Filter search by category:
Search Results:
Currently, we do not integrate with third-party health solutions, including Apple HealthKit and Google Health Connect. While it is possible that future versions may incorporate this capability, there is no firm commitment at this time and it is not expected to be available in the near future.

The AHI Developer Documents outline the technical specifics and integration code of the AHI offerings. This section of the AHI document is geared towards software developers rather than designers or marketers of a company.
AHI Cloud
AHI Cloud provides mechanisms to support AHI technologies, including such features as:
- Remote files hosting to offload some of the SDK content to help reduce the SDK install size.
- User authorization (authZ), not to be confused with user authentication, which helps control rate limits.
- Billing service for the SDK to submit billing events to for AHI to track and create invoices.
- "Scan Control" user scan credit solution, where user must first be in credit to do a scan (if enabled).
MultiScan SDK
AHI MultiScan SDK is designed to help simplify the integration work for potentially many different scan technologies into an App project. MultiScan SDK accomplishes this by abstracting the specific scanner details to all be within a single abstraction layer / interface, which can be summarized as:
- setup() Initialization aspects of the AHI solution.
- userAuthorization() Provide user access to AHI services (not to be confused with user authentication).
- initiateScan() Initiate the scan process.
MultiScan SDK is the umbrella project to which an App integrates the AHI scan technologies, such as:
BodyScan
Scan technology where a front and side capture of a user's body is used to determine body circumference and body composition measurements.

FaceScan
Scan technology where a recording of a user's face is used to determine vital signs, cardiovascular health indicators, and health risks.

Quality Assurance
Quality of the products AHI provide is of utmost importance. AHI continue to strive to make sure the products released meet our high threshold of reliability, performance, and resilience. Likewise, AHI look to help verify that scan technology is being used properly and to the greatest benefit for the client integration.
Advanced Health Intelligence (AHI) provides scalable health assessment, risk stratification and digital triage to health care providers, insurers, employers and governments.
Since 2014, AHI has been delivering health tech innovations using smartphones – starting with the first on-device body-dimensioning capability. Now, with global patents in all major markets, AHI brings forth the next frontier in digitizing health assessment with composable solutions.
AHI has assembled a leading team of medically trained professionals, AI, computer vision and data scientists to develop the most comprehensive smartphone-based risk assessment tool currently available, culminating in the following:
- Body dimension and composition assessment to identify the comorbidities of obesity, such as diabetes risk estimates.
- Blood biomarker prediction, including HbA1C, HDL, LDL, 10-year mortality risk.
- Transdermal Optical Imaging (TOI) to return vital signs and, cardiovascular disease risk estimates.
- On-device dermatological skin identification with over 588 skin conditions across 133 categories, including melanoma.
- Personalized therapeutic and non-therapeutic health coaching to improve daily health habits and build health literacy.
With a focus on impact at scale, AHI is proud to showcase a milestone in digital health transformation – a biometrically-derived triage solution – all accessible on a smartphone. With these advanced technologies, AHI can help partners escalate patients into right-care pathways for proactive health management at the population-scale.
This delivery of proprietary capabilities ushers forth an era of cost-effective health assessment for billions of smartphone users worldwide. In doing so, AHI endeavors to put the power of possibilities in the hands of communities, empowering people to take control of their journey to better health.
This is ubiquitous proactive healthcare.
Overview
FaceScan provides a reliable and easy way to estimate vital signs and predict risks associated with chronic disease. Monitor health vitals and uncover comorbidity risk of cardiovascular disease, heart attack, and stroke using your smartphone.

