An Intelligent Approach for Prediction of Life Style Conditions in Adolescent Girls by Analyzing Health Parameters

Monitoring health parameters has become a challenging task due to unpredictable diseases and related symptoms. Lifestyle is a crucial factor to decide to be healthy, in adolescent girls especially. This chapter presents a work in progress on prediction of lifestyle of adolescent girls based on problems like unhealthy routines of eating habits, sleep patterns, stress, etc. Therefore, an IT-enabled system is presented to assess current lifestyle of adolescent girls in an easy and faster way. A systematic survey is conducted with specially designed survey form by consulting medical practitioners and physical trainers. Twenty-one factors related to age, diet habits, exercise habits, sleeping habits, health history, etc. are included in the expert-guided form. One hundred fifty-five individual responses are collected and assessed manually by medical experts to annotate as healthy or unhealthy types. The healthy lifestyle prediction accuracy with support vector machine is 83.87% whereas it is 80.64% using logistic regression.

Detection of the level of attention in children with ADHD through brain waves and corporal posture1

In the current world, the need to know instantaneous information that helps people to know their current physical and intellectual conditions has become paramount, each time new systems that provide information to the user in real time are incorporated in portable devices. This information indicates different health parameters of the user, it can be obtained through their physiological variables such as: number of steps, heart rate, oxygenation level in the blood and other ones. One of the most requested intellectual conditions to be known by the user is: the level of attention reached when the user executes a task. This work describes a methodology and the experimentation to know the level of attention of people through a test to identify colors also are shown the development and the application of a system (hardware and software) to measure the level of attention of people using two input signals: corporal posture and brain waves. The mathematical analysis to find the correlation between the corporal posture and the level of attention is shown in this paper. The results obtained indicate that the corporal posture influences on the level of attention of people directly.

Exploring the Link between Leaky-Gut-Related Markers and Metabolic Health in a Large Dutch Adult Population

A leaky gut can trigger chronic inflammation and poses a primary risk for metabolic diseases. This study established a relationship between intestinal integrity (leaky gut) and metabolic health in a general population. Leaky-gut markers (LGMs) were studied in a large population of Dutch adults with a broad spectrum of metabolic health. This study enrolled 500 individuals selected within the NQplus cohort study (n = 2048) by stratified randomization, based on waist circumference, fasting glucose, and high-density lipoprotein (HDL) cholesterol to obtain a representative and balanced population in terms of metabolic health parameters, sex (male/female), and age (<54/≥54 years). LGMs—zonulin, lipopolysaccharide-binding protein (LBP), and soluble CD14 (sCD14)—were measured in EDTA plasma or serum. Zonulin was most strongly associated with metabolic health. Zonulin and LBP were most strongly associated with the inflammatory marker C-reactive protein (CRP). The quartile analysis for zonulin and LBP showed that most metabolic health parameters and CRP levels increased from Q1 to Q4, with significant differences between quartiles, except for markers related to glucose homeostasis (glucose and glycated hemoglobin A1c (HbA1c)). Associations between LGMs and metabolic health parameters in this large Dutch adult population indicate that LGMs are valuable markers for identifying people at risk of a leaky gut and subsequent chronic inflammation linked to metabolic disorders.

Association Between Sense of Coherence and Health Outcomes at 10 and 20 Years Follow-Up: A Population-Based Longitudinal Study in Germany

Background: The sense of coherence (SOC) is reported to influence health, but health may also have an impact on SOC. The objective of this study was to examine the longitudinal associations between SOC and selected self-reported and physician-assessed health outcomes over a period of 10 and 20 years and to determine the predominant direction of the associations.Methods: We conducted a population-based, longitudinal study, involving 392 participants (188 females and 204 males; mean age 43.01 years) who were followed for a median of 10 and 18 years. Analyses of variance were carried out to examine the longitudinal associations between SOC at baseline and health outcomes (i.e., self-rated health status, SHS; physical health status assessed by a physician, PHS; self-reported satisfaction with life, SWL) at follow-ups. The direction of associations was examined using a cross-lagged model on correlation coefficients.Results: There were significant group effects for SOC at baseline on SHS at 20-year follow-up (F = 4.09, p = 0.018, ηp2 = 0.041), as well as on SWL at 10-year (F = 12.67, p &lt; 0.01, ηp2 = 0.072) and at 20-year follow-up (F = 8.09, p &lt; 0.1, ηp2 = 0.069). SHS (r = 0.238, p &lt; 0.01), PHS (r = −0.140, p &lt; 0.05) and SWL (r = 0.400, p &lt; 0.01) predicted SOC at 10-year follow-up stronger than vice versa. The direction of associations between SOC and health parameters at 20-year follow-up was less consistent.Conclusions: The long-term associations between SOC and self-reported and physician-assessed health may be reciprocal in community-dwelling adults. More research is needed to examine the predictive power of health on SOC and whether interventions targeted at improving health parameters, may impact SOC.

