Using the Intel® AI Analytics Toolkit and Intel® oneAPI Base Toolkit, HippoScreen improved efficiency and build times of deep-learning models used in its brainwave artificial intelligence (AI) system. These improvements enabled HippoScreen to broaden its system’s applications to a wider range of psychiatric conditions and diseases.
Globally, an estimated 5% of adults suffer from depression.1 There is no one-size-fits-all diagnostic procedure for depression, and while some cases can be clinically diagnosed, most assessments are dependent on patients’ subjective self-descriptions. To overcome this problem, along with the widespread stigma surrounding depression, HippoScreen developed the Stress EEG Assessment (SEA) System, which helps doctors more accurately diagnose mental health conditions. The system includes an electroencephalogram (EEG) amplifier for data collection and signal processing, a graphic user interface for test process control, and an AI algorithm for data analysis. SEA analyzes 90-second brainwave signals and provides an objective and quantifiable evaluation index that aims to numerically represent the probability that an individual is suffering from depression.
To improve algorithm efficiency and diagnostic accuracy while reducing the delivery times of critical diagnostic results to medical personnel, HippoScreen leveraged the optimizations of Intel analysis tools and AI frameworks. Using the Intel® VTune™ Profiler analysis tool, the company reached maximum performance and minimum CPU utilization with a thread count of five. In addition, performance improved by 2 times, allowing the company to quickly identify and resolve threading oversubscription issues.2 Intel® Optimization for PyTorch and Intel® Extension for Scikit-learn, alongside HippoScreen’s proprietary algorithms, analyzed system EEG data features that culminated in a unique decision factor and resulted in 2.4 times performance improvements.3
“We at HippoScreen have been able to take advantage of the software optimizations in Intel® Extension for Scikit-learn and Intel® Optimization for PyTorch to accelerate the build times for the AI models in our customized EEG Brain Waves analysis system by 2.4x,” said Daniel Weng, chief technology officer, HippoScreen NeuroTech Corp.
More: Read the full case study “HippoScreen Improves AI Performance by 2.4x with oneAPI Tools.”
1 WHO Fact Sheet, September 2021 www.who.int/news-room/fact-sheets/detail/depression
2 Test by HippoScreen and Intel completed Dec. 1, 2022. Test configurations: Intel® Xeon® Silver 4310T Processor @ 2.30GHz, 2.30GHz, 2 Sockets, 20 Core(s) per socket, tested on HippoScreen's simple_performance_test.py workload, with analysis and optimization by Intel® VTune™ Profiler from Intel® oneAPI Base Toolkit 2022.2.0. Note: www.Intel.com/PerformanceIndex.
3 Tested by HippoScreen and Intel. Hipposcreen test validation completed on Nov. 17, 2022. Test configurations: 2 Intel® Xeon® Gold 6330 CPU @ 2.00GHz, 2 Sockets, 28 Core(s) per socket. Software used: (env_intelsklearn) root123@root123:/opt/intel/oneapi/vtune$ python, Python 3.9.12: Intel Corporation. Intel® VTune™ Profiler from Intel® oneAPI Base Toolkit 2022.2.0, From Intel® AI Analytics Toolkit 2022.2.0: Intel® Distribution for Python* 3.9.12, Intel® Optimization for PyTorch*, Intel® Extension for Scikit-learn* 2021.7.0 based on py39_intel_8746. Ubuntu 20.04 LTS. Note: www.Intel.com/PerformanceIndex
Notices & Disclaimers
Performance varies by use, configuration and other factors. Learn more on the Performance Index site.
Performance results are based on testing as of dates shown in configurations and may not reflect all publicly available updates. See backup for configuration details. No product or component can be absolutely secure.
Intel does not control or audit third-party data. You should consult other sources to evaluate accuracy.