scholarly journals Diabetes and its Complication Prediction using Multi-Task Learning

2020 ◽  
Vol 9 (5) ◽  
pp. 1426-1430
Keyword(s):  
Risk Factors ◽  
Diabetes Patient ◽  
Prediction Performance ◽  
Multitask Learning ◽  
High Dimensional ◽  
Disease Prediction ◽  
Healthcare Applications ◽  
Future Health ◽  
High Dimensional Datasets

Diabetes is a long-term disease that ends up in multiple side-effects. It has now become a reticent exterminator in society because it doesn’t reveal any signs hitherto to the patients until it’s too late. It leads to many complications to other organs, such as kidney, cardiovascular, liver or blood pressure [1]. This work tends to apply a unique multitask learning [2] to synchronously map the relation between manifold complications wherever every task conforms to risks of modelling of complications [3]. It also uses feature selection to reduce the set of risk factors from high-dimensional datasets. Then using the concept of correlation, it finds the degree of relativity among various sideeffects. The proposed method is able to identify the possible future health hazards identified with the diabetes patient. This will enable us to explain medical conditions and can improves healthcare applications which would help to improve disease prediction performance.

Diabetic vitrectomy in a large type 1 diabetes patient population: long-term incidence and risk factors

2013 ◽  
Vol 92 (5) ◽  
pp. 439-443 ◽  
Author(s):  
Christoffer Ostri ◽  
Morten la Cour ◽  
Henrik Lund-Andersen
Keyword(s):  
Risk Factors ◽  
Type 1 Diabetes ◽  
Patient Population ◽  
Diabetes Patient ◽  
Large Type ◽  
Diabetic Vitrectomy

Predicting attrition in long-term residential substance use disorder treatment: A modifiable risk factors perspective.

2020 ◽  
Vol 17 (4) ◽  
pp. 472-482
Author(s):  
Danielle E. Baker ◽  
Keith A. Edmonds ◽  
Maegan L. Calvert ◽  
Sarah M. Sanders ◽  
Ana J. Bridges ◽  
...  
Keyword(s):  
Risk Factors ◽  
Substance Use ◽  
Substance Use Disorder ◽  
Modifiable Risk Factors ◽  
Substance Use Disorder Treatment ◽  
Disorder Treatment

Non-operative Risk Factors and the Implications of Sandostatin for Postoperative Pancreatic Fistula in Malignant Pancreatic Surgery

2018 ◽  
Vol 68 (12) ◽  
pp. 2875-2878
Author(s):  
Delia Rusu Andriesi ◽  
Ana Maria Trofin ◽  
Irene Alexandra Cianga Spiridon ◽  
Corina Lupascu Ursulescu ◽  
Cristian Lupascu
Keyword(s):  
Risk Factors ◽  
Pancreatic Fistula ◽  
Pancreatic Surgery ◽  
Postoperative Pancreatic Fistula ◽  
University Center ◽  
Preoperative Hemoglobin ◽  
Term Administration ◽  
Postoperative Administration

Pancreatic fistula is the most frecquent and severe postoperative complication after pancreatic surgery, with impressive implications for the quality of life and vital prognosis of the patient and for these reasons it is essential to identify risk factors. In the current study, who included 109 patient admitted to a single university center and who underwent pancreatic resection for malignant pathology, we assessed the following factors as risk factors: age, sex, preoperative hemoglobin value, preoperative total protein value, obesity and postoperative administration of sandostatin. Of the analyzed factors, it appears that only obesity and long-term administration of sandostatin influences the occurrence of pancreatic fistula.

Design and Development of a Web-based Delirium Preventive Application for Long-term Care Facilities: A Methodological Study (Preprint)

2020 ◽  
Author(s):  
Kyoung Ja Moon ◽  
Chang-Sik Son ◽  
Jong-Ha Lee ◽  
Mina Park
Keyword(s):  
Risk Factors ◽  
Long Term Care ◽  
Cloud System ◽  
Evidence Based ◽  
Methodological Study ◽  
Term Care ◽  
Web Based ◽  
Care Facilities ◽  
Delirium Prevention

