Search

Background: Blood pressure (BP) is an essential indicator for human health and is known to be greatly influenced by lifestyle factors, like activity and sleep factors. However, the degree of impact of each lifestyle factor on BP is unknown and may vary between individuals. Our goal is to investigate the relationships between BP and lifestyle factors and provide personalized and precise recommendations to improve BP, as opposed to the current practice of general lifestyle recommendations. Method: Our proposed system consists of automated data collection using home BP monitors and wearable activity trackers and feature engineering techniques to address time-series data and enhance interpretability. We propose Random Forest with Shapley-Value-based Feature Selection to offer personalized BP modeling and top lifestyle factor identification, and subsequent generation of precise recommendations based on the top factors. Result: In collaboration with UC San Diego Health and Altman Clinical and Translational Research Institute, we performed a clinical study, applying our system to 25 patients with elevated BP or stage I hypertension for three consecutive months. Our study results validate our system’s ability to provide accurate personalized BP models and identify the top features which can vary greatly between individuals. We also validate the effectiveness of personalized recommendations in a randomized controlled experiment. After receiving recommendations, the subjects in the experimental group decreased their BPs by 3.8 and 2.3 for systolic and diastolic BP, compared to the decrease of 0.3 and 0.9 for the subjects without recommendations. Conclusion: The study demonstrates the potential of using wearables and machine learning to develop personalized models and precise lifestyle recommendations to improve BP.

The prognostic and health management (PHM) of rolling bearings has been a popular research area. Since bearing fault is inevitable during degradation, how to improve the PHM performance based on both degradation states and fault types is still an open problem. In this study, two multilabel learning algorithms are proposed for PHM of rolling bearings, named personalized binary relevance (PBR) and hierarchical multilabel K-nearest neighbor (HML-KNN), respectively. Degradation states and fault types are used as the labels of the bearing data so that each sample has a corresponding label sequence, that is to say, the PHM problem is converted to a multilabel learning problem. Both algorithms have a personalized search process, which can not only help samples build a personalized model to improve classification accuracy but also solve the problem of data imbalance between labels. At the same time, the two algorithms also have their own characteristics and focus on different application situations. The PBR algorithm has faster modeling speed, more flexible use, and replaceable subclassifiers. HML-KNN is a high-order algorithm with global information analysis capabilities through the hierarchical processing of data and the conversion of label information. Both methods have achieved good enough results in the XJTU-SY bearing dataset. In order to illustrate the practicality of the algorithm, the experimental part further increases the difficulty. Using only a single faulty sample as the training set to determine the type of compound fault, the algorithms also show high performance. In the era of industrial big data, the depth of data mining and the design of algorithm models will help us better manage equipment health. [ABSTRACT FROM AUTHOR]

Objective: Personalization of hemodynamic modeling plays a crucial role in functional prediction of the cardiovascular system (CVS). While reduced-order models of one-dimensional (1D) blood vessel models with zero-dimensional (0D) blood vessel and heart models have been widely recognized to be an effective tool for reasonably estimating the hemodynamic functions of the whole CVS, practical personalized models are still lacking. In this paper, we present a novel 0-1D coupled, personalized hemodynamic model of the CVS that can predict both pressure waveforms and flow velocities in arteries. Methods: We proposed a methodology by combining the multiscale CVS model with the Levenberg–Marquardt optimization algorithm for effectively solving an inverse problem based on measured blood pressure waveforms. Hemodynamic characteristics including brachial arterial pressure waveforms, artery diameters, stroke volumes, and flow velocities were measured noninvasively for 62 volunteers aged from 20 to 70 years for developing and validating the model. Results: The estimated arterial stiffness shows a physiologically realistic distribution. The model-fitted individual pressure waves have an averaged mean square error (MSE) of 7.1 mmHg2; simulated blood flow velocity waveforms in carotid artery match ultrasound measurements well, achieving an average correlation coefficient of 0.911. Conclusion: The model is efficient, versatile, and capable of obtaining well-fitting individualized pressure waveforms while reasonably predicting flow waveforms. Significance: The proposed methodology of personalized hemodynamic modeling may therefore facilitate individualized patient-specific assessment of both physiological and pathological functions of the CVS. [ABSTRACT FROM AUTHOR]

Objective: In this paper, a framework to visualize and model internal fixation plates is presented for computer-aided personalized and minimally invasive curved bone fracture surgery. Methods: We focus on personalized reverse reconstruction of the bone fracture plate based on three-dimensional (3-D) mesh models obtained from a 3-D optical scanner. The steps of the method are as follows. First, principal component analysis and the K-means method are used to reconstruct a Bezier curve (ridge line) of broken bones. Second, based on the geometric shape of the curved broken bones, a capsule projection model of the broken bones is proposed to obtain the feature information of the broken bone sections. Third, the ordering points to identify the clustering structure (OPTICS) method is utilized for preregistration (rough registration). Fourth, a regional self-growth strategy is designed to extract the cross-section points. Fifth, the iterative closest point method is applied for the accurate registration of the fracture surface models. Finally, a personalized internal fixation plate model is reconstructed based on several user points. Results: The internal fixation plate model can be reconstructed according to the patient's bone parameters. Conclusion: Clinicians can use this framework to obtain personalized and accurate internal fixation plate models that effectively represent the broken bones of patients. Via X-ray navigation, the personalized forged plate can be fixed on the target area through a small incision. Significance: This framework provides a reasonable and practicable technical approach for computer-aided minimally invasive curved bone fracture surgery. [ABSTRACT FROM AUTHOR]