Single Diseases Research Articles

Diabetes Disease Prediction using Machine-Learning with AI-Powered Health Advice

The integration of machine learning and artificial intelligence is transforming various industries, including healthcare. With the vast amount of patient data available, there is an unprecedented opportunity to utilize machine learning for improving disease detection and diagnosis. This research introduces an advanced prediction system designed to identify multiple diseases simultaneously, addressing the limitations of conventional systems that typically focus on single diseases with varying accuracy levels. The current scope of this system includes predictions for five critical diseases: Heart Disease, Liver Disease, Diabetes, Lung Cancer, and Parkinson’s Disease, with plans to expand its capabilities in the future. The system leverages Convolutional Neural Networks (CNN) to process disease-specific parameters, enabling users to input their data and receive accurate predictions. Advanced feature engineering techniques were applied to enhance model performance, achieving a prediction accuracy of 85%. This platform empowers users to monitor their health proactively, facilitating early interventions and improving quality of life. By harnessing the power of machine learning, this project aims to make a meaningful impact on healthcare, offering reliable and actionable insights to help individuals manage their health effectively. Beyond providing accurate disease predictions, this system empowers users to actively monitor their health, offering personalized insights that facilitate early detection and timely interventions. By proactively addressing potential health risks, the platform aims to enhance the quality of life for individuals by enabling them to manage their health more effectively. Key Words: Machine Learning, Artificial Intelligence, Convolutional Neural Networks (CNN), Feature Engineering, Disease Prediction, Healthcare Monitoring, Proactive Health Management, Predictive System, Deep Learning, Neural Network, AI in Healthcare, Smart Diagnostics.

Educational and income inequalities across diseases in Denmark: a register-based cohort study

Educational attainment and income are often, but not always, associated with disease incidence. Existing research typically examines single diseases, resulting in disparate analyses with little comparability. In this study, we aimed to assess educational and income inequalities across diseases in Denmark. This register-based study included all Danish residents aged at least 30 years between Jan 1, 2013, and Dec 31, 2022, who were born after 1920, and with known educational attainment and income. We used a disease-wide approach to assess associations between education and income and the incidence of 751 diagnostic codes determined upon hospital admission. We estimated age-standardised incidence rates and incidence rate ratios (IRRs) using Poisson regression, adjusted for birth cohort and stratified by sex. Participants were followed up until time of diagnosis, death, emigration, or until Dec 31, 2022. 4 541 309 individuals aged 30 years and older were registered as living in Denmark between Jan 1, 2013, and Dec 31, 2022. 121 083 were excluded due to limited or missing information about educational attainment. 4 420 226 individuals were included in the analysis of educational inequalities (2 232 200 [50%] were female and 2 188 026 [50%] were male). 23 708 were excluded due to absence of income information, and 4 396 518 were included in the analysis of income inequalities (2 223 217 (51%) were female and 2 173 301 (49%) were male). Socioeconomic differences in incidence rates were observed across all disease groups; incidence rates of most diseases decreased with higher educational attainment and income. The magnitude of the socioeconomic inequalities varied substantially. Among non-communicable diseases, the strongest positive association with regard to education was observed in chronic obstructive pulmonary disease for female individuals (low education vs high education, IRR 2·7 [95% CI 2·4-3·0]) and schizophrenia for male inividuals (low education vs high education, IRR 4·4 [2·2-8·8]), and the strongest negative association was in melanoma and other skin cancers for females (low education vs high education, IRR 0·7 [0·7-0·8]) and melanoma and skin cancers for males (low education vs high education, 0·7 [0·6-0·8]). With regard to income, for females, the strongest positive association was observed in schizophrenia (quartile 1 [Q1] vs quartile 4 [Q4], IRR 10·1 [6·1-17·2]), whereas the strongest negative association was in melanoma and other skin cancers (Q1 vs Q4, IRR 0·5 [0·5-0·6]). For males, the strongest positive assocation was schizophrenia (Q1 vs Q4, IRR 18·4 [95% CI 8·5-39·9]) and the strongest negative association was also melanoma and other skin cancers (Q1 vs Q4, IRR 0·5 [0·5-0·6]). The most prevalent disease category, other digestive diseases, was also strongly positively associated with education (low education vs high education, IRR 1·6 [95% CI 1·6-1·6] for females; IRR 1·5 [1·4-1·5] for males) and income (Q1 vs Q4, IRR 1·5 [1·5-1·5] for females; IRR 1·3 [1·3-1·4] for males). Our study provides a detailed representation of the association between two socioeconomic indicators and disease incidence. A broad spectrum of diseases, and not only the most prevalent, show socioeconomic disparities. This finding highlights the need for not only policies that address specific diseases, but also universal policies addressing the root causes of socioeconomic disparities and their health consequences. The Novo Nordisk Foundation.