Transdermal Optical Imaging (TOI)
TOI paves the way to a non-intrusive and easy-to-use method for estimating vital signs, and predict risks associated with chronic disease.
Quick and contactless
Receive vital health risk estimates across cardiovascular disease, stroke, and heart attack in less than a minute through your smartphone camera.
Accurate and validated
Up o 96% accuracy and 98% repeatability. Peer-reviewed and clinically validated for accuracy and repeatability.
No additional hardware needed
Allon the smartphone. No additional hardware or wearable connection needed.
What does it capture?
Vital signs
- Heart rate
- Blood pressure estimate
- Respiration rate
Health indicators
- Cardiac workload
- Irregular heartbeats
- Heart rate variability
- Hypertension
- Hypotension
Health risk predictions
- Cardiovascular disease
- Mental stress index
- Stroke
- Heart attack
Scan capture time
<30s
Accuracy
- Avg. accuracy: 96%
- Heart rate accuracy: 99%
- Blood pressure accuracy: 95%
- Pulse pressure accuracy: 95%
- Repeatability: 98%
Integration
Quick, contactless, and scalable
FaceScan is a convenient, cost-effective, and scalable solution for estimating vital signs and predicting health risks. Using only a smartphone camera, FaceScaneliminates the need for any additional hardware, making it a quick and contactless way to gather real-time data. FaceScan’s accurate and quick capabilities, enable faster, more informed decision-making for cohort risk stratification and modeling.
Integrate seamlessly with SDKDPR
FaceScan is delivered as a mobile software development kit (SDK) to integrate with the TOI, vital predictions, and health risk results to in-house or commercial applications. FaceScanSDK is available for both Android and iOS.
Safety, security, and privacy
TOI only captures data signals and does not capture any identifying images. Once the results are received, the encrypted data sent for processing is immediately deleted from the cloud.
All AHI products are secure and compliant across some of the most stringent policies, our technology is G, HIPAA, CCPA, POPI Act, LGPD, and APP compliant making it globally available.
Research and validation
A study was conducted with the affiliated hospital of Hangzhou Normal University in China and the University of Toronto in Canada. There was no exclusion criteria, although most were healthy adults above 18 years of age. Conducted under a controlled environment, reference heartbeat information was collected with a 3-lead electrocardiograph (ECG), and video of various data points of the participant's faces were captured with one of several RGB cameras (iPhone, GoPro, and Basler).

Authorization, not Authentication
AHI make a clear distinction between what is Authentication and Authorization.
- User authentication is the process related to verifying that the person is who they say they are. For example, prior knowledge of username/email and password, or associated Social login (Facebook, Google, etc..). It is separate to user authorization.
- User authorization is the process related to providing access to services to the authenticated user.
The user base is the responsibility of the partner, therefore AHI do not offer services to manage or implement user authentication or management solutions. However, once a user is authenticated and verified by the partner App, that user must be granted permission to AHI services through an authorization process with AHI.
In summary, authentication is "proving" that the user is who they say they are, and authorization is "granting access" to the user to the services they have permission to.
AHI suggest finding more information on the topic here.
Why do we need authorization?
A unique user ID, salt and claims ensure that all billable events can be registered to a unique user and transmitted and stored securely, thereby preventing unauthorized or potentially malicious actors from undertaking unauthorized scans or intercepting unencrypted and or manipulating billing events in transit.
How do we authorize users?
AHI MultiScan SDK authorizes a user with 3 requirements.
- userID - Unique to the user that never changes; do not use email or phone numbers as these may change.
- salt - The salt, also known as "initiation vector", is used for signing the user, which enables secure encryption of details and greatly assists in preventing decryption of transported data. You can read more about using salt an best security practices here:
- https://public.cyber.mil/stigs/
- https://www.okta.com/au/identity-101/hmac/
- claims - An array of claims unique to the user and will not change (e.g. registration date). Likewise, the order must not change. Therefore, don’t include the email, as the user could change this.
..............................................................................................................................................................................................
Cloud
AHI Cloud provides mechanisms to support AHI technologies, including such features as:
- Remote files hosting to offload some of the SDK content to help reduce the SDK install size.
- User authorization (authZ), not to be confused with user authentication, which helps control rate limits.
- Billing service for the SDK to submit billing events to for AHI to track and create invoices.
AHI Cloud is built in a way that can be deployed and managed by AHI clients. Optionally, AHI can deploy and manage on the cloud service on the client's behalf.
AHI Cloud is implemented as a suite of Terraform scripts, following the "Infrastructure as Code" architecture solution. Currently, AHI Cloud is devised of AWS (Amazon Web) services, but as these services are generic and widely offered by other Cloud providers, it is entirely possible for AHI Cloud to adopt other Cloud providers in the future.
Architecture
High level architecture of the AHI Cloud solution:

