A5051924946- ECG Monitoring and Analysis
- Machine Learning in Healthcare
- Prostate Cancer Treatment and Research
- Medical Imaging Techniques and Applications
- Breast Cancer Treatment Studies
- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Transplantation: Methods and Outcomes
- Cardiac Imaging and Diagnostics
- Acute Myocardial Infarction Research
- Bone health and treatments
- Prostate Cancer Diagnosis and Treatment
- Neural Networks and Applications
- Renal Transplantation Outcomes and Treatments
- Artificial Intelligence in Healthcare
- Cardiomyopathy and Myosin Studies
- Cardiac electrophysiology and arrhythmias
- Advanced X-ray and CT Imaging
- Explainable Artificial Intelligence (XAI)
- Organ Transplantation Techniques and Outcomes
- Statistical Methods and Inference
- Protease and Inhibitor Mechanisms
- Monoclonal and Polyclonal Antibodies Research
- Global Cancer Incidence and Screening
- Metaheuristic Optimization Algorithms Research
Halmstad University
2019-2025
Lund University
2015-2024
Intelligent Systems Research (United States)
2023-2024
Computational Physics (United States)
2013-2022
Institute of Education of the Republic of Azerbaijan
2022
University of Gothenburg
2010-2012
Sahlgrenska University Hospital
2004-2012
CREATe Centre
2011
Nordic Institute for Theoretical Physics
2009-2010
Assistance Publique – Hôpitaux de Paris
2008
There is an urgent need for biomarkers in plasma to identify Alzheimer's disease (AD). It has previously been shown that a signature of 18 proteins can AD during pre-dementia and dementia stages (Ray et al, Nature Medicine, 2007). We quantified the same from 174 controls, 142 patients with AD, 88 other dementias. Only three these (EGF, PDGF-BB MIP-1δ) differed significantly between controls AD. The could classify low diagnostic precision (area under ROC curve was 63%). Moreover, they not...
Background Non-alcoholic fatty liver disease (NAFLD) is highly prevalent and causes serious health complications in individuals with without type 2 diabetes (T2D). Early diagnosis of NAFLD important, as this can help prevent irreversible damage to the and, ultimately, hepatocellular carcinomas. We sought expand etiological understanding develop a diagnostic tool for using machine learning. Methods findings utilized baseline data from IMI DIRECT, multicenter prospective cohort study 3,029...
The purpose of this study was to develop a computer-assisted diagnosis (CAD) system based on image-processing techniques and artificial neural networks for the interpretation bone scans performed determine presence or absence metastases. <b>Methods:</b> A training group 810 consecutive patients who had undergone scintigraphy due suspected metastatic disease were included in study. Whole-body images, anterior posterior views, obtained after an injection <sup>99m</sup>Tc-methylene...
Heart transplantation is life saving for patients with end-stage heart disease. However, a number of factors influence how well recipients and donor organs tolerate this procedure. The main objective study was to develop validate flexible risk model prediction survival after using the largest transplant registry in world.We developed flexible, non-linear artificial neural networks (IHTSA) classification regression tree comprehensively evaluate impact recipient-donor variables on over time....
d We present a method for inferring gene regulatory networks (GRNs) from single cells Lineage cross-antagonism is key property of GRNs early lineage commitment Ddit3 node in erythroid programming A Ddit3-Gata2 axis antagonizes myeloid and enables programs
The primary objective of this study is to compare the accuracy two risk models, International Heart Transplantation Survival Algorithm (IHTSA), developed using deep learning technique, and Index for Mortality Prediction After Cardiac (IMPACT), predict survival after heart transplantation. Data from adult transplanted patients between January 1997 December 2011 were collected UNOS registry. included 27,860 transplantations, corresponding 27,705 patients. cohorts divided into before 2009...
A strategy for finding approximate solutions to discrete optimization problems with inequality constraints using mean field neural networks is presented. The x ≤ 0 are encoded by x⊖(x) terms in the energy function. careful treatment of approximation self-coupling parts crucial, and results an essentially parameter-free algorithm. This methodology extensively tested on knapsack problem size up 10 3 items. algorithm scales like NM N items M constraints. Comparisons made exact branch bound when...
The risk of distant recurrence in breast cancer patients is difficult to assess with current clinical and histopathological parameters, no validated serum biomarkers currently exist. Using a recently developed recombinant antibody microarray platform containing 135 antibodies against 65 mainly immunoregulatory proteins, we screened 240 sera from 64 primary cancer. This unique longitudinal sample material was collected each patient between 0 36 mo after the operation. velocity for protein...
Gonadotropin-releasing hormone (GnRH) acts directly on the ovary to induce ovulation in hypophysectomized proestrous rats. Because plasminogen activators (PAs) are implicated gonadotropin-induced ovulation, we have studied effect of GnRH ovarian PA synthesis. induced tissue-type (tPA) secretion by cultured rat granulosa cells, but inhibited urokinase-type PA. These effects were blocked co-treatment with a antagonist, suggesting that stereospecific receptors involved. Follicle-stimulating...
Molecular mechanisms employed by individual multipotent cells at the point of lineage commitment remain largely uncharacterized. Current paradigms span from instructive to noise-driven mechanisms. Of considerable interest is also whether involves a limited set genes or entire transcriptional program, and what extent gene expression configures multiple trajectories into commitment. Importantly, transient nature transition confounds experimental capture committing cells. We develop...
The objective of this study was to explore the prognostic value Bone Scan Index (BSI) obtained at time diagnosis in a group high-risk prostate cancer patients receiving primary hormonal therapy.This retrospective based on 130 consecutive high risk, clinical stage (T2c/T3/T4), Gleason score (8 10) and prostate-specific antigen (PSA) (> 20 ng/mL), who had undergone whole-body bone scans < 3 months after received therapy. BSI calculated using an automated method. Cox proportional-hazards...