AI-Based Health Monitoring System
Our technology is built on science fact, not science fiction. We offer a cutting-edge AI based health monitoring system that enables remote physiological assessments, setting a new standard in remote patient monitoring. Our system uses proprietary AI technology and the power of light to transform consumer technology devices, such as laptops or smartphones (iOS or Android), into a tool that can track advanced health analytics and provide health data from a camera.
Heart Rate
Remote heart beat capture
Respiration Rate
Remote respiration rate capture
Oxygen Saturation
Remote oxygen saturation capture
Heart Rate Variability
Remote HRV capture
Stress Index
Remote Stress measurement
Blood Pressure
Remote Blood pressure assessment
How it works
To use our AI-based health monitoring system, all you need is a smartphone or laptop. Our technology captures vital health data such as heart rate, respiration rate, oxygen saturation, heart rate variability, stress index, and blood pressure remotely. The data is collected using contactless vital signs monitoring techniques and our system is device-agnostic. Which means it can work with almost any smartphone or laptop. Our easy-to-integrate SDKs for iOS, Android, and the web make it simple for businesses to implement our technology.
Healthcare with AI
Contactless Vital Sign Monitoring
Fast & Seamless
It’s takes just 40 seconds to gain vital data insights.
Easy to Integrate SDK
We provide quick and easy SDKs for iOS, Android and the Web.
Simple Commercials
Simple SaaS based pricing model.
Built with AI
By using AI, we’re able to provide personalised recommendations.
Highly Secure
We use state of the art security measures.
Device Agnostic
Simple & flexible APIs to suit your business.
Our research and studies
We’ve conducted various clinical studies to collect data showing the accuracy of our tool. This is reflected in our peer-reviewed papers.
The Evaluation of Remote Monitoring Technology Across Participants With Different Skin Tones
Published 12th Sep 2023
The results showed that our proposed methodology could estimate heart rate with a mean absolute error of 3 bpm across all samples and subgroups. Moreover, for heart rate variability (HRV) metrics, we achieved the following results: in terms of mobility assistive equipment (MAE), the HRV-inter-beat interval (IBI) was 10 ms, the HRV-standard deviation of normal to normal heartbeats (SDNN) was 14 ms, and the HRV-root mean square of successive differences (RMSSD) between normal heartbeats was 22 ms. No significant performance decrease was found for any skin tone group, and there was no error trend toward a certain group.
Evaluation of Atrial Fibrillation Detection in Short-Term Photoplethysmography (PPG) Signals Using Artificial Intelligence
Published 12th Sep 2023
The aim of this study is to develop and compare two different techniques to detect AFIB events in short-term ECG signals, as well as verify the feasibility of using PPG signals. The primary method is based only on signal processing, while the secondary method uses AI models to predict AFIB.
Evaluation of a Camera-Based Monitoring Solution Against Regulated Medical Devices to Measure Heart Rate, Respiratory Rate, Oxygen Saturation, and Blood Pressure
Published Nov 18th 2022
Vastmindz conducted a clinical evaluation of their remote photoplethysmography (rPPG) technology to estimate vital signs such as heart rate, respiratory rate, and blood pressure. The study was conducted in a clinical environment with a wide range of subjects of different ages, heights, weights, and baseline vital signs. The study confirmed that Vastmindz's rPPG technology was able to estimate heart rate, respiratory rate, and oxygen saturation with a mean error of ±3 units and systolic and diastolic blood pressure with a mean error of ±10 mmHg. The technology was found to be acceptable for users who want to understand their general health and wellness.
Frequently Asked Questions
Vastmindz primarily offers its technology as an SDK for integration into various platforms, such as telehealth services, wellness applications, and insurance providers’ platforms. The solution is not a standalone app that can be downloaded from the App Store. However, if you are interested in utilizing Vastmindz’s technology, you can look for platforms or applications that have integrated Vastmindz’s SDK into their services. Additionally, you can reach out to the Vastmindz team for more information on how to access our solutions or explore potential collaborations.
Vastmindz SDK supports various operating systems and platforms to ensure compatibility with a wide range of applications. The main platforms supported by Vastmindz SDK include:
iOS: The SDK is compatible with Apple’s iOS operating system, allowing integration into iPhone and iPad applications.