Habitual Coffee, Tea, and Caffeine Consumption, Circulating Metabolites, and the Risk of Cardiometabolic Multimorbidity.

Cardiometabolic multimorbidity (CM) is an increasing public health concern. Previous observational studies have suggested inverse associations between coffee, tea, and caffeine intake and risks of individual cardiometabolic diseases; however, their associations with CM and related biological markers are unknown. This prospective study involved 172 315 (for caffeine analysis) and 188 091 (tea and coffee analysis) participants free of any cardiometabolic diseases at baseline from the UK Biobank; 168 metabolites were measured among 88 204 and 96 393 participants. CM was defined as the coexistence of at least 2 of the following conditions: type 2 diabetes, coronary heart disease, and stroke. Nonlinear inverse associations of coffee, tea, and caffeine intake with the risk of new-onset CM were observed. Compared with nonconsumers or consumers of less than 100 mg caffeine per day, consumers of moderate amount of coffee (3 drinks/d) or caffeine (200-300 mg/d) had the lowest risk for new-onset CM, with respective hazard ratios (95% CIs) of 0.519 (0.417-0.647) and 0.593 (0.499-0.704). Multistate models revealed that moderate coffee or caffeine intake was inversely associated with risks of almost all developmental stages of CM, including transitions from a disease-free state to single cardiometabolic diseases and subsequently to CM. A total of 80 to 97 metabolites, such as lipid components within very low-density lipoprotein, histidine, and glycoprotein acetyls, were identified to be associated with both coffee, tea, or caffeine intake and incident CM. Habitual coffee or caffeine intake, especially at a moderate level, was associated with a lower risk of new-onset CM and could play important roles in almost all transition phases of CM development. Future studies are warranted to validate the implicated metabolic biomarkers underlying the relation between coffee, tea, and caffeine intake and CM.

What can we learn from multimorbidity? A deep dive from its risk patterns to the corresponding patient profiles

Multimorbidity, the presence of two or more chronic conditions within an individual, represents one of the most intricate challenges for global health systems. Traditional single-disease management often fails to address the multifaceted nature of multimorbidity. Network model emerges as a growing field for elucidating the interconnections among multimorbidity. However, the field lacks a standardized method to compute and visually represent of these networks. Given the challenges, this study proposes a three-stage methodology to decipher multimorbidity. First, we integrate the Failure Modes and Effects Analysis (FMEA) method with the multimorbidity encapsulation framework to develop the Multimorbidity Risk Network (MRN). Second, we use complex network techniques to identify high-risk patterns within MRN communities. Finally, we apply machine learning techniques to correlate these communities with the biological attributes of patients that have been marginalized in most studies. Our approach advocates a paradigm shift from the conventional focus on single diseases to a holistic, patient-centric approach, providing decision-makers with integrated information technology artifacts for deciphering the multimorbidity.

Integrating multi-task and cost-sensitive learning for predicting mortality risk of chronic diseases in the elderly using real-world data

Background and ObjectiveReal-world data encompass population diversity, enabling insights into chronic disease mortality risk among the elderly. Deep learning excels on large datasets, offering promise for real-world data. However, current models focus on single diseases, neglecting comorbidities prevalent in patients. Moreover, mortality is infrequent compared to illness, causing extreme class imbalance that impedes reliable prediction. We aim to develop a deep learning framework that accurately forecasts mortality risk from real-world data by addressing comorbidities and class imbalance. MethodsWe integrated multi-task and cost-sensitive learning, developing an enhanced deep neural network architecture that extends multi-task learning to predict mortality risk across multiple chronic diseases. Each patient cohort with a chronic disease was assigned to a separate task, with shared lower-level parameters capturing inter-disease complexities through distinct top-level networks. Cost-sensitive functions were incorporated to ensure learning of positive class characteristics for each task and achieve accurate prediction of the risk of death from multiple chronic diseases. ResultsOur study covers 15 prevalent chronic diseases and is experimented with real-world data from 482,145 patients (including 9,516 deaths) in Shenzhen, China. The proposed model is compared with six models including three machine learning models: logistic regression, XGBoost, and CatBoost, and three state-of-the-art deep learning models: 1D-CNN, TabNet, and Saint. The experimental results show that, compared with the other compared algorithms, MTL-CSDNN has better prediction results on the test set (ACC=0.99, REC=0.99, PRAUC=0.97, MCC=0.98, G-means = 0.98). ConclusionsOur method provides valuable insights into leveraging real-world data for precise multi-disease mortality risk prediction, offering potential applications in optimizing chronic disease management, enhancing well-being, and reducing healthcare costs for the elderly population.