Where the cloud components are:
- a. The AHI Billing service.
- b. The AHI License service.
- c. The CDN files service. SDK resources can either be geo-located (as depicted) or global (default).
- d. The license auto-renew service.
- e. The client specific billing service backbone.
- f. The client specific user authorization service.
- g. The "Scan Control" mechanism, where user's must first be in credit to do a scan.
And MultiScan client SDK interacts with AHI Cloud:
- MultiScan Client SDK will request and receive configuration details when setup() is called.
- SDK remote resources will be downloaded by the MultiScan Client SDK. This can either be from AHI global CDN, or client confined CDN (as depicted), depending on the arrangement.
- Once user has been authenticated (i.e. logged in), the user must be "announced" to AHI to grant them access, through a process of user authorization. No sensitive data is transmitted for user authorization to AHI services.
- Billing events will be sent from AHI MultiScan Client SDK to AHI Cloud so that AHI may can accurately determine invoices and usage metrics for AHI clients.
- Some scan technologies require cloud resources for processing, such as FaceScan. This can be unique depending on the particular scan being requested.
- Each client deployment will periodically be reissued with a new AHI service license. Without this license, the service will expire and cause scans to be disabled.
- Billing events are first buffered in each client deployment, then submitted to AHI global as a batch operation. This allows AHI service to be highly scalable and consist of multiple data redundancies. AHI Billing solution utilizes a ledger technology where each billing event is unique and immutable on the chain, allowing for a high degree of confidence in the security and accuracy of billing events.
- Scan credit will be recorded and signed by AHI as a security measure.
..............................................................................................................................................................................................
Data
AHI have made a commitment to refrain from the collection and storage of our partner's user data. Because of this, AHI do not persist/store user scan result data. Therefore:
ATTENTION: it is the responsibility of AHI partner to persist the scan result data.
Smoothing
Occasionally, results from scans would have outliers, values that were not consistent and seemingly wrong / not as expected. This has been defined as an issue relating to "repeatability", the expectation that doing multiple scans in a row should yield similar/same results.
The solution is to "smooth" scan results with respect to prior scan results to yield more repeatable and stable results. However, due to AHI not persisting scan result data, the App must implement and provide a persistence delegate that the AHI SDK can invoke to retrieve prior scan data for the smoothing algorithm to be able to run.
IMPORTANT: An app should use _adj_ measurement values from the scan result where possible, and fallback to using the _raw_ values. For example:
var waistCM = result["cm_adj_waist"] ?? result["cm_raw_waist"]
Persistence Delegate
MultiScan SDK provides a protocol/interface class specification that an App must implement for smoothing algorithm to invoke. This implementation, referred to as the "persistence delegate", should be registered with MultiScan SDK for scan modules to utilize.
If a persistence delegate is not provided, smoothing will not run, and only the _raw_ measurement values (see schema) will be present.
Scan Extra
Some scan modules can provide extra measurement data, not returned during the initial scan result. This can be due to many factors, such as for performance reasons or level of importance. Once such example is the generation of the 3D mesh artifact from a BodyScan result.
For scan extra to work, it is expected that the scan result is in the same format as returned, per result schema.
..............................................................................................................................................................................................
Quality Assurance
AHI have a Quality Assurance team to help verify that AHI technology is integrated appropriately. This is help our clients get the most out of the AHI scan technology and avoid common mistakes.
What We Check
The AHI quality assurance team will check off the following:
User Interface: Where pertaining to activities directly affecting the Scan operations and outputs, the implemented UI will be compared to the designs provided by the client to ensure implementation matches designs.
Functional Checks: The functionality of the individual Scans is verified for consistency. Including the app displaying expected results, and any derived results.
Usability/User Experience Checks: The flow of the app directly leading up to the creation of a scan, the act of performing a scan, and any part of the app either displaying results or displaying derived results will be checked to ensure it makes sense for users. And that the first and returning user experiences are acceptable.
What We Don't Check
The AHI quality assurance team is not responsible for the general testing of client's apps. However, if the team does discover something in your app, as a courtesy we will inform the client.
How We Check
AHI's quality assurance team will execute several test scenarios against the client's app.
Minimum Acceptance Criteria
- The implemented UI matches designs supplied.
- The UI contains no unreadable text.
- The app contains no offensive language.
- Users of the app can create a new account.
- Users of the app can perform Scan(s).
- Any in-app purchases pertaining to the ability to perform Scans are functioning.
- When a user is either unsubscribed or hasn't purchased a Scan, they are unable to perform a Scan.
- Expected results are being returned from the Scans, any derived results are being calculated correctly.
- The appropriate billing events are being sent to AHI's billing database.
What happens if a defect is discovered?
Any defects discovered in the activities directly pertaining to the operation of performing a Scan or Scans will be logged, prioritized and categorized.
Defects will be prioritized by their likelihood to occur, and the severity of their impact on a user performing a Scan or Scans.
Defects will be categorized into two categories, blockers and potential issues for consideration.
Blockers will need to be completed prior to the app being signed off by AHI, an example blocker is the user being unable to perform one of the provided Scans or the Scan not functioning correctly. Considerations are generally graphical inconsistencies in the app that the client might want to action prior to go live, or potentially in a different version of the app. An example of a consideration is a color in one of the Scan capture processes not matching the colors used throughout the app.
Sign Off
Once all blockers have been resolved, and any of the considerations determined to be completed for release have been verified, the AHI quality assurance team will sign the app off, and it will be considered go-live ready.
..............................................................................................................................................................................................
Remote Resources
Some of AHI scan technologies are able to perform processing entirely within the user's device, without the need for processing on servers. This does come with the drawback that Machine Learning models must first need to be available on the user's device and can require a larger file size footprint for the app that otherwise would not be the case for more simple offerings.
AHI's solution for this is to allow such resources to be remotely hosted, instead of needing to be packaged with the App install bundle. This is particularly important for some App distribution stores, where there is a specific size limitation. It is also possible to embed these resources where remote asset download is not feasible, such as due to network limitations or other factors.
An advantage of remote resources solution is that updates to scan models can be rolled out without the user needing to reinstall the App (or App needing an AHI SDK version update), in most cases.
FaceScan
FaceScan is a non-intrusive, transdermal optical imaging process that extracts facial blood flow information to provide a range of results such as vital signs, health indicators and health risks. This is all possible via a 30-second scan of the user's face.
Delivery: FaceScan is available for partners to integrate into their own app via a software development kit (SDK).
BodyScan
BodyScan technology is a highly efficient and accurate way to obtain a baseline of an individual’s current health by providing predictions and estimates regarding a user's body composition, dimensions and health risks. This is all possible via a 60-second scan of the user's front and side profile.
Delivery: BodyScan is available for partners to integrate into their own app via a software development kit (SDK).
MultiScan (FaceScan and BodyScan bundle)
MultiScan is a bundle package of FaceScan and BodyScan. The results obtained from FaceScan when combined with the results from BodyScan, provide a unique additional level of analysis for metabolic disease risks.
Delivery: MultiScan is available for partners to integrate into their own app via a software development kit (SDK).
*(AHI SDKs are compatible with Swift, Kotlin, React Native and Flutter Platforms)
Biometric Health Assessment
The Biometric Health Assessment is an integration of pre-existing AHI products, combined with additional methodology, that together unlocks the ability for a comprehensive assessment of physical, psychological, and mental health.
The comprehensive suite of assessments included in the Biometric Health Assessment includes standalone BodyScan, providing estimations of body composition and dimensions, standalone FaceScan, which captures health vitals and predicted risk factors, and a 4-tier Health Risk Assessment that utilizes FaceScan, BodyScan, FingerScan, and medically endorsed health surveys to provide a comprehensive health report available for consultation with a healthcare professional.
Delivery: The Biometric Health Assessment is available for partners to integrate as a Turnkey SDK or White-Label Application. AHI will also make the Health Risk Assessment available as a multi-Tenant application - requiring users to access the public-facing "AHI app" with an access code. The AHI app will be accessible on the iOS and Android marketplaces.
More
What is the difference between an SDK and a Turnkey SDK? Click Here.
What does FingerScan do? Click Here.
Overview
BodyScan offers a simple way to self-assess body composition and dimension in comfort and privacy. Discover comprehensive body composition data alongside key health risk indicators associated with obesity and diabetes.

