We propose a random forest classifier for identifying adequacy of liver MR images using handcrafted (HC) features and deep convolutional neural networks (CNNs), and analyze the relative role of these two components in relation to the training sample size. The HC features, specifically developed for this application, include Gaussian mixture models, Euler characteristic curves and texture analysis. Using HC features outperforms the CNN for smaller sample sizes and with increased interpretability. On the other hand, with enough training data, the combined classifier outperforms the models trained with HC features or CNN features alone. These results illustrate the added value of HC features with respect to CNNs, especially when insufficient data is available, as is often found in clinical studies.

Risk factors for pancreatic cancer among patients with pancreatic cysts are incompletely characterized. The primary aim of this study is to evaluate risk factors for development of pancreatic cancer among patients with pancreatic cysts. We conducted a retrospective case-control study of U.S. Veterans with suspected BD-IPMN diagnosis from 1999 to 2013. Age (HR 1.03 per year, 95%CI 1.00-1.06), larger cyst size at cyst diagnosis (HR 1.03 per mm, 95%CI 1.01-1.04), cyst growth rate (HR 1.22 per mm/yr, 95%CI 1.14-1.31), and pancreatic duct dilation (5-9.9 mm, HR 3.78, 95%CI 1.90-7.51; ≥ 10 mm, HR 13.57, 95%CI 5.49-33.53) are significant predictors for pancreatic cancer on multivariable analysis. Age, cyst size, cyst growth rate, and high-risk or worrisome features are associated with higher risk of developing pancreatic cancer. Applying current and developing novel strategies are required to optimize early detection of pancreatic cancer after cyst diagnosis.

Wearable accelerometers allow for continuous monitoring of function and behaviors in the participant’s naturalistic environment. Devices are typically worn in different body locations depending on the concept of interest and endpoint under investigation. The lumbar and wrist are commonly used locations: devices placed at the lumbar region enable the derivation of spatio-temporal characteristics of gait, while wrist-worn devices provide measurements of overall physical activity (PA). Deploying multiple devices in clinical trial settings leads to higher patient burden negatively impacting compliance and data quality and increases the operational complexity of the trial. In this work, we evaluated the joint information shared by features derived from the lumbar and wrist devices to assess whether gait characteristics can be adequately represented by PA measured with wrist-worn devices. Data collected at the Pfizer Innovation Research (PfIRe) Lab were used as a real data example, which had around 7 days of continuous at-home data from wrist- and lumbar-worn devices (GENEActiv) obtained from a group of healthy participants. The relationship between wrist- and lumbar-derived features was estimated using multiple statistical methods, including penalized regression, principal component regression, partial least square regression, and joint and individual variation explained (JIVE). By considering multilevel models, both between- and within-subject effects were taken into account. This work demonstrated that selected gait features, which are typically measured with lumbar-worn devices, can be represented by PA features measured with wrist-worn devices, which provides preliminary evidence to reduce the number of devices needed in clinical trials and to increase patients’ comfort. Moreover, the statistical methods used in this work provided an analytic framework to compare repeated measures collected from multiple data modalities.

Alzheimer’s disease (AD) studies often collect longitudinal biomarker measures of multiple cohorts at different stages of disease and follow these biomarkers with a relatively short period of time. The heterogeneity of the longitudinal patterns of biomarkers can be ubiquitous across both individual trajectories and cognitive domains. We propose a flexible Bayesian multivariate growth mixture model to identify distinct longitudinal patterns of data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) study. A Gibbs sampling is implemented for achieving the Bayesian inference. We perform a simulation study to demonstrate the adequate performance of our proposed approach and apply the model to identify three latent cognitive decline patterns among patients from the ADNI study.

Background: Digital health technologies, such as accelerometry, offer low participant burden and provide quantitative metrics with ease of deployment, making them increasingly popular for gait monitoring. Remote gait monitoring delivers quantifiable, continuous health measures over extended periods, surpassing the limited insights from single clinic or laboratory visits and offering a more comprehensive health perspective. Numerous gait algorithm implementations, inspired by prior research, aim to standardize these metrics across devices. The SciKit Digital Health (SKDH) package exemplifies this as a device-agnostic framework. Objective: This study introduces a series of literature-informed enhancements to the SKDH gait algorithm, improving its performance against reference standards and reducing the need for manual parameter adjustments across diverse populations. Methods: A block-wise refinement process was undertaken, examining each algorithmic component for potential enhancements and evaluating their cumulative impact on the complete gait algorithm and the metrics generated. Results: Using data from healthy adult and pediatric participants, the novel gait event estimation method reduced the mean absolute error by more than 50% compared with its predecessor. Following the updates, the intraclass correlation values for final gait metric concordance with the in-laboratory reference improved markedly, from 0.50-0.74 to 0.81-0.90. Additionally, the systematic bias observed in the previous version’s gait speed estimation was rectified, narrowing the difference from the reference from 0.065-0.230 to 0.00-0.03 m/s. Conclusions: The findings from this study provide robust evidence supporting the validity of the enhancements made to the gait algorithm. They demonstrate that a single lumbar accelerometer can capture gait characteristics with high accuracy and reliability across various speeds and age groups.

BACKGROUND Digital health technologies, such as accelerometry, offer low participant burden and provide quantitative metrics with ease of deployment, making them increasingly popular for gait monitoring. Remote gait monitoring delivers quantifiable, continuous health measures over extended periods, surpassing the limited insights from single clinic or laboratory visits and offering a more comprehensive health perspective. Numerous gait algorithm implementations, inspired by prior research, aim to standardize these metrics across devices. The SciKit Digital Health (SKDH) package exemplifies this as a device-agnostic framework. OBJECTIVE This study introduces a series of literature-informed enhancements to the SKDH gait algorithm, improving its performance against reference standards and reducing the need for manual parameter adjustments across diverse populations. METHODS A block-wise refinement process was undertaken, examining each algorithmic component for potential enhancements and evaluating their cumulative impact on the complete gait algorithm and the metrics generated. RESULTS Using data from healthy adult and pediatric participants, the novel gait event estimation method reduced the mean absolute error by more than 50% compared with its predecessor. Following the updates, the intraclass correlation values for final gait metric concordance with the in-laboratory reference improved markedly, from 0.50-0.74 to 0.81-0.90. Additionally, the systematic bias observed in the previous version’s gait speed estimation was rectified, narrowing the difference from the reference from 0.065-0.230 to 0.00-0.03 m/s. CONCLUSIONS The findings from this study provide robust evidence supporting the validity of the enhancements made to the gait algorithm. They demonstrate that a single lumbar accelerometer can capture gait characteristics with high accuracy and reliability across various speeds and age groups.