Association of NPAC score with survival after acute myocardial infarction.

BACKGROUND AND AIMS: Risk stratification in acute myocardial infarction (AMI) is important for guiding clinical management. Current risk scores are mostly derived from clinical trials with stringent patient selection. We aimed to establish and evaluate a composite scoring system to improve short-term mortality classification after index episodes of AMI, independent of electrocardiography (ECG) pattern, in a large real-world cohort. METHODS: Using electronic health records, patients admitted to our regional teaching hospital (derivation cohort, n = 1747) and an independent tertiary care center (validation cohort, n = 1276), with index acute myocardial infarction between January 2013 and December 2017, as confirmed by principal diagnosis and laboratory findings, were identified retrospectively. RESULTS: Univariate logistic regression was used as the primary model to identify potential contributors to mortality. Stepwise forward likelihood ratio logistic regression revealed that neutrophil-to-lymphocyte ratio, peripheral vascular disease, age, and serum creatinine (NPAC) were significant for 90-day mortality (Hosmer- Lemeshow test, p = 0.21). Each component of the NPAC score was weighted by beta-coefficients in multivariate analysis. The C-statistic of the NPAC score was 0.75, which was higher than the conventional Charlson's score (C-statistic = 0.63). Judicious application of a deep learning model to our dataset improved the accuracy of classification with a C-statistic of 0.81. CONCLUSIONS: The NPAC score comprises four items from routine laboratory parameters to basic clinical information and can facilitate early identification of cases at risk of short-term mortality following index myocardial infarction. Deep learning model can serve as a gatekeeper to facilitate clinical decision-making.

Figure Correction: Resting and Postexercise Heart Rate Detection From Fingertip and Facial Photoplethysmography Using a Smartphone Camera: A Validation Study.

[This corrects the article DOI: 10.2196/mhealth.7275.].

Resting and Postexercise Heart Rate Detection From Fingertip and Facial Photoplethysmography Using a Smartphone Camera: A Validation Study.

BACKGROUND: Modern smartphones allow measurement of heart rate (HR) by detecting pulsatile photoplethysmographic (PPG) signals with built-in cameras from the fingertips or the face, without physical contact, by extracting subtle beat-to-beat variations of skin color. OBJECTIVE: The objective of our study was to evaluate the accuracy of HR measurements at rest and after exercise using a smartphone-based PPG detection app. METHODS: A total of 40 healthy participants (20 men; mean age 24.7, SD 5.2 years; von Luschan skin color range 14-27) underwent treadmill exercise using the Bruce protocol. We recorded simultaneous PPG signals for each participant by having them (1) facing the front camera and (2) placing their index fingertip over an iPhone's back camera. We analyzed the PPG signals from the Cardiio-Heart Rate Monitor + 7 Minute Workout (Cardiio) smartphone app for HR measurements compared with a continuous 12-lead electrocardiogram (ECG) as the reference. Recordings of 20 seconds' duration each were acquired at rest, and immediately after moderate- (50%-70% maximum HR) and vigorous- (70%-85% maximum HR) intensity exercise, and repeated successively until return to resting HR. We used Bland-Altman plots to examine agreement between ECG and PPG-estimated HR. The accuracy criterion was root mean square error (RMSE) ≤5 beats/min or ≤10%, whichever was greater, according to the American National Standards Institute/Association for the Advancement of Medical Instrumentation EC-13 standard. RESULTS: We analyzed a total of 631 fingertip and 626 facial PPG measurements. Fingertip PPG-estimated HRs were strongly correlated with resting ECG HR (r=.997, RMSE=1.03 beats/min or 1.40%), postmoderate-intensity exercise (r=.994, RMSE=2.15 beats/min or 2.53%), and postvigorous-intensity exercise HR (r=.995, RMSE=2.01 beats/min or 1.93%). The correlation of facial PPG-estimated HR was stronger with resting ECG HR (r=.997, RMSE=1.02 beats/min or 1.44%) than with postmoderate-intensity exercise (r=.982, RMSE=3.68 beats/min or 4.11%) or with postvigorous-intensity exercise (r=.980, RMSE=3.84 beats/min or 3.73%). Bland-Altman plots showed better agreement between ECG and fingertip PPG-estimated HR than between ECG and facial PPG-estimated HR. CONCLUSIONS: We found that HR detection by the Cardiio smartphone app was accurate at rest and after moderate- and vigorous-intensity exercise in a healthy young adult sample. Contact-free facial PPG detection is more convenient but is less accurate than finger PPG due to body motion after exercise.