Utilizing Machine Learning Techniques to Predict the Efficacy of Aerobic Exercise Intervention on Young Hypertensive Patients Based on Cardiopulmonary Exercise Testing.

Recently, the incidence of hypertension has significantly increased among young adults. While aerobic exercise intervention (AEI) has long been recognized as an effective treatment, individual differences in response to AEI can seriously influence clinicians' decisions. In particular, only a few studies have been conducted to predict the efficacy of AEI on lowering blood pressure (BP) in young hypertensive patients. As such, this paper aims to explore the implications of various cardiopulmonary metabolic indicators in the field by mining patients' cardiopulmonary exercise testing (CPET) data before making treatment plans. CPET data are collected "breath by breath" by using an oxygenation analyzer attached to a mask and then divided into four phases: resting, warm-up, exercise, and recovery. To mitigate the effects of redundant information and noise in the CPET data, a sparse representation classifier based on analytic dictionary learning was designed to accurately predict the individual responsiveness to AEI. Importantly, the experimental results showed that the model presented herein performed better than the baseline method based on BP change and traditional machine learning models. Furthermore, the data from the exercise phase were found to produce the best predictions compared with the data from other phases. This study paves the way towards the customization of personalized aerobic exercise programs for young hypertensive patients.

A partial encryption algorithm for medical images based on quick response code and reversible data hiding technology.

BACKGROUND: Medical image data, like most patient information, have a strong requirement for privacy and confidentiality. This makes transmitting medical image data, within an open network, problematic, due to the aforementioned issues, along with the dangers of data/information leakage. Possible solutions in the past have included the utilization of information-hiding and image-encryption technologies; however, these methods can cause difficulties when attempting to recover the original images. METHODS: In this work, we developed an algorithm for protecting medical image key regions. Coefficient of variation is first employed to identify key regions, a.k.a. image lesion areas; then additional areas are processed as blocks and texture complexity is analyzed. Next, our novel reversible data-hiding algorithm embeds lesion area contents into a high-texture area, after which an Arnold transformation is utilized to protect the original lesion information. After this, we use image basic information ciphertext and decryption parameters to generate a quick response (QR) code used in place of original key regions. RESULTS: The approach presented here allows for the storage (and sending) of medical image data within open network environments, while ensuring only authorized personnel are able to recover sensitive patient information (both image and meta-data) without information loss. DISCUSSION: Peak signal to noise ratio and the Structural Similarity Index measures show that the algorithm presented in this work can encrypt and restore original images without information loss. Moreover, by adjusting the threshold and the Mean Squared Error, we can control the overall quality of the image: the higher the threshold, the better the quality and vice versa. This allows the encryptor to control the amount of degradation as, at appropriate amounts, degradation aids in the protection of the image. CONCLUSIONS: As shown in the experimental results, the proposed method allows for (a) the safe transmission and storage of medical image data, (b) the full recovery (no information loss) of sensitive regions within the medical image following encryption, and (c) meta-data about the patient and image to be stored within and recovered from the public image.

Development of a support vector machine learning and smart phone Internet of Things-based architecture for real-time sleep apnea diagnosis.

BACKGROUND: The breathing disorder obstructive sleep apnea syndrome (OSAS) only occurs while asleep. While polysomnography (PSG) represents the premiere standard for diagnosing OSAS, it is quite costly, complicated to use, and carries a significant delay between testing and diagnosis. METHODS: This work describes a novel architecture and algorithm designed to efficiently diagnose OSAS via the use of smart phones. In our algorithm, features are extracted from the data, specifically blood oxygen saturation as represented by SpO2. These features are used by a support vector machine (SVM) based strategy to create a classification model. The resultant SVM classification model can then be employed to diagnose OSAS. To allow remote diagnosis, we have combined a simple monitoring system with our algorithm. The system allows physiological data to be obtained from a smart phone, the data to be uploaded to the cloud for processing, and finally population of a diagnostic report sent back to the smart phone in real-time. RESULTS: Our initial evaluation of this algorithm utilizing actual patient data finds its sensitivity, accuracy, and specificity to be 87.6%, 90.2%, and 94.1%, respectively. DISCUSSION: Our architecture can monitor human physiological readings in real time and give early warning of abnormal physiological parameters. Moreover, after our evaluation, we find 5G technology offers higher bandwidth with lower delays ensuring more effective monitoring. In addition, we evaluate our algorithm utilizing real-world data; the proposed approach has high accuracy, sensitivity, and specific, demonstrating that our approach is very promising. CONCLUSIONS: Experimental results on the apnea data in University College Dublin (UCD) Database have proven the efficiency and effectiveness of our methodology. This work is a pilot project and still under development. There is no clinical validation and no support. In addition, the Internet of Things (IoT) architecture enables real-time monitoring of human physiological parameters, combined with diagnostic algorithms to provide early warning of abnormal data.

Using an artificial neural network to map cancer common data elements to the biomedical research integrated domain group model in a semi-automated manner.

