Listing Thumbnail

    Menopause Evela Health 10 Dimension

     Info
    Deployed on AWS
    Compact 0.5B parameter model that converts wearable and phone activity summaries into structured 10 health Evela dimension readouts, with honest refusal for dimensions it cannot assess.

    Overview

    The Evela Health Model is a compact instruction-tuned text model that converts summaries of wearable and phone activity data into structured, per-dimension health readouts. Given a 30-day window of daily step, distance, floors, and optional heart rate signals, it produces an ordinal 1 to 5 level for each health dimension it can assess, with a short rationale naming the signals it used. For dimensions where sensor data carries no signal, the model declines to score and states why, rather than inventing one. The model is approximately 0.5 billion parameters, derived from an Apache-2.0 licensed open-weights base and LoRA fine-tuned on synthetic training pairs sampled from aggregate statistics of a production wearable corpus. No patient records are used in training, and no personal health data is embodied in the weights. At ~1 GB fp16, it serves comfortably from a single instance and is intended for high-volume summarization workloads where routing continuous wearable data through a general-purpose frontier model is prohibitively expensive. Input is a plain-text device summary; output is a plain-text structured readout, both over the standard Bedrock chat interface. Intended use is wellness and activity summarization for health and fitness applications. The model is explicitly not a medical device and must not be used for diagnosis, treatment, or clinical decision making. Scoring is grounded in Evela's eight-dimension preventive-health framework, which the model applies consistently and conservatively: it will refuse to score sleep, nutrition, prevention, sexual health, skin and hair, and social connections from sensor data alone, since these dimensions require additional structured input beyond what wearables and phone sensors capture.

    Highlights

    • Compact and cost-efficient A 0.5 billion parameter model that serves from a single instance, keeping the cost floor an order of magnitude below routing wearable data through a general-purpose frontier model.

    Details

    Delivery method

    Latest version

    Deployed on AWS

    Features and programs

    Financing for AWS Marketplace purchases

    AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
    Financing for AWS Marketplace purchases

    Pricing

    Menopause Evela Health 10 Dimension

     Info
    Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
    Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator  to estimate your infrastructure costs.

    Usage costs (2)

     Info
    Dimension
    Description
    Cost
    ml.g4dn.xlarge Inference (Batch)
    Recommended
    Model inference on the ml.g4dn.xlarge instance type, batch mode
    $1.12/host/hour
    inference.count.m.i.c Inference Pricing
    inference.count.m.i.c Inference Pricing
    $1.12/request

    Vendor refund policy

    All software charges are final and non-refundable. Billing is per instance-hour and the buyer controls when charges stop by deleting the deployed endpoint. For support, contact support@evela.health .

    How can we make this page better?

    Tell us how we can improve this page, or report an issue with this product.
    Tell us how we can improve this page, or report an issue with this product.

    Legal

    Vendor terms and conditions

    Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .

    Content disclaimer

    Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.

    Usage information

     Info

    Delivery details

    Amazon SageMaker model

    An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.

    Deploy the model on Amazon SageMaker AI using the following options:
    Deploy the model as an API endpoint for your applications. When you send data to the endpoint, SageMaker processes it and returns results by API response. The endpoint runs continuously until you delete it. You're billed for software and SageMaker infrastructure costs while the endpoint runs. AWS Marketplace models don't support Amazon SageMaker Asynchronous Inference. For more information, see Deploy models for real-time inference  .
    Deploy the model to process batches of data stored in Amazon Simple Storage Service (Amazon S3). SageMaker runs the job, processes your data, and returns results to Amazon S3. When complete, SageMaker stops the model. You're billed for software and SageMaker infrastructure costs only during the batch job. Duration depends on your model, instance type, and dataset size. AWS Marketplace models don't support Amazon SageMaker Asynchronous Inference. For more information, see Batch transform for inference with Amazon SageMaker AI  .
    Version release notes

    8 health dimensions with activity data sets.

