Sweat biomarker levels estimation using a smartphone

This study aims to effectively estimate levels of clinically relevant biomarkers in sweat in an attempt to develop a real-time application. This will be accomplished by investigating the feasibility of smartphones and artificial intelligence in extracting biomarkers compared to clinically-used gold standard techniques. Real-time sweat biomarkers assessment is challenging. It would be desirable to build an affordable, automated solution that can monitor sweat-based biomarkers in any clinical setting and, ultimately, at home.

This study aims to effectively estimate levels of clinically relevant biomarkers in sweat in an attempt to develop a real-time application. This will be accomplished by investigating the feasibility of smartphones and artificial intelligence in extracting biomarkers compared to clinically-used gold standard techniques. Real-time sweat biomarkers assessment is challenging. It would be desirable to build an affordable, automated solution that can monitor sweat-based biomarkers in any clinical setting and, ultimately, at home.

- Collect sweat samples and smartphone readings. - Identify patterns in smartphone data that are correlated with biomarker levels. - Differentiate between low vs. high biomarker levels. - Visualize results. **Tasks** - Literature review (10%) - Data analysis (loading data, extracting segments, and basic statistical analysis) (40%) - Design and implement a basic machine learning algorithm (20%) - Test and evaluation (10%) - Report and presentation (20%) **Your Profile ** - Background in Electrical Engineering, Biomedical Engineering, Computer Science, Software Engineering, Information Systems, or related fields - Prior experience with programming (MATLAB or Python) is desired - Able to work independently, pay attention to detail, and deliver results - Can visualize data using different charts such as boxplots and scatter plots - Aware of data filtering, data segmentation, and data manipulation techniques - Can develop simple classification models

- Collect sweat samples and smartphone readings.
- Identify patterns in smartphone data that are correlated with biomarker levels.
- Differentiate between low vs. high biomarker levels.
- Visualize results.

**Tasks**

- Literature review (10%)
- Data analysis (loading data, extracting segments, and basic statistical analysis) (40%)
- Design and implement a basic machine learning algorithm (20%)
- Test and evaluation (10%)
- Report and presentation (20%)

**Your Profile
**

- Background in Electrical Engineering, Biomedical Engineering, Computer Science, Software Engineering, Information Systems, or related fields
- Prior experience with programming (MATLAB or Python) is desired
- Able to work independently, pay attention to detail, and deliver results
- Can visualize data using different charts such as boxplots and scatter plots
- Aware of data filtering, data segmentation, and data manipulation techniques
- Can develop simple classification models

The research will be performed at ETH Zurich's Biomedical and Mobile Health Technology research group (www.bmht.ethz.ch) in the Balgrist Campus in Zurich, Switzerland. If you are interested and have questions regarding this project, please get in touch with Dr. Moe Elgendi (moe.elgendi@hest.ethz.ch). For research-related topics, Google Scholar: https://scholar.google.com/citations?user=-WFwzjoAAAAJ&hl=en

The research will be performed at ETH Zurich's Biomedical and Mobile Health Technology research group (www.bmht.ethz.ch) in the Balgrist Campus in Zurich, Switzerland. If you are interested and have questions regarding this project, please get in touch with Dr. Moe Elgendi (moe.elgendi@hest.ethz.ch).

For research-related topics, Google Scholar: https://scholar.google.com/citations?user=-WFwzjoAAAAJ&hl=en