Android: Vastmindz SDK supports Android OS, enabling integration with a broad range of Android smartphones and tablets.
Web: Vastmindz SDK also supports web-based applications, making it compatible with various browsers and web technologies.
By offering support for these major platforms, Vastmindz ensures that its innovative health monitoring solutions can be easily integrated into a wide variety of applications, reaching diverse audiences and catering to different needs.
The time it takes to integrate the Vastmindz SDK into an application can vary depending on several factors, such as the complexity of the application, the developer’s familiarity with the SDK, and the specific features being integrated. For experienced developers with a good understanding of the SDK, the integration process can be relatively quick, taking anywhere from a few hours to a couple of days. However, for those new to the SDK or working with a more complex application, the integration process might take longer, possibly ranging from a few days to a couple of weeks.
It’s essential to allocate sufficient time for integration, testing, and troubleshooting to ensure the seamless functioning of the Vastmindz technology within the application. Additionally, Vastmindz provides documentation and support to assist developers throughout the integration process, helping to minimize potential challenges and reduce the time required for successful integration.
The accuracy of Vastmindz’s solution is a critical aspect of its performance, and the company has invested significant effort into ensuring that their technology provides reliable and accurate results. Vastmindz’s algorithms are designed to extract vital signs and health parameters with a high degree of precision, comparable to traditional medical-grade devices.
The accuracy of Vastmindz’s technology is achieved through:
Extensive data collection: Vastmindz gathers large datasets containing diverse physiological data, which serve as the foundation for training and validating their algorithms.
Advanced algorithms: The company employs state-of-the-art machine learning techniques and signal processing methods to develop algorithms that can accurately extract health parameters from the collected data.
Validation: Vastmindz validates the accuracy of their technology by comparing the results obtained from their solution to those from standard medical devices, such as blood pressure cuffs, pulse oximeters, and ECG machines.
Trials and user testing: The company may conduct clinical trials and user testing to evaluate the accuracy and reliability of their technology under real-world conditions.
Continuous improvement: Vastmindz is committed to refining and updating their algorithms based on feedback, new research, and emerging trends in the industry to maintain and improve the accuracy of their solution.
To review accuracy and papers please see our technology section which highlights the papers that have been published.
The time it takes to get a reading using Vastmindz’s technology can vary depending on the specific health parameter being measured and the conditions under which the reading is taken. Generally, obtaining a reading with Vastmindz’s solution is relatively quick, often taking just a few seconds. Parameters like Heart Rate, Heart Rate Variability and Respiration are quite quick, Blood pressure and SpO2 take a few seconds longer.
No, we don’t store any data, we simply process pixelelated face information and provide the data back to the application where the SDK is used. When you use VISIX, the Microsoft Teams Health and Wellness Application, your data is stored in secure encrypted format in MS Azure servers. Vastmindz follows industry best practices and adhere to applicable data protection regulations (e.g., GDPR, HIPAA) and a strict privacy policy to ensure the confidentiality and security of their users’ personal and health-related information.
Vastmindz’s SDK is designed to run on various devices with different internet speeds, ensuring a seamless experience for users. For optimal performance, it’s essential to have a stable internet connection, but the specific bandwidth requirements should be relatively low compared to other video streaming or conferencing services.If you have concerns about bandwidth requirements or if you experience any difficulties while using Vastmindz’s technology, consider reaching out to their support team for guidance and assistance.
Vastmindz processes various types of data to extract vital health parameters from a user’s face. Primarily, the data processed by Vastmindz includes:
Video data: The technology captures real-time video data and pixelates the data from the device’s camera, focusing on the user’s face. The pixelated video data contains subtle changes in facial color and expressions, which are essential for extracting health parameters.
Photoplethysmography (PPG) signals: Vastmindz’s remote photoplethysmography (rPPG) technology processes PPG signals obtained from the video data. These signals represent the changes in blood volume in facial tissues, allowing the algorithm to analyze blood flow patterns and extract vital signs.
