Chronic diseases such as heart disease, cancer, and diabetes are leading drivers of mortality worldwide, underscoring the need for improved efforts around early detection and prediction. The pathophysiology and management of chronic diseases have benefitted from emerging fields in molecular biology like genomics, transcriptomics, proteomics, glycomics, and lipidomics. The complex biomarker and mechanistic data from these "omics" studies present analytical and interpretive challenges, especially for traditional statistical methods. Machine learning (ML) techniques offer considerable promise in unlocking new pathways for data-driven chronic disease risk assessment and prognosis. This review provides a comprehensive overview of state-of-the-art applications of ML algorithms for chronic disease detection and prediction across datasets, including medical imaging, genomics, wearables, and electronic health records. Specifically, we review and synthesize key studies leveraging major ML approaches ranging from traditional techniques such as logistic regression and random forests to modern deep learning neural network architectures. We consolidate existing literature to date around ML for chronic disease prediction to synthesize major trends and trajectories that may inform both future research and clinical translation efforts in this growing field. While highlighting the critical innovations and successes emerging in this space, we identify the key challenges and limitations that remain to be addressed. Finally, we discuss pathways forward toward scalable, equitable, and clinically implementable ML solutions for transforming chronic disease screening and prevention.

Chronic diseases such as heart disease, cancer, and diabetes are leading drivers of mortality worldwide, underscoring the need for improved efforts around early detection and prediction. The pathophysiology and management of chronic diseases have benefitted from emerging fields in molecular biology like genomics, transcriptomics, proteomics, glycomics, and lipidomics. The complex biomarker and mechanistic data from these "omics" studies present analytical and interpretive challenges, especially for traditional statistical methods. Machine learning (ML) techniques offer considerable promise in unlocking new pathways for data-driven chronic disease risk assessment and prognosis. This review provides a comprehensive overview of state-of-the-art applications of ML algorithms for chronic disease detection and prediction across datasets, including medical imaging, genomics, wearables, and electronic health records. Specifically, we review and synthesize key studies leveraging major ML approaches ranging from traditional techniques such as logistic regression and random forests to modern deep learning neural network architectures. We consolidate existing literature to date around ML for chronic disease prediction to synthesize major trends and trajectories that may inform both future research and clinical translation efforts in this growing field. While highlighting the critical innovations and successes emerging in this space, we identify the key challenges and limitations that remain to be addressed. Finally, we discuss pathways forward toward scalable, equitable, and clinically implementable ML solutions for transforming chronic disease screening and prevention.

Background: and Purpose Recent studies suggested an increased incidence of cerebral venous thrombosis (CVT) during the coronavirus disease 2019 (COVID-19) pandemic. We evaluated the volume of CVT hospitalization and in-hospital mortality during the 1st year of the COVID-19 pandemic compared to the preceding year. Methods: We conducted a cross-sectional retrospective study of 171 stroke centers from 49 countries. We recorded COVID-19 admission volumes, CVT hospitalization, and CVT in-hospital mortality from January 1, 2019, to May 31, 2021. CVT diagnoses were identified by International Classification of Disease-10 (ICD-10) codes or stroke databases. We additionally sought to compare the same metrics in the first 5 months of 2021 compared to the corresponding months in 2019 and 2020 (ClinicalTrials.gov Identifier: NCT04934020). Results: There were 2,313 CVT admissions across the 1-year pre-pandemic (2019) and pandemic year (2020); no differences in CVT volume or CVT mortality were observed. During the first 5 months of 2021, there was an increase in CVT volumes compared to 2019 (27.5%; 95% confidence interval [CI], 24.2 to 32.0; P<0.0001) and 2020 (41.4%; 95% CI, 37.0 to 46.0; P<0.0001). A COVID-19 diagnosis was present in 7.6% (132/1,738) of CVT hospitalizations. CVT was present in 0.04% (103/292,080) of COVID-19 hospitalizations. During the first pandemic year, CVT mortality was higher in patients who were COVID positive compared to COVID negative patients (8/53 [15.0%] vs. 41/910 [4.5%], P=0.004). There was an increase in CVT mortality during the first 5 months of pandemic years 2020 and 2021 compared to the first 5 months of the pre-pandemic year 2019 (2019 vs. 2020: 2.26% vs. 4.74%, P=0.05; 2019 vs. 2021: 2.26% vs. 4.99%, P=0.03). In the first 5 months of 2021, there were 26 cases of vaccine-induced immune thrombotic thrombocytopenia (VITT), resulting in six deaths. Conclusions During the 1st year of the COVID-19 pandemic, CVT hospitalization volume and CVT in-hospital mortality did not change compared to the prior year. COVID-19 diagnosis was associated with higher CVT in-hospital mortality. During the first 5 months of 2021, there was an increase in CVT hospitalization volume and increase in CVT-related mortality, partially attributable to VITT.