Association between dietary vitamin A intake and risk of cardiometabolic multimorbidity

The association between vitamin A and single cardiometabolic diseases has been extensively studied, but the relationship between dietary vitamin A intake and the risk of cardiometabolic multimorbidity (CMM) has not been studied. Therefore, the present study was conducted to explore the association with CMM risk by analyzing different sources of vitamin A. This study utilized 13,603 subjects aged ≥ 18 years from 1997 to 2015 from the China Health and Nutrition Survey (CHNS). Dietary intake was calculated from 3 consecutive 24-h dietary recalls combined with a house hold food inventory. CMM is defined as the development of at least two cardiometabolic diseases. After a median follow-up of 9.0 years, there were 1050 new cases of CMM. The risk of CMM was significantly lower in those with higher vitamin A intake (Q1 vs Q5 HR 0.66, 95% CI 0.54–0.81). β-carotene (Q1 vs Q5 HR 0.82, 95% CI 0.66–1.02) and retinol (Q1 vs Q5 HR 0.59, 95% CI 0.48–0.73) intake had a similarly negative correlation. Using restricted cubic spline found an L-shaped relationship between retinol intake and CMM (p non-linear < 0.001). Negative associations were also found in specific CMD groups (hypertension, cardiovascular disease, stroke and diabetes). Dietary intake of vitamin A was negatively associated with CMM risk, and this protective effect was more pronounced in patients with cardiovascular disease. There was an L-shaped association between retinol intake and CMM risk.

Association between chronic pain and risk of cardiometabolic multimorbidity: a prospective cohort study

BackgroundAlthough chronic pain was deleteriously related to single cardiometabolic diseases, the relationship between chronic pain and cardiometabolic multimorbidity remains unclear. The purpose of this study was to investigate the association...

Association between single and multiple cardiometabolic diseases and all-cause mortality among Chinese older adults: A prospective, nationwide cohort study

Background and aimCardiometabolic diseases (CMDs) are leading causes of death and disability, but little is known about the additive mortality effects of multiple CMDs. This study aimed to examine the association between single and multiple CMDs and all-cause mortality among older Chinese population. Methods and resultsUsing the Chinese Longitudinal Healthy Longevity Survey (CLHLS) database, we analyzed data from 2008 to 2018 to assess the relationship between CMDs and mortality. Cox regression models estimated hazard ratios (HRs) and 95% confidence intervals (CIs) for single and multiple CMDs. At baseline, 11,351 participants (56.9% female) aged 60 years or older were included. 11.91% of participants had a single CMD, 1.51% had two CMDs, and 0.22% had three CMDs. Over a decade follow-up, 8992 deaths (79.2%) were recorded. A dose-response relationship was observed, with the mortality risk increasing by 17% for each additional disease. The fully-adjusted HRs for all-cause mortality were 1.16, 1.36, and 2.03 for one, two, and three CMDs, respectively. Larger effects of single and multiple CMDs were observed in the male group (P = 0.015) and the younger senior group (P < 0.001). ConclusionsThis large-scale study found that CMDs multiply mortality risks, especially in younger seniors and males. The risk is highest when heart disease and stroke coexist, and diabetes further increases it. Public health efforts should prioritize evidence-based management and prevention of CMDs.