Physiological parameters: Vastmindz processes data related to the user’s vital signs, such as heart rate, blood pressure, respiratory rate, oxygen saturation (SpO2), heart rate variability (HRV), and mental stress levels, this data is sent back to the clients application for storage.
Demographic information: In some cases, Vastmindz may process demographic information like age, gender, or ethnicity to refine their algorithms and provide more personalized health insights.
It’s important to note that Vastmindz’s data processing typically occurs on the user’s device or within the platform it’s integrated with, ensuring data privacy and security. For more information about Vastmindz’s data handling practices, refer to our privacy policy or contact our support team.
Vastmindz is designed to handle different skin tones effectively, ensuring accurate and reliable health parameter extraction for individuals with diverse skin colors. The company achieves this by incorporating the following approaches:
Diverse training data: Vastmindz collects extensive datasets containing video recordings and physiological data from a wide variety of participants with different skin tones, ages, and ethnic backgrounds. This diverse data serves as the foundation for training and validating their algorithms, ensuring the technology performs well across different skin tones.
Advanced algorithms: Vastmindz uses advanced machine learning techniques and signal processing methods that can adapt to variations in skin tones. These algorithms account for differences in light absorption and reflection properties associated with different skin colors, enabling accurate extraction of vital signs and health parameters.
Continuous improvement: Vastmindz is committed to refining and updating its algorithms based on feedback, new research, and emerging trends in the industry. By continuously improving their technology, the company ensures that it remains inclusive and effective for individuals with diverse skin tones.
Vastmindz’s focus on inclusivity and its dedication to developing technology that works well across different skin tones make it a valuable health monitoring solution for a wide range of users.
Yes, lighting conditions can have an impact on the readings obtained using Vastmindz’s remote photoplethysmography (rPPG) technology. Since the technology relies on detecting subtle color changes in the user’s face and blood flow patterns, proper lighting is essential to capture accurate data and ensure reliable results.
Here are some guidelines to consider for optimal lighting conditions when using Vastmindz’s solution:
1. Avoid direct sunlight or overly bright light sources, as they may cause glare or washed-out video, making it difficult for the algorithm to detect color changes in the face.
2. Prefer diffused or evenly distributed lighting, which helps minimize shadows and allows for more consistent facial color representation.
3. Avoid dim or poorly lit environments, as they may result in low-quality video data and potentially impact the accuracy of the readings.
4. A Well Lit face which is clearly visible in the camera frame and without any obstructions or excessive movement.
By following these guidelines and ensuring proper lighting conditions, users can help minimize the impact of lighting on Vastmindz’s readings and obtain accurate and reliable health parameter measurements.
Our models have been trained in individuals from 18-90yrs old. However age can potentially have an impact on the readings obtained using Vastmindz’s remote photoplethysmography (rPPG) technology, as physiological changes associated with aging may influence vital signs and health parameters.
For example, older individuals may experience changes in skin elasticity, blood vessel structure, and heart function, which could affect the measurements obtained using Vastmindz’s solution. However, Vastmindz is designed to account for variations in age and other demographic factors when extracting health parameters. The company achieves this through the following approaches:
Diverse training data: Vastmindz collects extensive datasets containing video recordings and physiological data from a wide range of participants with different ages, skin tones, and ethnic backgrounds. This diverse data helps train and validate their algorithms to perform well across various age groups.
Advanced algorithms: Vastmindz uses advanced machine learning techniques and signal processing methods that can adapt to age-related physiological variations, enabling accurate extraction of vital signs and health parameters for individuals of different ages.
Continuous improvement: Vastmindz is committed to refining and updating its algorithms based on feedback, new research, and emerging trends in the industry.
By continuously improving their technology, the company ensures that it remains effective for individuals across different age groups.By considering age-related factors and ensuring that their technology adapts to physiological variations, Vastmindz aims to provide accurate and reliable health monitoring solutions for users of all ages.
Makeup has the potential to affect the accuracy of readings obtained using Vastmindz’s remote photoplethysmography (rPPG) technology. Since the technology relies on detecting subtle color changes in the user’s face and analyzing blood flow patterns, makeup that alters the natural appearance of the skin could interfere with the measurements. Heavy makeup, particularly foundation or concealer with a high coverage, might mask the color changes associated with blood flow, making it difficult for the algorithm to accurately detect vital signs and health parameters. Additionally, makeup that reflects light or causes glare could also impact the quality of the video data and the accuracy of the readings.