BACKGROUND: The medical community uses a variety of data standards for both clinical and research reporting needs. ISO 11179 Common Data Elements (CDEs) represent one such standard that provides robust data point definitions. Another standard is the Biomedical Research Integrated Domain Group (BRIDG) model, which is a domain analysis model that provides a contextual framework for biomedical and clinical research data. Mapping the CDEs to the BRIDG model is important; in particular, it can facilitate mapping the CDEs to other standards. Unfortunately, manual mapping, which is the current method for creating the CDE mappings, is error-prone and time-consuming; this creates a significant barrier for researchers who utilize CDEs. METHODS: In this work, we developed a semi-automated algorithm to map CDEs to likely BRIDG classes. First, we extended and improved our previously developed artificial neural network (ANN) alignment algorithm. We then used a collection of 1284 CDEs with robust mappings to BRIDG classes as the gold standard to train and obtain the appropriate weights of six attributes in CDEs. Afterward, we calculated the similarity between a CDE and each BRIDG class. Finally, the algorithm produces a list of candidate BRIDG classes to which the CDE of interest may belong. RESULTS: For CDEs semantically similar to those used in training, a match rate of over 90% was achieved. For those partially similar, a match rate of 80% was obtained and for those with drastically different semantics, a match rate of up to 70% was achieved. DISCUSSION: Our semi-automated mapping process reduces the burden of domain experts. The weights are all significant in six attributes. Experimental results indicate that the availability of training data is more important than the semantic similarity of the testing data to the training data. We address the overfitting problem by selecting CDEs randomly and adjusting the ratio of training and verification samples. CONCLUSIONS: Experimental results on real-world use cases have proven the effectiveness and efficiency of our proposed methodology in mapping CDEs with BRIDG classes, both those CDEs seen before as well as new, unseen CDEs. In addition, it reduces the mapping burden and improves the mapping quality.

A semantics-oriented computational approach to investigate microRNA regulation on glucocorticoid resistance in pediatric acute lymphoblastic leukemia.

BACKGROUND: Acute lymphoblastic leukemia is the most prevalent neoplasia among children. Despite the tremendous achievements of state-of-the-art treatment strategies, drug resistance is still a major cause of chemotherapy failure leading to relapse in pediatric acute lymphoblastic leukemia. The underlying mechanisms of such phenomenon are not yet clear and subject to further exploration. Prior research has shown that microRNAs can act as post-transcriptional regulators of many genes related to drug resistance. However, details of microRNA regulation mechanisms in pediatric acute lymphoblastic leukemia are far from completely understood. METHODS: We utilized a computational approach based upon emerging biomedical and biological ontologies and semantic technologies to investigate the important roles of microRNA: mRNA regulation on glucocorticoid resistance in pediatric acute lymphoblastic leukemia. In particular, various filtering mechanisms were designed based on the user-provided MeSH term to narrow down the most promising microRNAs in an effective manner. RESULTS: During our manual search on background literature, we found a total of 18 candidate microRNAs that possibly regulate glucocorticoid resistance in pediatric acute lymphoblastic leukemia. After the first-round filtering using the Broader-Match option where both the user-provided MeSH term and its direct parent term were utilized, the number of targets for 18 microRNAs was reduced from 232 to 74. During the second-round filtering with the Exact-Match option where only the MeSH term itself was utilized, the number of targets was further reduced to 19. Finally, we conducted semantic searches in the OmniSearch software tool on the five likely regulating microRNAs and identified two most likely microRNAs. CONCLUSIONS: We successfully identified two microRNAs, hsa-miR-142-3p and hsa-miR-17-5p, which are computationally predicted to closely relate to glucocorticoid resistance, thus potentially serving as novel biomarkers and therapeutic targets in pediatric acute lymphoblastic leukemia.

An integrative approach to investigate the association among high-sensitive C-reactive protein, body fat mass distribution, and other cardiometabolic risk factors in young healthy women.

Prior research has indicated that as an important biomarker of chronic low-grade inflammation, high-sensitivity C-reactive protein (hs-CRP) can play important roles on the onset of metabolic syndrome and cardiovascular diseases (CVD). We conducted an integrative approach, which combines biological wet-lab experiments, statistical analysis, and semantics-oriented bioinformatics & computational analysis, to investigate the association among hs-CRP, body fat mass (FM) distribution, and other cardiometabolic risk factors in young healthy women. Research outcomes in this study resulted in two novel discoveries. Discovery 1: There are four primary determinants for hs-CRP, i.e., central/abdominal FM (a.k.a. trunk FM) accumulation, leptin, high density lipoprotein cholesterol (HDL-C), and plasminogen activator inhibitior-1 (PAI-1). Discovery 2: Chronic inflammation may involve in adipocyte-cytokine interaction underlying the metabolic derangement in healthy young women.

The development of non-coding RNA ontology.

Identification of non-coding RNAs (ncRNAs) has been significantly improved over the past decade. On the other hand, semantic annotation of ncRNA data is facing critical challenges due to the lack of a comprehensive ontology to serve as common data elements and data exchange standards in the field. We developed the Non-Coding RNA Ontology (NCRO) to handle this situation. By providing a formally defined ncRNA controlled vocabulary, the NCRO aims to fill a specific and highly needed niche in semantic annotation of large amounts of ncRNA biological and clinical data.