Heterogeneity in statin responses explained by variation in the human gut microbiome

Statins remain one of the most prescribed medications worldwide. While effective in decreasing atherosclerotic cardiovascular disease risk, statin use is associated with several side effects for a subset of patients, including disrupted metabolic control and increased risk of type II diabetes. We investigated the potential role of the gut microbiome in modifying patient response to statin therapy. In a cohort of >1840 individuals, we find that the hydrolyzed substrate for 3-hydroxy-3-methylglutarate-CoA (HMG-CoA) reductase, HMG, may serve as a reliable marker for statin on-target effects. Through exploring gut microbiome associations between blood-derived measures of statin effectiveness and metabolic health parameters among statin users and non-users, we find that heterogeneity in statin response is associated with variation in the gut microbiome. A Bacteroides rich, α-diversity depleted, microbiome composition corresponds to the strongest statin on-target response, but also greatest disruption to glucose homeostasis, indicating lower treatment doses and/or complementary therapies may be beneficial in those individuals. Our findings suggest a potential path towards personalizing statin treatment through gut microbiome monitoring.Between 25% - 30% of older adults across the United States and Europe take statins regularly for the purpose of treating or preventing atherosclerotic cardiovascular disease (ACVD), making statins one of the most prescribed medications in the developed world 1,2. While statins have proven to be highly effective in decreasing ACVD-associated mortality, considerable heterogeneity exists in terms of efficacy (i.e., lowering low density lipoprotein (LDL) cholesterol) 3. Furthermore, statin use can give rise to a number of side effects in a subset of patients, including myopathy, disrupted glucose control, and increased risk of developing type II diabetes (T2D) 4–8. Several guidelines exist for which at-risk populations should be prescribed statins and at what intensity 9. However, despite considerable progress in identifying pharmacological 10 and genetic factors 11 contributing to heterogeneity in statin response, personalized approaches to statin therapy remain limited. Many times, treatment decisions are made through trial and error between the clinician and patient to obtain an optimal tolerable dose 12. Avoiding this trial-and-error phase through individualized analysis of genetic, physiological, and health parameters has the potential to improve drug tolerance, adherence, and long-term health benefits, as well as guide complementary therapies aimed at mitigating side effects.Several studies have recently demonstrated a link between the gut microbiome and statin use 13,14. Similar to other prescription drugs, statins are widely metabolized by gut bacteria into secondary compounds 15,16. This indicates that the gut microbiome may impact statin bioavailability or potency to its host, contributing to the interindividual variability in LDL response seen among statin users 17. Additionally, biochemical modification of statins by gut bacteria could potentially contribute to side effects of the drug 18. Independent of statins, the gut microbiome has a well characterized role in contributing to host metabolic health through regulating insulin sensitivity, blood glucose, and inflammation, hence sharing considerable overlap with off-target effects of statin therapy 19,20.Statin intake has also been implicated in shifting gut microbiome composition, where primarily obese individuals taking statins were less likely to be classified into a putative gut microbiome compositional state, or ‘enterotype’, defined by high relative abundance of Bacteroides and a depletion of short-chain fatty acid (SCFA) producing Firmicutes taxa 21. However, contradictory findings in animal models have also been reported, where a statin intervention decreased abundance of SCFA-producing taxa and, consequently, the gut ecosystem’s capacity to produce butyrate 22.Given the numerous documented interactions between the gut microbiome and statins, and the established effect of the gut microbiome on metabolic health, we sought to explore the potential role of the gut microbiome in modifying the effect of statins on inhibiting their target enzyme 3-hydroxy-3-methylglutarate-CoA (HMG-CoA) reductase, as well as influencing the negative side effects of statins on metabolic health parameters. We analyzed data from over 1840 deeply-phenotyped individuals with extensive medication histories, clinical laboratory tests, plasma metabolomics, whole genome and stool 16S rRNA gene amplicon sequencing data. We found that heterogeneity in statin on-target effects and off-target metabolic disruption could be explained by variation in the composition of the gut microbiome. Overall, our results suggest that, with further study and refinement, the taxonomic composition of the gut microbiome may be used to inform personalized statin therapies.