To obtain accurate and reliable results when using Vastmindz’s solution, it is advisable to minimize the use of makeup or opt for a light, natural makeup look that does not significantly alter the appearance of the skin. Ensuring that the face is clean and free of excessive makeup can help the technology better capture and analyze the subtle facial color changes required to extract vital health parameters.
No, our algorithms have been trained on adults with the age range of 18-90 and has been determined based on the dataset used to train and validate our algorithms, as well as other factors related to physiological variations across different age groups. Our technology is not intended to be used on any minors.
The size of the Vastmindz SDK integration can vary depending on the specific features being integrated and the platform it’s integrated with. However, in general, the size of the SDK is relatively small, allowing for easy integration into various applications and platforms.
Not yet, we are going through the regulatory process both in the USA, UK & Europe. If you have any concerns or questions about Vastmindz’s regulatory status, it’s advisable to reach out to the support team or consult with a healthcare professional or regulatory expert for guidance and assistance.
The Baevsky Stress Index, also known as the Baevsky Index, is a physiological parameter used to assess a person’s stress level. It is named after its creator, Russian physiologist Professor Oleg Baevsky. The index is derived from heart rate variability (HRV) measurements, which is the variation in time between successive heartbeats.
Heart rate variability is influenced by the autonomic nervous system, which has two branches: the sympathetic nervous system (responsible for the “fight or flight” response) and the parasympathetic nervous system (responsible for the “rest and digest” response). During stress or intense emotions, the sympathetic nervous system becomes more active, leading to changes in heart rate and HRV.
The Baevsky Stress Index quantifies the ratio between low-frequency (LF) and high-frequency (HF) components of heart rate variability. The LF component is associated with sympathetic activity, while the HF component is linked to parasympathetic activity. A higher LF/HF ratio suggests a dominance of sympathetic activity, which is often related to stress, anxiety, and other physiological responses to challenging situations.
In practical terms, the Baevsky Stress Index is calculated from an electrocardiogram (ECG) recording. It is utilized in various fields such as medicine, psychology, and sports to monitor stress levels and overall autonomic nervous system balance. However, it’s important to note that while the Baevsky Stress Index can provide insights into stress levels, it should be considered as part of a comprehensive assessment alongside other clinical and contextual information.
The formula for the Baevsky stress index is:SI = AMo × 100% / 2Mo × MxDMn where AMo is the mode of the distribution of RR intervals, Mo is the number of RR intervals in the mode, Mx is the maximum number of successive RR intervals that differ by more than 50 ms, and DMn is the difference between the minimum and maximum numbers of successive RR intervals that differ by more than 50 ms. The Baevsky stress index is used to evaluate autonomic function and to assess sympathetic tone.
The Fitzpatrick scale is a numerical classification schema for human skin color developed by American dermatologist Thomas B. Fitzpatrick in 1975. The scale is used to estimate the response of different types of skin to ultraviolet (UV) light and to determine a patient’s risk of burning or tanning when exposed to UV light. The Fitzpatrick scale remains a recognized tool for dermatological research into human skin pigmentation.The scale classifies skin into six categories based on skin color and how it responds to the sun. The following are the six categories of the Fitzpatrick scale in relation to the 36 categories of the older von Luschan scale (in parenthesis)
- Type I (scores 0–6) always burns, never tans (palest; freckles)
- Type II (scores 7–13) usually burns, tans minimally
- Type III (scores 14–20) sometimes mild burn, tans uniformly
- Type IV (scores 21–27) burns minimally, always tans well (moderate brown)
- Type V (scores 28–34) very rarely burns, tans very easily (dark brown)
- Type VI (scores 35–36) never burns (deeply pigmented dark brown to darkest brown)
The Fitzpatrick scale has some limitations, including that the original version of the scale did not contain classifications for darker skin tones. In its first version, the scale only included types I to IV and was considered “Anglo-Irish centric.” Types V and VI were added later.
