Abhinav Sharma
H -
B-
Education
2018– Karolinska Institutet and Stockholm University, Joint Masters Programme .
Ongoing Health Informatics- Indian Institute of Technology - Kanpur, B.Tech. (Biological Sciences and Bioengineering).
CPI 6.1/10.0
Publications
2018 "Extending PubMed Searches to ClinicalTrials.gov Through a Machine Learning Approach for
Systematic Reviews", Corrado Lanera, Clara Minto, Abhinav Sharma, Dario Gregori, Paola
Berchialla, Ileana Baldi, The Journal of Clinical Epidemiology.
Papers in Review
2018 "Bayesian Machine Learning Techniques for Clinical Outcome Classification", Bottigliengo
Daniele, Lanera Corrado, Baldi Ileana, Sharma Abhinav; Gregori Dario, Berchialla Paola ,
AMIA 2018 Annual Symposium.
2018 "Screening PubMed abstracts: is class imbalance always a challenge to machine learning?",
Corrado Lanera , Paola Berchialla, Abhinav Sharma, Clara Minto, Dario Gregori, Ileana Baldi ,
AMIA 2018 Annual Symposium.
Projects
Dec’18 – Development of Prognostic Risk Score in the SCREAM cohort, Karolinska Institutet
Ongoing (Sweden), Prof. Mattias Rantaleinen.
Public Health Informatics
{ Application of conventional survival analysis (e.g. Cox PH model) to derive prognostic risk score in the
Stockholm Creatinine Measurements (SCREAM) cohort
{ Classification of the patients that will progress in their disease within a certain time frame using
machine learning techniques.
Jan’18 – Genomics Data Analysis, Indian Institute of Technology Kanpur (India), Prof. Bushra
April’18 Ateeq.
Transcriptomics Data Analysis
{ Classification of different patients into SPINK1 positive and SPINK1 knockdown in accordance with the
transcriptome data available
{ All the computations are being done using the R programming language
May’17 – HUTCH, Unit of Biostatistics, Epidemiology and Public Health - University of Padova
July’17 (Italy), Prof. Ileana Baldi.
HUTCH (Highly Unbalanced Text Classification in Health Care) project is the application of text mining
to support researchers dealing with screening process of a systematic review and the identification of
relevant papers through the online databases like PubMed.
{ Comparison of various Machine Learning Techniques with different data handling approaches to deal
with the unbalanced data retrieved from the online database PubMed.
{ All the computations involved in this project were done on the R programming language and also
learned to contribute in the development of R package.
{ The second part of this study is a further extension where the best methodology from this study is
used to solve the difficulties in replication of query in not organised databases (such as clinical trials
registries).
{ Contributed in the abstract of this project for the national SISMEC congress 2017 in Gargnano, September
13th-17th, 2017 and preparation of the slides and the poster for the jsm17 in Baltimore, July 29th August 3rd, 2017
Aug’16 – Cognitive Behavioural Therapy, Indian Institute of Technology Kanpur (India), Prof.
Nov’16 Nitin Gupta.
I worked on a web application based on a Cognitive Behavior Therapy designed to be used by people
who would like to prevent mental health problems or manage problems which are troubling but not
incapacitating
{ Learned web framework Django(written in Python) and modification of E-mail template using HTML
and CSS.
{ Incorporation of conversations on Psychoeducation on Depression which included problems faced by
users like Sleeping very less, Avoiding Mastery activities, Ruminating in bed etc.
May’16 – Data Mining and Knowledge Discovery, Indian Institute of Technology Kanpur (India),
July’16 Instructor. Faiz Hamid.
Course Project
{ Applied Data pre-processing techniques and Statistical analysis in R to reshape the raw form of data to
knowledge.
{ Developed a model for predicting customer churn for a wireless telecommunication company and used
insights from the model to develop an incentive plan for enticing churners to remain with the company.
Relevant Courses
Bioinformatics/Computational Biology
Functional Genomics
Computer applications in Healthcare and Biomedicine
Health informatics - needs, objectives and limitations
Supplementary course in Computer and Systems
Sciences
User Needs, Requirements Engineering and Evaluation
(Ongoing)
Data Mining & Knowledge Discovery
Statistical Methods in Business Analytics
Probability and Statistics
Application of Markov chains in Computing
Computational Methods in Engineering
Fundamentals of Computing
Achievements
2017 Selected for Summer Innovation Award for the project HUTCH
2014 IIT JEE rank: top 0.8% of about 1.5 mil. participants
2012 Secured perfect 10.0/ 10.0 in class Tenth CBSE board
Technical Skills
OS { Mac, Windows, Linux
Software/IDE { Rstudio, Eclipse, Pymol, Django
Programming { R, Python, Java, C, LATEX
Extracurricular
2017 - 18 Captain of Badminton team IIT-Kanpur
2016 Won Gold Medal in InterIIT’16
2017 Won Gold in Rube Goldberg in Takneek’15 (Inter-Hall technical competition)