified diagnostic laboratories.

Application of a machine learning-driven, multibiomarker panel for prediction of incident cardiovascular events in patients with suspected myocardial infarction.

Background: In patients with suspected myocardial infarction (MI), we sought to validate a machine learning-driven, multibiomarker panel for prediction of incident major adverse cardiovascular events (MACE). Methodology & results: A previously described prognostic panel for MACE consisting of four biomarkers was measured in 748 patients with suspected MI. The investigated end point was incident MACE within 1 year. The prognostic value of a continuous score and an optimal cut-off was investigated. The area under the curve was 0.86 for the overall model. Using the optimal cut-off resulted in a negative predictive value of 99.4% for incident MACE. Patients with an elevated prognostic score were at high risk for MACE. Conclusion: Among patients with suspected MI, we validated a multibiomarker panel for predicting 1-year MACE. Clinical Trial Registration: NCT02355457 (ClinicalTrials.gov).

Individualizing hypertension treatment with impedance cardiography: a meta-analysis of published trials.

OBJECTIVE: Hypertension affects 73 million Americans and costs the US healthcare system over $73 billion annually. Despite increasing awareness of the consequences of uncontrolled hypertension, numerous antihypertensive pharmacologic clinical studies and consistent updates to hypertension guidelines, control rates are suboptimal and have not met national goals. Among treated hypertensives, only 45% of women and 51% of men have reached blood pressure (BP) levels below 140/90 mmHg. Individualization of antihypertensive regimens with hemodynamic information from impedance cardiography (ICG) has been advocated to further improve hypertension control rates. We therefore undertook a quantitative analysis of the trials evaluating the role of ICG as an adjunct to therapeutic decision-making in the treatment of hypertension and the attainment of BP control. METHODS: Five studies comprising a total population of 759 patients met the inclusion criteria. Two randomized controlled trials (RCTs) involving a total of 268 patients and three single-arm prospective trials with 491 patients were evaluated using ICG data to guide therapeutic decision-making in the treatment of hypertensive patients. RESULTS: Significant benefit was found in both RCTs for ICG-guided BP treatment. The combined odds ratio for the two trials was 2.41 (95% CI = 1.44-4.05, p = 0.0008), in favor of ICG treatment, meaning that it was more than twice as likely to achieve BP success when using ICG than if ICG was not used. Success attainment of goal BP of <140/90 mmHg was 67% in the ICG-guided arms of the combined randomized trials. Overall success in the single-arm prospective trials of ICG-guided BP treatment was a similar 68%. CONCLUSION: The results of this meta-analysis confirm the value of using ICG-derived hemodynamic data as an adjunct to therapeutic decision-making in the treatment of hypertension. The data reviewed here demonstrate that ICG-based approaches are in keeping with previously advocated strategies incorporating patient-individualized drug regimens, evidence-based medicine, and practical, easy to apply, cost-effective principles to further improve hypertension control rates.

Use of noninvasive hemodynamics in hypertension management.

Hypertension is a chronic disease that is controlled in the United States in only 34% of those taking antihypertensive medications. Because hypertension is a hemodynamic disorder, the patient's hemodynamic profile before and after medical intervention may assist in the decision and evaluation of ongoing antihypertensive therapy. There are several medication classes used in the management of hypertension and it is challenging at best for the clinician to determine the optimal therapeutic combination of medications for each patient. Physician perceptions and patient symptoms are examples of barriers affecting the management and control of hypertension. Impedance cardiography is a noninvasive monitoring technique that provides reliable and reproducible hemodynamic measurements. Three case studies are presented that illustrate how hemodynamic parameters were used to achieve hypertension control in the outpatient setting.