Teaming-up nurses with ophthalmologists to expand the reach of eye care in a middle-income country: Validation of health data acquisition by nursing staff in a telemedicine strategy

Telemedicine can be used to conduct ophthalmological assessment of patients, facilitating patient access to specialist care. Since the teleophthalmology models require data collection support from other health professionals, the purpose of our study was to assess agreement between the nursing technician and the ophthalmologist in acquisition of health parameters that can be used for remote analysis as part of a telemedicine strategy. A cross-sectional study was conducted with 140 patients referred to an ophthalmological telediagnosis center by primary healthcare doctors. The health parameters evaluated were visual acuity (VA), objective ophthalmic measures acquired by autorefraction, keratometry, and intraocular pressure (IOP). Bland-Altman plots were used to analyze agreement between the nursing technician and the ophthalmologist. The Bland-Altman analysis showed a mean bias equal to zero for the VA measurements [95%-LoA: -0.25–0.25], 0.01 [95%-LoA: -0.86–0.88] for spherical equivalent (M), -0.08 [95%-LoA: -1.1–0.95] for keratometry (K) and -0.23 [95%-LoA: -4.4–4.00] for IOP. The measures had a high linear correlation (R [95%CI]: 0.87 [0.82–0.91]; 0.97 [0.96–0.98]; 0.96 [0.95–0.97] and 0.88 [0.84–0.91] respectively). The results observed demonstrate that remote ophthalmological data collection by adequately trained health professionals is viable. This confirms the utility and safety of these solutions for scenarios in which access to ophthalmologists is limited.

Ovarian Reserve Assessed by the Anti-Mullerian Hormone and Reproductive Health Parameters in Women With Crohn´s Disease, a Case-Control Study

According to several studies, women with Crohn's disease (CD) had reduced fertility, which is mostly due to voluntary decisions and reduced ovarian reserve. In our study, we aimed to compare reproductive health parameters (RHP), previous pregnancy complications and outcomes, and ovarian reserve (OR) assessed by the anti-Mullerian hormone (AMH) in CD patients with healthy controls. In CD patients, we also compared OR according to disease phenotypes. Consecutive pre-menopausal women with CD from two IBD centers were included. The control group consisted of age and BMI-matched healthy controls. We used a questionnaire that included RHP, CD phenotype, and CD activity. Serum AMH was assessed by the Elecsys AMH plus essay. We enrolled 50 patients and 56 controls with a median age of 31 years. All CD patients were in clinical remission. We observed no difference in RHP or AMH (median 2.6 vs. 2.1 ug/l, p = 0.98), or the proportion of low OR (AMH<1,77, 38 vs. 41.1 %, p=0.84). The slope of age-related decrease did not differ between the groups. The subgroup of CD patients after surgery and those older than 30 years with CD for >5years had a steeper decrease in AMH (slope -0.12 vs. -0.29, p = 0.04 and -0.31 vs. -0.2, p = 0.029). In a multivariate analysis, age was the single independent predictor of low OR (OR=1.25). In women with Crohn’s disease, once the disease activity is under control, the reproductive health and ovarian reserve do not substantially differ from healthy controls.

Ensemble-Based Machine Learning for Predicting Sudden Human Fall Using Health Data

We attempt to predict the accidental fall of human beings due to sudden abnormal changes in their health parameters such as blood pressure, heart rate, and sugar level. In medical terminology, this problem is known as Syncope. The primary motivation is to prevent such falls by predicting abnormal changes in these health parameters that might trigger a sudden fall. We apply various machine learning algorithms such as logistic regression, a decision tree classifier, a random forest classifier, K-Nearest Neighbours (KNN), a support vector machine, and a naive Bayes classifier on a relevant dataset and verify our results with the cross-validation method. We observe that the KNN algorithm provides the best accuracy in predicting such a fall. However, the accuracy results of some other algorithms are also very close. Thus, we move one step further and propose an ensemble model, Majority Voting, which aggregates the prediction results of multiple machine learning algorithms and finally indicates the probability of a fall that corresponds to a particular human being. The proposed ensemble algorithm yields 87.42% accuracy, which is greater than the accuracy provided by the KNN algorithm.