Outcome-guided Bayesian clustering for disease subtype discovery using high-dimensional transcriptomic data

Due to the tremendous heterogeneity of disease manifestations, many complex diseases that were once thought to be single diseases are now considered to have disease subtypes. Disease subtyping analysis, that is the identification of subgroups of patients with similar characteristics, is the first step to accomplish precision medicine. With the advancement of high-throughput technologies, omics data offers unprecedented opportunity to reveal disease subtypes. As a result, unsupervised clustering analysis has been widely used for this purpose. Though promising, the subtypes obtained from traditional quantitative approaches may not always be clinically meaningful (i.e. correlate with clinical outcomes). On the other hand, the collection of rich clinical data in modern epidemiology studies has the great potential to facilitate the disease subtyping process via omics data and to discovery clinically meaningful disease subtypes. Thus, we developed an outcome-guided Bayesian clustering (GuidedBayesianClustering) method to fully integrate the clinical data and the high-dimensional omics data. A Gaussian mixed model framework was applied to perform sample clustering; a spike-and-slab prior was utilized to perform gene selection; a mixture model prior was employed to incorporate the guidance from a clinical outcome variable; and a decision framework was adopted to infer the false discovery rate of the selected genes. We deployed conjugate priors to facilitate efficient Gibbs sampling. Our proposed full Bayesian method is capable of simultaneously (i) obtaining sample clustering (disease subtype discovery); (ii) performing feature selection (select genes related to the disease subtype); and (iii) utilizing clinical outcome variable to guide the disease subtype discovery. The superior performance of the GuidedBayesianClustering was demonstrated through simulations and applications of breast cancer expression data and Alzheimer's disease. An R package has been made publicly available on GitHub to improve the applicability of our method.

An efficient multi-disease prediction model using advanced optimization aided weighted convolutional neural network with dilated gated recurrent unit

In the medical field, prediction accuracy over multi-diseases is significant and it is helpful for improving the patient’s health. Most of the conventional machine learning techniques concentrates only on detecting single diseases. Only a few systems are developed for predicting more than one disease. The classification of multi-label data is a challenging issue. Patients have symptoms of various diseases while analyzing the medical data and hence it is necessary to implement tools for the earlier identification of problems. The patterns in the health data have been effectively identified through deep learning-based health risk prediction models. Thus, an efficient prediction model for predicting various types of diseases is implemented in this work. Initially, the required data regarding various types of diseases will be gathered from Kaggle database. The garnered healthcare data are pre-processed for quality enhancement. The pre-processing procedures include data cleaning, data transformation, and outlier detection are performed at first. The outlier detection is done using the “Density-Based Spatial Clustering of Applications with Noise (DBSCAN)” approach. The pre-processed data is then given to the Weighted Convolutional Neural Network Feature with Dilated Gated Recurrent Unit (WCNNF-DGRU) model. Here, the pre-processed data is provided to the CNN structure for feature extraction, in which the weights are optimized by means of the Enhanced Kookaburra Optimization Algorithm (EKOA). Then the features from the weighted CNN layer are provided to the Dilated GRU structure to determine the final prediction output. Experimental verification is carried out on the implemented WCDG in predicting multiple diseases by comparing it with other conventional prediction models and optimization algorithms.

Home non-invasive ventilation: An observational study of aetiology, chronic respiratory failure of multiple aetiologies, survival and treatment adherence

Home non-invasive ventilation (NIV) is used to treat patients with chronic respiratory failure (CRF). However, knowledge on the prevalence and impact of multimorbid aetiology of CRF, patterns of NIV use, and survival of these patients is limited. Our aim was to analyse the multiple aetiologies of CRF, patterns of NIV use and the outcome of those patients.We conducted a retrospective analysis of 1,281 patients treated with home-NIV between 2004 and 2014 in Turku University Hospital, Finland. The patients were divided into nine disease categories: obstructive airways disease (16 %); obesity hypoventilation syndrome (11 %); neuromuscular disease (10 %); chest wall diseases (4 %); sleep apnoea (26 %); interstitial lung diseases (3 %); malignancy (2 %); other (3 %) and acute (8 %), which refers to the patients who did not fulfil criteria of CRF. In addition, multiple aetiologies of CRF were found in 17 %. Mean adherence to home-NIV was 6.0 ± 4.4 h/d and median treatment duration 410 (120–1021) days. Adherence, treatment duration or survival did not significantly differ between patients with either single or multiple causative diseases leading to CRF. Median survival was 4.5 years (95 % CI 3.6 to 5.4). The main reasons for discontinuing NIV were death (56 %) and lack of motivation (19 %).We conclude that home-NIV is used in a variety of diseases. CRF of multiple aetiologies is prevalent and not limited to chronic obstructive lung disease and obstructive sleep apnoea overlap syndrome. However, the adherence to home-NIV or survival did not differ between patients with a single or multiple diseases causing CRF, but the survival of the home-NIV patients differed according to the underlying aetiology of CRF.