BACKGROUND Long-term care facilities demonstrate low levels of knowledge and care for patients with delirium and are often not properly equipped with an electronic medical record system, thereby hindering systematic approaches to delirium monitoring. OBJECTIVE This study aims to develop a web-based delirium preventive application (app), with an integrated predictive model, for long-term care (LTC) facilities using artificial intelligence (AI). METHODS This methodological study was conducted to develop an app and link it with the Amazon cloud system. The app was developed based on an evidence-based literature review and the validity of the AI prediction model algorithm. Participants comprised 206 persons admitted to LTC facilities. The app was developed in 5 phases. First, through a review of evidence-based literature, risk factors for predicting delirium and non-pharmaceutical contents for preventive intervention were identified. Second, the app, consisting of several screens, was designed; this involved providing basic information, predicting the onset of delirium according to risk factors, assessing delirium, and intervening for prevention. Third, based on the existing data, predictive analysis was performed, and the algorithm developed through this was calculated at the site linked to the web through the Amazon cloud system and sent back to the app. Fourth, a pilot test using the developed app was conducted with 33 patients. Fifth, the app was finalized. RESULTS We developed the Web_DeliPREVENT_4LCF for patients of LTC facilities. This app provides information on delirium, inputs risk factors, predicts and informs the degree of delirium risk, and enables delirium measurement or delirium prevention interventions to be immediately implemented with a verified tool. CONCLUSIONS This web-based application is evidence-based and offers easy mobilization and care to patients with delirium in LTC facilities. Therefore, the use of this app improves the unrecognized of delirium and predicts the degree of delirium risk, thereby helping initiatives for delirium prevention and providing interventions. This would ultimately improve patient safety and quality of care. CLINICALTRIAL none

scholarly journals EGFR-mutant NSCLC presenting with stroke and massive systemic embolization as the first manifestation: case report

BMC Neurology ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Zheng Wang ◽  
Jiangyong Miao ◽  
Lina Wang ◽  
Ying Liu ◽  
Hui Ji ◽  
...  
Keyword(s):  
Risk Factors ◽  
Ischemic Stroke ◽  
Cancer Therapy ◽  
Acute Ischemic Stroke ◽  
Oral Anticoagulants ◽  
Initial Manifestation ◽  
Arterial Thromboembolism ◽  
Systemic Embolization ◽  
Effective Cancer Therapy

Abstract Background Presentation with massive systemic embolization as the initial manifestation of occult malignancy is infrequent. The standard management of cancer-related arterial thromboembolism has not yet been established. Case presentation We described a case of Trousseau’s syndrome resulting in acute ischemic stroke concomitant with multiple embolizations in the spleen and kidney during oral administration of dabigatran for pulmonary embolism preceding the diagnosis of a malignant tumor. A cancer-related hypercoagulable state was suspected because the patient was admitted to the neurology department due to acute ischemic stroke with three territory infarcts on diffusion-weighted imaging (DWI) in the absence of identifiable conventional risk factors and brain vessel narrowing. The patient was subsequently diagnosed with epidermal growth factor receptor (EGFR) mutation–positive non-small-cell lung cancer (NSCLC) (stage IV) with pleural metastasis. Administration of low-molecular-weight heparin followed by long-term dabigatran under effective cancer therapy comprising gefitinib and subsequent chemotherapy did not cause stroke relapse during the 1-year follow-up. Conclusions This case suggests that cancer-related hypercoagulability should be considered an important etiology for stroke patients who develop unexplained disseminated acute cerebral infarction without conventional stroke risk factors, especially concomitant with multiple organ embolization. Novel oral anticoagulants may be an alternative therapy for the long-term management of cancer-related arterial thromboembolism under effective cancer therapy.

scholarly journals Queensland Family Cohort: a study protocol

BMJ Open ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. e044463
Author(s):  
Danielle Borg ◽  
Kym Rae ◽  
Corrine Fiveash ◽  
Johanna Schagen ◽  
Janelle James-McAlpine ◽  
...  
Keyword(s):  
Mental Health ◽  
Family Environment ◽  
Biological Samples ◽  
Local Governments ◽  
Financial Stability ◽  
Federal State ◽  
Physical And Mental Health ◽  
Future Health ◽  
The Impact

IntroductionThe perinatal–postnatal family environment is associated with childhood outcomes including impacts on physical and mental health and educational attainment. Family longitudinal cohort studies collect in-depth data that can capture the influence of an era on family lifestyle, mental health, chronic disease, education and financial stability to enable identification of gaps in society and provide the evidence for changes in government in policy and practice.Methods and analysisThe Queensland Family Cohort (QFC) is a prospective, observational, longitudinal study that will recruit 12 500 pregnant families across the state of Queensland (QLD), Australia and intends to follow-up families and children for three decades. To identify the immediate and future health requirements of the QLD population; pregnant participants and their partners will be enrolled by 24 weeks of gestation and followed up at 24, 28 and 36 weeks of gestation, during delivery, on-ward, 6 weeks postpartum and then every 12 months where questionnaires, biological samples and physical measures will be collected from parents and children. To examine the impact of environmental exposures on families, data related to environmental pollution, household pollution and employment exposures will be linked to pregnancy and health outcomes. Where feasible, data linkage of state and federal government databases will be used to follow the participants long term. Biological samples will be stored long term for future discoveries of biomarkers of health and disease.Ethics and disseminationEthical approval has been obtained from the Mater Research Ethics (HREC/16/MHS/113). Findings will be reported to (1) QFC participating families; (2) funding bodies, institutes and hospitals supporting the QFC; (3) federal, state and local governments to inform policy; (4) presented at local, national and international conferences and (5) disseminated by peer-review publications.

Sign in / Sign up

Export Citation Format

Share Document