Predicting Childhood Obesity Based on Single and Multiple Well-Child Visit Data Using Machine Learning Classifiers.

Childhood obesity is a public health concern in the United States. Consequences of childhood obesity include metabolic disease and heart, lung, kidney, and other health-related comorbidities. Therefore, the early determination of obesity risk is needed and predicting the trend of a child's body mass index (BMI) at an early age is crucial. Early identification of obesity can lead to early prevention. Multiple methods have been tested and evaluated to assess obesity trends in children. Available growth charts help determine a child's current obesity level but do not predict future obesity risk. The present methods of predicting obesity include regression analysis and machine learning-based classifications and risk factor (threshold)-based categorizations based on specific criteria. All the present techniques, especially current machine learning-based methods, require longitudinal data and information on a large number of variables related to a child's growth (e.g., socioeconomic, family-related factors) in order to predict future obesity-risk. In this paper, we propose three different techniques for three different scenarios to predict childhood obesity based on machine learning approaches and apply them to real data. Our proposed methods predict obesity for children at five years of age using the following three data sets: (1) a single well-child visit, (2) multiple well-child visits under the age of two, and (3) multiple random well-child visits under the age of five. Our models are especially important for situations where only the current patient information is available rather than having multiple data points from regular spaced well-child visits. Our models predict obesity using basic information such as birth BMI, gestational age, BMI measures from well-child visits, and gender. Our models can predict a child's obesity category (normal, overweight, or obese) at five years of age with an accuracy of 89%, 77%, and 89%, for the three application scenarios, respectively. Therefore, our proposed models can assist healthcare professionals by acting as a decision support tool to aid in predicting childhood obesity early in order to reduce obesity-related complications, and in turn, improve healthcare.

Analyte Quantity Detection from Lateral Flow Assay Using a Smartphone.

Lateral flow assay (LFA) technology has recently received interest in the biochemical field since it is simple, low-cost, and rapid, while conventional laboratory test procedures are complicated, expensive, and time-consuming. In this paper, we propose a robust smartphone-based analyte detection method that estimates the amount of analyte on an LFA strip using a smartphone camera. The proposed method can maintain high estimation accuracy under various illumination conditions without additional devices, unlike conventional methods. The robustness and simplicity of the proposed method are enabled by novel image processing and machine learning techniques. For the performance analysis, we applied the proposed method to LFA strips where the target analyte is albumin protein of human serum. We use two sets of training LFA strips and one set of testing LFA strips. Here, each set consists of five strips having different quantities of albumin-10 femtograms, 100 femtograms, 1 picogram, 10 picograms, and 100 picograms. A linear regression analysis approximates the analyte quantity, and then machine learning classifier, support vector machine (SVM), which is trained by the regression results, classifies the analyte quantity on the LFA strip in an optimal way. Experimental results show that the proposed smartphone application can detect the quantity of albumin protein on a test LFA set with 98% accuracy, on average, in real time.

A novel diversity method for smartphone camera-based heart rhythm signals in the presence of motion and noise artifacts.

The advent of smartphones has advanced the use of embedded sensors to acquire various physiological information. For example, smartphone camera sensors and accelerometers can provide heart rhythm signals to the subjects, while microphones can give respiratory signals. However, the acquired smartphone-based physiological signals are more vulnerable to motion and noise artifacts (MNAs) compared to using medical devices, since subjects need to hold the smartphone with proper contact to the smartphone camera and lens stably and tightly for a duration of time without any movement in the hand or finger. This results in more MNA than traditional methods, such as placing a finger inside a tightly enclosed pulse oximeter to get PPG signals, which provides stable contact between the sensor and the subject's finger. Moreover, a smartphone lens does not block ambient light in an effective way, while pulse oximeters are designed to block the ambient light effectively. In this paper, we propose a novel diversity method for smartphone signals that reduces the effect of MNAs during heart rhythm signal detection by 1) acquiring two heterogeneous signals from a color intensity signal and a fingertip movement signal, and 2) selecting the less MNA-corrupted signal of the two signals. The proposed method has advantages in that 1) diversity gain can be obtained from the two heterogeneous signals when one signal is clean while the other signal is corrupted, and 2) acquisition of the two heterogeneous signals does not double the acquisition procedure but maintains a single acquisition procedure, since two heterogeneous signals can be obtained from a single smartphone camera recording. In our diversity method, we propose to choose the better signal based on the signal quality indices (SQIs), i.e., standard deviation of instantaneous heart rate (STD-HR), root mean square of the successive differences of peak-to-peak time intervals (RMSSD-T), and standard deviation of peak values (STD-PV). As a performance metric evaluating the proposed diversity method, the ratio of usable period is considered. Experimental results show that our diversity method increases the usable period 19.53% and 6.25% compared to the color intensity or the fingertip movement signals only, respectively.