SEEI: spherical evolution with feedback mechanism for identifying epistatic interactions

BackgroundDetecting epistatic interactions (EIs) involves the exploration of associations among single nucleotide polymorphisms (SNPs) and complex diseases, which is an important task in genome-wide association studies. The EI detection problem is dependent on epistasis models and corresponding optimization methods. Although various models and methods have been proposed to detect EIs, identifying EIs efficiently and accurately is still a challenge.ResultsHere, we propose a linear mixed statistical epistasis model (LMSE) and a spherical evolution approach with a feedback mechanism (named SEEI). The LMSE model expands the existing single epistasis models such as LR-Score, K2-Score, Mutual information, and Gini index. The SEEI includes an adaptive spherical search strategy and population updating strategy, which ensures that the algorithm is not easily trapped in local optima. We analyzed the performances of 8 random disease models, 12 disease models with marginal effects, 30 disease models without marginal effects, and 10 high-order disease models. The 60 simulated disease models and a real breast cancer dataset were used to evaluate eight algorithms (SEEI, EACO, EpiACO, FDHEIW, MP-HS-DHSI, NHSA-DHSC, SNPHarvester, CSE). Three evaluation criteria (pow1, pow2, pow3), a T-test, and a Friedman test were used to compare the performances of these algorithms. The results show that the SEEI algorithm (order 1, averages ranks = 13.125) outperformed the other algorithms in detecting EIs.ConclusionsHere, we propose an LMSE model and an evolutionary computing method (SEEI) to solve the optimization problem of the LMSE model. The proposed method performed better than the other seven algorithms tested in its ability to identify EIs in genome-wide association datasets. We identified new SNP–SNP combinations in the real breast cancer dataset and verified the results. Our findings provide new insights for the diagnosis and treatment of breast cancer.Availability and implementation: https://github.com/scutdy/SSO/blob/master/SEEI.zip.

Effect of a comprehensive geriatric assessment-based individualized intervention on postoperative patients with cerebral hemorrhage: A randomized controlled study.

Comprehensive geriatric assessment (CGA) has been used in inpatient, outpatient, and emergency patients in Western countries and is an important evaluation tool in medicine. In China, the application of CGA to multiple single diseases has achieved satisfactory intervention effects. To explore the effect of CGA on postoperative quality of life (QoL), psychological state, neurological recovery, and self-efficacy in patients with cerebral hemorrhage. In this randomized controlled trial, a total of 133 postoperative patients with cerebral hemorrhage who were treated and nursed in our hospital between March 2019 and March 2021 were randomly assigned to a control group (68 patients) and an observation group (65 patients). The control group was given a general comprehensive care intervention. The observation group was evaluated using an electronic medical record-based CGA system that assessed patient prognosis and was given individualized interventions based on the CGA findings. The postoperative QoL, psychological state, neurological recovery, and self-efficacy of the two groups were compared. After the intervention, self-decompression, self-decision-making, and positive attitudes of the observation group were higher than those of the control group. However, the National Institute of Health Stroke Scale score of the observation group was lower than that of the control group, the Self-rating anxiety scale and self-rating depression scale scores of the observation group were lower than those of the control group, and the social support score was significantly higher in the observation group than in the control group. After the intervention, the mental vitality, social interaction, emotional restriction, and mental status scores of the observation group were significantly higher than those of the control group. Comprehensive evaluation of patients with cerebral hemorrhage based on a CGA, targeting the individual factors that affect the prognosis of patients, and formulating and implementing individualized nursing intervention programs based on the CGA results can effectively relieve the symptoms of cerebral hemorrhage, reduce anxiety and depression, and improve the QoL of patients with cerebral hemorrhage.

Adequacy and Acceptability of the Self-Collected Anal Pap Smear in People Living With Human Immunodeficiency Virus in the Infectious Diseases Clinic.

