Publications

Publications & preprints.

Current-field work in causal inference, biological data science, and scientific machine learning — with the numerical-methods foundations that underpin it.

Works in Progress

Active manuscripts in preparation; drafts not yet publicly available.

2026

Preoperative Focality Scoring for Predicting Seizure Freedom After Temporal-Lobe Epilepsy Surgery

H. Latifizadeh et al.

Statistical & data-science lead · Duke Comprehensive Epilepsy Center & Department of Neurology (Epilepsy Surgery Outcomes Project)

Diagnostic-performance and causal-explanatory modeling of an SEEG-derived focality score for epilepsy-surgery outcomes; subgroup analysis and principled structural-missingness handling across resective surgery, laser ablation (LITT), and neuromodulation cohorts. Manuscript completion August 2026.

In prep

2026

Transferable Cross-Species Cell-Type Mapping via Relaxed-Marginal Probabilistic Optimal Transport in Flow Cytometry

H. Latifizadeh et al.

Lead author & project lead · Duke–Weill Cornell Medicine (Congenital CMV Research Team)

A methods manuscript on reproducible cross-species alignment of flow-cytometry measurements via probabilistic optimal transport with relaxed marginals, supporting standardized biomedical data integration, transferable out-of-sample inference, and robust analytical pipelines applicable to multi-site clinical-data harmonization.

In prep

2026

A Multi-Scale Scientific Machine Learning Framework for In Silico Modeling of Maternal Immunity and Vaccine Efficacy in Congenital CMV Transmission

H. Latifizadeh et al.

Lead author & project lead · Duke–Weill Cornell Medicine (Congenital CMV Research Team)

A translational modeling manuscript integrating mechanistic simulation with scientific machine learning to study maternal immunity, vaccine efficacy, and congenital CMV transmission — supporting computational vaccinology and maternal–fetal health analytics.

In prep

Peer-Reviewed Publications & Preprints

2025

BaMANI: Bayesian Multi-Algorithm Causal Network Inference using Machine Learning and Deep Learning Frameworks ↗

H. Latifizadeh, A. C. Pirkey, A. Gould, D. J. Klinke II

arXiv preprint, 2025

First author

Open release of an ensemble pipeline for relational mechanistic discovery from heterogeneous biomedical signals: constraint- and score-based structure learning under Bayesian model averaging, conditional-independence testing with multiple-hypothesis correction, and bootstrapping for edge stability — supporting prediction, calibration, and uncertainty quantification in biomolecular and clinical-relation inference.

Preprint arXiv ↗Code ↗

2022

Data-driven learning how oncogenic gene expression locally alters heterocellular networks ↗

D. J. Klinke II, A. Fernandez, W. Deng, A. Razazan, H. Latifizadeh, A. C. Pirkey

Nature Communications, 13(1): 1986, 2022

Co-author · method development and computational analysis

Tissue-scale interaction modeling in tumor microenvironments, characterizing how Cell Communication Network 4 (CCN4/WISP1) reorganizes local regulatory context linked to anti-tumor immunity in breast cancer and melanoma — linking molecular signaling to immune-microenvironment phenotyping and computational immunology.

Press coverage (2022): AAAS / Science-affiliated press, TechiLive, and WVU Research & Graduate Education.

Nature Comms. DOI ↗

Methodological Foundations

Nonlinear dynamical systems and numerical analysis (2009–2020) — analytical and semi-analytical solvers for stiff, fractional, and memory-bearing differential equations. This body of work established the solver design, basis representations, and convergence analysis that underpin my current scientific-machine-learning methods. Several appear in AMS / MathSciNet. Full citations on the CV.

The full publication record — including all methodological-foundations papers — is available here:

↓ Full CV (PDF) ↗ Google Scholar