Computer vision and machine learning
BodyScan leverages proprietary image processing, computer vision, and machine learning capabilities to provide composition, dimensioning, and health risk identification all on the smartphone.
Quick and contactless
Receive vital health and risk estimates across obesity and diabetes in less than a minute through your smartphone camera.
Accurate and Validated
Up to 97% accuracy and 98% repeatability. Peer-reviewed and clinically validated for accuracy and repeatability.
Key Stats:
- Overall Circumference Accuracy: 97.5%
- Chest Circumference Accuracy: 98%
- Hip Circumference Accuracy: 97%
- Waist Circumference Accuracy: 98%
- Thigh Circumference Accuracy: 97%
- Weight Inference (avg): 96.6%
- Repeatability: 98%
Scalability in real-time
BodyScan’s smartphone accessibility offers a convenient, cost-effective, and scalable alternative to body dimensioning and composition for health risk prediction. With no additional hardware requirements, BodyScan offers real-time data gathering, for faster, better, data-driven decision-making in real-time cohort risk stratification and modeling.
Software Development Kits (SDKs)
BodyScan is delivered as a mobile software development kit (SDK) to integrate with the composition/dimension capabilities, the 3D analyzer, and health risk estimates to in-house or commercial applications. BodyScan SDK is available for both Android and iOS.
Safety, security, and privacy
BodyScan images or videos never leave the device or are saved. BodyScan is optimized to process on-device. Once the results are returned, any encrypted data sent for processing is immediately deleted from the cloud. All AHI products are secure and compliant across some of the most stringent policies, our technology is GDPR, HIPAA, CCPA, POPI Act, LGPD, and APP compliant making it globally available.
Research and validation
Research, testing, and data were collected across participants in Thailand, Australia, Indonesia, and Taiwan to gather a cross-section of excess body fat storage differences across ethnicities. Over 7,000 individual’s data points were gathered to train the technology before 929 participated in a validation study against gold standards. These results were compared with published commercial and clinical standards of anthropometry (Human measurement) and body composition. The validation showed digital circumferences, body fat percentage, and fat-free mass have equalled, and outperformed peer-reviewed anthropometry results from 4different commercial 3D scanning systems, and body composition results from 3in-Body bioelectrical analysis (BIA) machines.

