# TOPIC 425 - COMPUTER VISION-BASED ANALYSIS OF GAIT FOR THE ASSESSMENT OF GERIATRIC CANCER

> **NIH NIH N43** · AUTONOMOUS HEALTHCARE, INC. · 2021 · $399,923

## Abstract

Older patients with cancer undergo detailed clinical assessment prior to and after surgery as well as prior to and during chemotherapy. Studies show that frailty (quantified by the frailty index) and various gait
characteristics such as gait speed or tests such as timed up and go (TUG) are predictors of mortality for surgical geriatric cancer patients. In addition, the neurotoxicity associated with some of the chemotherapy drugs can have a significant impact on the mobility and balance of the older patient increasing the risk of fall-related injuries, and hence, an objective assessment of patient's balance as part of a comprehensive geriatric assessment (CGA) may be associated with cancer-related outcomes. However, given the time constraints in oncology clinics, many oncologists do not assess gait and balance of older adults with cancer. In this study, we propose to build on our earlier work to develop an easy-to-use point-of-care technology for objective gait assessment in geriatric cancer patients using computer vision. As part of the process, an access-controlled public repository of videos will be developed to cultivate development of computer vision techniques for gait assessment.

## Key facts

- **NIH application ID:** 10498246
- **Project number:** 75N91021C00052-0-9999-1
- **Recipient organization:** AUTONOMOUS HEALTHCARE, INC.
- **Principal Investigator:** BEHNOOD GHOLAMI
- **Activity code:** N43 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2021
- **Award amount:** $399,923
- **Award type:** —
- **Project period:** 2021-09-16 → 2022-06-15

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10498246

## Citation

> US National Institutes of Health, RePORTER application 10498246, TOPIC 425 - COMPUTER VISION-BASED ANALYSIS OF GAIT FOR THE ASSESSMENT OF GERIATRIC CANCER (75N91021C00052-0-9999-1). Retrieved via AI Analytics 2026-05-23 from https://api.ai-analytics.org/grant/nih/10498246. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*