Background Anal Pap smears are imperative to screening for human papillomavirus (HPV)-associated anal squamous cell cancers, particularly in patients living withhuman immunodeficiency virus (HIV) given a higher incidence of disease. Self-collection of specimens may be favored by patients and more feasible to collect, increasing screening. Methods This was a single-center observational cohort study at a single academic medical center Infectious Diseases clinic from October to December 2021. We aimed to improve compliance of anal Pap collection documentation of "self-collected" versus "physician-collected" as well as verify if self-collected specimens (SCS) were adequate for interpretation equivalent to physician-collected specimens (PCS). Additionally, we aimed to evaluate patient and provider satisfaction with self-collected anal Paps. Results Sixty anal Pap smears were available for evaluation. The rate of documentation of the collection method (self-collected vs. physician-collected) was 88% during the intervention. A total of 75% of patients opted for self-collection, and 35/45 (78%) of these samples were adequate for interpretation. There was no difference in the adequacy of specimen (the ability of a cytopathologist to interpret the specimen) between the SCS and PCS. Conclusion Limited prior data suggest self-collected anal Pap specimens are adequate for interpretation only slightly less often than PCS. In our small cohort, there was no statistically significant difference between collection methods. Satisfaction with self-collection of specimens was high for both patients and providers. Additional validation in more diverse/larger clinical settings may be helpful to support this practice.

Cardiovascular mortality attributable to dietary risk factors in 54 countries in the WHO European Region from 1990 to 2019: an updated systematic analysis of the Global Burden of Disease Study.

This study aimed to estimate the association between single dietary risk factors and cardiovascular diseases (CVDs) in the WHO European Region (WHO ER) by age and sex using the data of the Global Burden of Diseases Study (GBD) from 1990 to 2019. For this purpose, 13 dietary risks and 13 forms of CVDs were included in the study, and the comparative risk assessment framework of the GBD was used to estimate the deaths attributable to them. The study included four regions, with a total of 54 countries. In 2019, 1.55 million (95% UI, 1.2-1.9 million) people in the WHO ER died from CVDs attributable to suboptimal diet. Diet-related CVD deaths (DRCDs) accounted for 16.4% of total deaths and 36.7% of CVD deaths in 2019. Between 1990 and 2019, there was a DRCDs reduction of 8.1% and the age-standardised death rate decreased. The deaths were almost equally distributed between women (777,714 deaths) and men (772,519 deaths). The distribution of death numbers between the sexes has changed only slightly over the study period. The largest percentage across the age groups were found in the group 85+ years (32.1%). Most DRCDs in the WHO ER were caused by a diet low in whole grains (326,755 deaths), followed by a diet low in legumes (232,918 deaths) and a diet high in sodium (193,713 deaths). Overall, 80.3% of deaths were due to ischaemic heart disease, which was the most common cause of death in all countries.

X chromosome rearrangement associated with premature ovarian insufficiency as diagnosed by molecular cytogenetic methods: a case report and review of the literature

BackgroundPremature ovarian insufficiency (POI) is a clinical condition characterized by ovarian dysfunction in women under 40. The etiology of most POI cases remains unidentified and is believed to be multifactorial, including factors such as autoimmunity, metabolism, infection, and genetics. POI exhibits significant genetic heterogeneity, and it can result from chromosomal abnormalities and monogenic defects.Case presentationThe study participant, a 33-year-old woman, presented with a history of irregular menstruation that commenced two years ago, progressing to prolonged menstrual episodes and eventual cessation. The participant exhibits a rearrangement of the X chromosome, characterized by heterozygosity duplication on the long arm and heterozygosity deletion on the short arm by whole exome sequencing(WES) combined with cell chromosome detection.ConclusionsThis study expands the spectrum of mutations associated with POI resulting from X chromosomal abnormalities. WES-Copy number variation analysis, in conjunction with chromosome karyotype analysis and other detection techniques, can provide a more comprehensive understanding of the genetic landscape underlying complex single or multi-system diseases.

Studies on the association of genes with language disorders in the post-genomic era

Since genetic research entered the post-genomic era, the high heritability of language disorders has been confirmed. A variety of genetic-related diseases may cause various types of language disorders in children and/or adults. This article has summarized language disorders and their underlying mechanisms by searching the Web of Science database over the last decade, and combed the genetic researches for dyslexia, frontotemporal degeneration, specific language disorder, childhood speech apraxia and other single diseases that are strongly associated with the language disorders. It also provided a discussion over the co-occurrence of multiple diseases, with an aim to revealing the genetic association and/or pathogenetic mechanism in order to provide inspiration for the prevention, diagnosis, and treatment of language disorders.