Our Technology Demo app is an app that demonstrates the scan processes and the results that each scan generates.
It is important that those involved in integrating our technology take multiple scans using the Technology Demo App provided (iOS or Android). This will give you a fundamental understanding of the environmental and human requirements needed to complete a scan.
Downloading the Technology Demo App
If you would like to get access to the Technology Demo App, please contact support@ahi.tech.
Photoplethysmography (PPG) is an optical measurement method.
Photoplethysmography (PPG) is a non-invasive medical technology that measures changes in blood volume in the microvascular bed of tissues, such as the skin, using light. It works by shining light into the skin and measuring the changes in light absorption as blood flows in and out of the vessels.
Changes in blood volume are related to cardiac activity, including heart rate and blood pressure, which are key indicators of cardiovascular health.
When light is shone into the skin, it is absorbed by the blood in the vessels and scattered by the surrounding tissue. The amount of light that is absorbed and scattered depends on the amount of blood in the vessels. When the heart beats, blood is pumped into the vessels, increasing the volume and hence the amount of light absorbed. As the blood flows back out of the vessels between beats, the volume decreases, and the amount of light absorbed decreases as well.
Machine learning is a branch of artificial intelligence (AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy. Machine learning algorithms are typically created using frameworks that accelerate solution development. Algorithms build a model based on sample data, known as training data, in order to make predictions or decisions without being explicitly programmed to do so.
Image processing is the process of transforming an image into a digital form and performing certain operations to get useful information from it. It is one of the fastest-growing technologies today, with its use in various business sectors.
Transdermal Optical Imaging (TOI) uses a digital camera to estimate vital signs by analyzing the way light travels through the skin and is re-emitted to extract information about blood flow, the blood vessels, and other structures beneath the surface of the skin. FaceScan employs TOI to surface basic health vitals.
The process begins by using ambient light, which penetrates the skin and reaches the tissue below. Some of this light is re-emitted and captured by a camera. The color of that light contains information about both the blood and the skin2. The information is separated based on the different colors of hemoglobin (in the red blood cells in the blood) and melanin (in the skin) using advanced machine learning algorithms. These algorithms process the information to create a map of the blood flow across relevant areas of the face, which is then linked together to form a video of the changes in blood flow over time. Utilizing this blood flow map, various vital signs can be estimated.
Blood pressure is the measured force that blood exerts against the walls of the arteries as it flows through them. As the heart pumps blood, the blood vessels in the face will expand and contract. TOI can measure blood pressure by analyzing how much the shape of the blood vessel changes with each expansion and contraction, estimating blood pressure.

The heart rate is the number of times the heart beats per minute. This beating of the heart causes changes in the diameter of blood vessels. By measuring the rate at which these blood vessels change diameter, the heart rate can be estimated.
TOI can also measure oxygen saturation. Oxygen saturation is the amount of oxygen in the red blood cells in the blood. The more oxygen in the blood, the more hemoglobin is saturated with oxygen. TOI can measure the concentration of hemoglobin in the blood through the unique way it absorbs certain colors light, which can give then be used to calculate an estimate of the oxygen saturation of the blood.
TOI is often used as a non-invasive alternative to arterial blood gas analysis (ABG) where invasive methods are not practical or desirable. By analyzing these changes, the data signals captured by TOI are then passed through patented and proprietary calculations and algorithms to estimate health vitals.

Further information regarding TOI research can be found here: https://bit.ly/2zbDgFk
FaceScan and BodyScan will work on iOS operating systems 12.1 or above, and Android operating systems running version 8 or above (64-bit and OpenGL 3.1 supported).
All types of cameras on the devices within the range above, will be able to conduct scans.