A panel of stroke experts from the Gulf and Iran region convened a consensus meeting to discuss how the Covid-19 pandemic has affected stroke care in the region. Lower stroke admissions were observed locally, but acute stroke care has largely been maintained in their centres despite the challenges of staff and resource shortages, and public fear of the virus. This article provides a snapshot of the pandemic in the region, its impact on local stroke care, highlights the approaches and practices shared between panellists in order to protect stroke care pathways during this uncertain period, and provides a guideline that is simple and easily adaptable to different locations. The intent is to protect stroke care pathways through Covid-19 risk stratification, infection control measures, and ensuring that all stroke patients have a full Covid-19 diagnostic assessment. Opportunities for increasing the use of telemedicine to reduce physical contact between patients and healthcare workers is also discussed.

OBJECTIVETo evaluate the effectiveness of Judet's quadricepsplasty for treatment of knee contractures and to identify the effect of local infiltration of epinephrine on blood loss associated with this procedure.

METHODSA retrospective cohort study was conducted in which all cases of knee contractures managed with Judet's quadricepsplasty from 1st January 2009 to 31st December 2013 were included and were divided into two groups. The epinephrine group included patients who were infiltrated with diluted epinephrine (1:400,000) along with xylocaine, around the operative field 15 min prior to the incision time, while the control group did not receive any infiltration. Judet's outcome, blood loss, drop in hemoglobin and required blood transfusion were noted for all patients and compared between both groups.

RESULTSMost common preceding pathology identified for the development of knee contractures was periarticular fracture while ilizarov application was the most common etiology. Both groups were found similar in all preoperative characteristics except preoperative flexion contracture (p = 0.02). All functional outcome measures including Judet's outcome were similar in both groups. In contrast, duration of surgery (p = 0.01), blood loss (p = 0.02), drop in hemoglobin (p = 0.01) and number of transfusions (p = 0.03) were significantly reduced in epinephrine group.

CONCLUSIONJudet's quadricepsplasty is a useful procedure to increase the range of motion of rigid knees and local infiltration of epinephrine is effective in decreasing the amount of subsequent blood loss and transfusion requirements.

BACKGROUND: Workers in pesticide manufacturing industries are constantly exposed to pesticides. Genetic biomonitoring provides an early identification of potential cancer and genetic diseases in exposed populations. The objectives of this biomonitoring study were to assess DNA damage through comet assay in blood samples collected from industry workers and compare these results with those of classical analytical techniques used for complete blood count analysis. METHODS: Samples from controls (n = 20) and exposed workers (n = 38) from an industrial area in Multan, Pakistan, were subjected to various tests. Malathion residues in blood samples were measured by gas chromatography. RESULTS: The exposed workers who were employed in the pesticide manufacturing industry for a longer period (i.e., 13-25 years) had significantly higher DNA tail length (7.04 μm) than the controls (0.94 μm). Workers in the exposed group also had higher white blood cell and red blood cell counts, and lower levels of mean corpuscular hemoglobin (MCH), MCH concentration, and mean corpuscular volume in comparison with normal levels for these parameters. Malathion was not detected in the control group. However, in the exposed group, 72% of whole blood samples had malathion with a mean value of 0.14 mg/L (range 0.01-0.31 mg/L). CONCLUSION: We found a strong correlation (R2 = 0.91) between DNA damage in terms of tail length and malathion concentration in blood. Intensive efforts and trainings are thus required to build awareness about safety practices and to change industrial workers' attitude to prevent harmful environmental and anthropogenic effects.
Blood Cell Count ; Chromatography, Gas ; Comet Assay ; DNA ; DNA Damage ; Environmental Monitoring* ; Erythrocyte Count ; Erythrocyte Indices ; Hematologic Tests ; Leukocytes ; Malathion ; Occupations* ; Pakistan ; Pesticides* ; Tail