What Complexity Science Predicts About the Potential of Artificial Intelligence/Machine Learning to Improve Primary Care.

Primary care physicians are likely both excited and apprehensive at the prospects for artificial intelligence (AI) and machine learning (ML). Complexity science may provide insight into which AI/ML applications will most likely affect primary care in the future. AI/ML has successfully diagnosed some diseases from digital images, helped with administrative tasks such as writing notes in the electronic record by converting voice to text, and organized information from multiple sources within a health care system. AI/ML has less successfully recommended treatments for patients with complicated single diseases such as cancer; or improved diagnosing, patient shared decision making, and treating patients with multiple comorbidities and social determinant challenges. AI/ML has magnified disparities in health equity, and almost nothing is known of the effect of AI/ML on primary care physician-patient relationships. An intervention in Victoria, Australia showed promise where an AI/ML tool was used only as an adjunct to complex medical decision making. Putting these findings in a complex adaptive system framework, AI/ML tools will likely work when its tasks are limited in scope, have clean data that are mostly linear and deterministic, and fit well into existing workflows. AI/ML has rarely improved comprehensive care, especially in primary care settings, where data have a significant number of errors and inconsistencies. Primary care should be intimately involved in AI/ML development, and its tools carefully tested before implementation; and unlike electronic health records, not just assumed that AI/ML tools will improve primary care work life, quality, safety, and person-centered clinical decision making.

Genome-wide association study of cardiometabolic multimorbidity in the UK Biobank.

Considering the high prevalence and poor prognosis of cardiometabolic multimorbidity (CMM), identifying causal factors and actively implementing preventive measures is crucial. However, Mendelian randomization (MR), a key method for identifying the causal factors of CMM, requires knowledge of the effects of SNPs on CMM, which remain unknown. We first analyzed the genetic overlap of single cardiometabolic diseases (CMDs) using the latest genome-wide association study (GWAS) for evidential support and comparison. We observed strong positive genetic correlations and shared loci among all CMDs. Further, GWAS and post-GWAS analyses of CMM were performed in 407 949 European ancestry individuals from the UK Biobank. Eleven loci and 12 lead SNPs were identified. By comparison, we found these SNPs were a subset of SNPs associated with CMDs, including both shared and non-shared SNPs. Then, the polygenic risk score model predicted the risk of CMM (C-index = 0.62) and we identified candidate genes related to lipid metabolism and immune function. Finally, as an example, two-sample MR analysis based on the GWAS revealed potential causal effects of total cholesterol, serum urate, body mass index, and smoking on CMM. These results provide a basis for future MR research and inspire future studies on the mechanism and prevention of CMM.

The Quality of Life of Urban Omani People During the COVID-19 Pandemic in A'Seeb Wilayat: A Cross-sectional Study.

COVID-19 is an emergent disease with significant global concern, which might have a negative effect on quality of life. This study aimed to determine the impact of the COVID-19 pandemic on the quality of life of people (with or without COVID-19) attending primary health centers in A'Seeb Wilayat in Muscat, Oman. This cross-sectional study was conducted in four randomly selected primary health centers in A'Seeb Wilayat from 17 July 2021 to 31 January 2022. All Omani men and women, aged ≥ 18 years, regardless of their COVID-19 infection status, who were able to read and use online questionnaire, were included. The consecutive sampling method was applied. An online self-administered and validated Arabic version of the Short Form-12 was used to determine the impact of the COVID-19 pandemic on mental and physical quality of life. A total of 701 participants were included with a mean age of 25.3 years. Two-thirds of the participants (n = 473, 67.5%) reported being physically affected by the COVID-19 pandemic (score of ≤ 50) and more than half (n = 392, 55.9%) had been mentally affected (score of ≤ 42). Univariate analysis revealed a significant association between physical impact and educational level, low family income, chronic diseases, and alcohol consumption. Gender, young age, being single, low income, and chronic diseases were significant risk factors for mental impact. Physical and mental impacts are very common during the COVID-19 pandemic. Several risk factors were identified. Public health programs need to be implemented to mitigate the negative impact of COVID-19 on quality of life.