Soha Niroumandi

Soha Niroumandi is a PhD candidate at the Medical Flow Physics Laboratory at the University of Southern California, advised by Niema Pahlevan. She also holds an MSc in Computer Science from USC. Her work lies at the intersection of computer science and medical engineering, utilizing her expertise in both fields. Her interdisciplinary research bridges mechanics, artificial intelligence, and medicine to model physiological wave propagation and develop noninvasive methods for assessing cardiovascular and cerebrovascular health.

Her current work focuses on heart–aorta–brain coupling mechanisms and the creation of AI-enhanced digital twins for real-time, personalized cardiovascular monitoring. She has been recognized as a 2025 Rising Star in Mechanical Engineering (MIT) and awarded the American Heart Association Predoctoral Fellowship for her project “A Noninvasive Smartphone-based Approach for Assessment of Dementia Risk Predictors Using Arterial Pressure Waveform.” She also received the Phi Kappa Phi Student Recognition Award, presented annually to only two USC graduate students, for her pioneering contributions to smartphone-based early detection of dementia and heart failure.

Email / CV / Google Scholar / LinkedIn / ORCID
Soha

Selected Publications

- Niroumandi S, Rinderknecht D, Bilgi C, Cole S, Ogbonnaya SA, Wolfson AM, Vaidya AS, King KS, and Pahlevan NM. (2025). “Smartphone Measurement of Aortic Arch Pulse Wave Velocity and Total Arterial Compliance: Accessible Local and Global Arterial Stiffness Assessment”. Journal of the American Heart Association, Accepted.

- Niroumandi S, Wei H, Amlani F, Gorji H, Alavi R, Chirinos JA, Pahlevan NM. Time-frequency machine learning transfer function for central pressure waveforms. European Heart Journal Open. 2025 Jul;5(4):oeaf082.

- Niroumandi S, Alavi R, Wolfson AM, Vaidya AS, Pahlevan NM. Assessment of aortic characteristic impedance and arterial compliance from non-invasive carotid pressure waveform in the Framingham heart study. The American Journal of Cardiology. 2023 Oct 1;204:195-9.

- Vaidya A, Niroumandi S, Mazandarani SP, Wolfson A, Pahlevan NM. Single Pressure Waveform Calculation of Total Arterial Compliance Predict Heart Failure Events in Framingham Heart Study. Journal of the American College of Cardiology. 2024 Apr 2;83(13):712-.

- Vaidya A, Niroumandi S, Mazandarani SP, Wolfson A, Pahlevan NM. Left Ventricle Pulsatile Workload from A Single Pressure Waveform Using Physics-Based Machine Learning Approach and Cardiovascular Disease Events in The Framingham Heart Study. Journal of the American College of Cardiology. 2024 Apr 2;83(13):2451-.

- Vaidya A, Niroumandi S, Mazandarani SP, Wolfson A, Pahlevan NM. Prognostic Value of Aortic Characteristic Impedance Calculated from A Single Carotid Waveform Using Hybrid Intrinsic Frequency-Machine Learning Approach. Journal of the American College of Cardiology. 2024 Apr 2;83(13):1988-.

- Liu J, Niroumandi S, Petrasek D, Pahlevan NM. Non-Invasive Insulin Resistance Evaluation Using Carotid Pressure Waveforms in Framingham Heart Study. Circulation. 2023 Nov 6;148: A16533- A16533

- Niroumandi S, Rinderknecht D, Bilgi C, Wolfson A, Vaidya A, King KS, Pahlevan NM. A Noninvasive Smartphone Assessment of Aortic Arch Pulse Wave Velocity and Total Arterial Compliance. Circulation. 2023 Nov 6;148:A18846-A18846.

- Niroumandi S, Wolfson A, Vaidya A, Pahlevan NM. Abstract P367: Evaluation of Left Ventricular Pulsatile Workload in Heart Failure with Preserved Ejection Fraction Using a Single Pressure Waveform Form Framingham Heart Study. Hypertension. 2023 Sep;80: AP367- AP367.

- Niroumandijahromi S, Vaidya A, Pahlevan NM. Hybrid Intrinsic Frequency Machine Learning Approach for Calculation of Total Arterial Compliance and Aortic Characteristic Impedance from A Single Carotid Waveform in Heart Failure With Preserved Ejection Fraction. Hypertension. 2022 Sep;79:A039- A039.

Selected Patents

- Alavi R, Amlani F, Gorji H, Niroumandijahromi S, Heng Wei H, and Pahlevan NM. (2024). “Sequentially-Reduced Artificial Intelligence Based Systems And Methods For Cardiovascular Transfer Functions” (US-20230138773-A1).