Brunel University London and University College London - Alan Turing and British Heart Foundation Biomedical Research Fellow Interdisciplinary project manager and research scientist.
Public Sector Problem Solver-Contributor–Data Study Talent at Alan Turing Institute Large-scale biological and chemical containment on diﬀerent surfaces; Identified surface deposited bacterial species and chemical hazards from their spectral signatures. pro-active team - self-motived contributor of the talent team enabled proposing innovative predictive/descriptive strategies that successfully implemented identification/detection of biological and chemical hazards. Solved significant real-world data science challenges Big Data Analysis, prototyping, Data-driven non-linear Machine Learning, Deep Learning techniques, e.g., multiclass embedding, Convolution Neural Networks (CNN), TensorFlow, Phyton, R, MATLAB programming.
National Healthcare UK (NHS Trust - PhD Placement) Pro-active enhancement achieved in the existing Data management/acquisition strategies to eﬀectively analyse COVID-19 patients administrations; reported analytics using SPSS, SQL, R, Data mining, and Machine Learning methods. Conducted eﬀective research methods, Time Series Data Analysis, planned, designed, implemented, and managed all aspects of the project lifestyle from requirements gathering data acquisition and preparation data translation hypothesis generation coding testing assessing and evaluating the statistical findings.
Educational Data Mining Research Fellow - Scientist STARS project, Brunel University London: Project Management, coordinated the activities; Eﬀectively Designed handled and pre-processed large data sets for analysis; Developed appropriate analytic algorithms and Machine Learning methods suitable for the data and met the objectives of the project on time; Inventively Designed AI engine in .NET framework; Translated the research outcomes into peer-reviewed scientiﬁc publications, press releases, stakeholder communications and for lay audiences; Discovered several inﬂuencing factors that aﬀect student performance; Designed a web-based platform powered by an AI engine to predict student dropout, which is essential to universities and the welfare of students. Along with my PhD research on healthcare and clinical data Suggested creative Educational Data mining methodology, adopted Intelligent Data Analytics - Bayesian Modelling, reasoning, causality, correlation, Database Design/Management, programmed AI engine with a highly enthused, multi-tasker precisely predicted student dropout, Discovered the influencing risk factors on student performance, provided imaginative results that were explainable for admission team; effectively communicated with technical and business experts at all levels of the organisation.
2020-now Postdoctoral Research Fellow, Computational Biological, Brunel University London, UCL, Alan Turing Institute and the British Heart Foundation Grant
2016-2020 PhD in Artificial Intelligence (AI) Computer Science, Brunel University London
2019 Taught Courses University College London (UCL): Applied Bayesian Methods, Advanced Computational Methods in Statistical Inference, Graph Theory
2009-2012 M.Sc. in Information Technology Engineering, Azad University, Tehran
2007-2009 Microsoft Certified System Engineer (MCSE) - Cisco Certified Network Manager, Technical Collage of Tehran, Technical Collage, Tehran
2002-2006 B.Sc. (Hons) in Computer Software Engineering, Azad University, Tehran
Responsible for modelling complex clinical data and healthcare challenges, discovering insights and identifying opportunities using computational, data mining, algorithmic, data structure modelling, management, and visualization techniques. Developed novel Computational Biology tools on the complex networks of diabetes biomarkers combined with other cause-and-effect networks derived from genetic information to assess drug development, visualized data effectively interpreted/negotiated the analytical/mathematical outcomes to non-expert at Brunel/UCL academics - external stakeholders Cardiovascular and GSK. Identifying the association between the genetic factors and COVID-19 test results for the assessment of the risk tolerance Data generated from UK Biobank on around 60k cases during the second wave.
Newest selected publications
Yousefi, L., Swift, S., Arzoky, M., Saachi, L., Chiovato, L. and Tucker, A. (2020) 'Opening the black box: Personalizing type 2 diabetes patients based on their latent phenotype and temporal associated complication rules'. Computational Intelligence, 0 ((in press)). ISSN: 0824-7935 Open Access Link
Yousefi, L., Al-Luhaybi, M., Sacchi, L., Chiovato, L. and Tucker, A. (Accepted) 'Identifying Latent Variables in Dynamic Bayesian Networks with Bootstrapping Applied to Type 2 Diabetes Complication Prediction'. .
Yousefi, L., Swift, S., Arzoky, M., Saachi, L., Chiovato, L. and Tucker, A. (2019) 'Opening the Black Box: Discovering and Explaining Hidden Variables in Type 2 Diabetic Patient Modelling'.2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). Madrid, Spain. 24 - 6 December. IEEE. pp. 1040 - 1044. ISSN: 2156-1125 Open Access Link
Yousefi, L., Tucker, A., Al-Luhaybi, M., Saachi, L., Bellazzi, R. and Chiovato, L. (2018) 'Predicting Disease Complications Using a Stepwise Hidden Variable Approach for Learning Dynamic Bayesian Networks'.2018 IEEE 31st International Symposium on Computer-Based Medical Systems (CBMS). Karlstad, Sweden. 23 - 21 June. IEEE. pp. 106 - 111. ISSN: 1063-7125
Yousefi, L., Saachi, L., Bellazzi, R., Chiovato, L. and Tucker, A. (2017) 'Predicting Comorbidities Using Resampling and Dynamic Bayesian Networks with Latent Variables'.2017 IEEE 30th International Symposium on Computer-Based Medical Systems. Thessaloniki, Greece. 13 - 24 June. IEEE. pp. 205 - 206. ISSN: 1063-7125 Open Access Link