our-people | research

Back

Qingchu Jin

Research Scientist

Dr. Qingchu Jin is a Research Scientist in Roux Institute at Northeastern University. with a focus on leveraging machine learning (ML) and deep learning (DL) technologies to address a broad spectrum of healthcare and biological challenges.

Dr. Qingchu Jin earned his Ph.D. in Biomedical Engineering at Johns Hopkins University School of Medicine. His dissertation focuses on developing statistical and machine learning models to analyze the ODE and stochastic process based mechanistic model in the field of cardiac electrophysiology. The ML methods developed can dramatically reduce the computational time and help to analyze the cellular arrhythmia events in a probabilistic manner.

Dr. Jin’s current research interest is to develop ML-based predictive analytics to enhance clinical decision-making processes such as early detection of postoperative adverse event in heart surgery patients, early risk stratification on cardiac arrest patients, etc. Additionally, Dr. Jin is interested to develop advanced AI analysis tool to provide deeper insights into the workings of ML models, ultimately aiming to improve model interpretability and robustness in real-world applications.

 

Selected publications.

[1] Jin Q, Greenstein JL, Winslow RL. Estimating the probability of early afterdepolarizations and predicting arrhythmic risk associated with long QT syndrome type 1 mutations. Biophys J. 2023 Oct 17;122(20):4042-4056. doi: 10.1016/j.bpj.2023.09.001. Epub 2023 Sep 12. PubMed PMID: 37705243; PubMed Central PMCID: PMC10598291.

[2] Kim HB, Nguyen HT, Jin Q, Tamby S, Gelaf Romer T, Sung E, Liu R, Greenstein JL, Suarez JI, Storm C, Winslow RL, Stevens RD. Computational signatures for post-cardiac arrest trajectory prediction: Importance of early physiological time series. Anaesth Crit Care Pain Med. 2022 Feb;41(1):101015. doi: 10.1016/j.accpm.2021.101015. Epub 2021 Dec 27. PubMed PMID: 34968747.

[3] Jin Q, Greenstein JL, Winslow RL. Estimating ectopic beat probability with simplified statistical models that account for experimental uncertainty. PLoS Comput Biol. 2021 Oct;17(10):e1009536. doi: 10.1371/journal.pcbi.1009536. eCollection 2021 Oct. PubMed PMID: 34665814; PubMed Central PMCID: PMC8577785.