    Additional details

    Inputs

    Summary

    The model accepts a standard chat-formatted JSON payload over the Bedrock Converse or SageMaker runtime API. Each request contains a system message carrying the Evela instruction set and a user message carrying a plain-text summary of a 30-day activity window. The user message follows a fixed text structure:

    Period: 30-day window Days with data: of 30 (

    % coverage) Data sources: <device, fitbit, oura, comma-separated> Heart rate available: <yes|no>

    Daily averages: Steps: steps Distance: meters Floors climbed: floors Steps interquartile range: - [optional]

    Heart rate: [only when available] Resting (estimated): bpm Daily average: bpm Peak: bpm

    Input MIME type
    application/json
    {"messages":[{"role":"system","content":"You are a health assessment model developed by Evela. You analyze wearable and phone activity data and produce structured health dimension assessments.\n\nYou MUST follow these rules:\n1. Only assess dimensions for which the input data provides direct signal.\n2. For exercise: use daily step counts, distance, and floors climbed to assign a level from 1 (very low) to 5 (very high).\n3. For resilience: use resting heart rate as a limited proxy, only when heart rate data is available. State clearly that this is an incomplete assessment.\n4. For all other dimensions (nutrition, sleep, prevention, sexual health, skin and hair, social connections): explicitly state that the dimension cannot be assessed from the available sensor data, and explain why.\n5. Never invent or hallucinate data that is not present in the input.\n6. This is a wellness tool, not a medical device. Do not make diagnostic claims."},{"role":"user","content":"Period: 30-day window\nDays with data: 28 of 30 (93% coverage)\nData sources: device, oura\nHeart rate available: yes\n\nDaily averages:\n Steps: 9450 steps\n Distance: 6820 meters\n Floors climbed: 12.3 floors\n Steps interquartile range: 7100 - 12400\n\nHeart rate:\n Resting (estimated): 58 bpm\n Daily average: 74 bpm\n Peak: 156 bpm"}]}
    {"messages":[{"role":"system","content":"You are a health assessment model developed by Evela. You analyze wearable and phone activity data and produce structured health dimension assessments.\n\nYou MUST follow these rules:\n1. Only assess dimensions for which the input data provides direct signal.\n2. For exercise: use daily step counts, distance, and floors climbed to assign a level from 1 (very low) to 5 (very high).\n3. For resilience: use resting heart rate as a limited proxy, only when heart rate data is available. State clearly that this is an incomplete assessment.\n4. For all other dimensions (nutrition, sleep, prevention, sexual health, skin and hair, social connections): explicitly state that the dimension cannot be assessed from the available sensor data, and explain why.\n5. Never invent or hallucinate data that is not present in the input.\n6. This is a wellness tool, not a medical device. Do not make diagnostic claims."},{"role":"user","content":"Period: 30-day window\nDays with data: 28 of 30 (93% coverage)\nData sources: device, oura\nHeart rate available: yes\n\nDaily averages:\n Steps: 9450 steps\n Distance: 6820 meters\n Floors climbed: 12.3 floors\n Steps interquartile range: 7100 - 12400\n\nHeart rate:\n Resting (estimated): 58 bpm\n Daily average: 74 bpm\n Peak: 156 bpm"}]} {"messages":[{"role":"system","content":"You are a health assessment model developed by Evela. You analyze wearable and phone activity data and produce structured health dimension assessments.\n\nYou MUST follow these rules:\n1. Only assess dimensions for which the input data provides direct signal.\n2. For exercise: use daily step counts, distance, and floors climbed to assign a level from 1 (very low) to 5 (very high).\n3. For resilience: use resting heart rate as a limited proxy, only when heart rate data is available. State clearly that this is an incomplete assessment.\n4. For all other dimensions (nutrition, sleep, prevention, sexual health, skin and hair, social connections): explicitly state that the dimension cannot be assessed from the available sensor data, and explain why.\n5. Never invent or hallucinate data that is not present in the input.\n6. This is a wellness tool, not a medical device. Do not make diagnostic claims."},{"role":"user","content":"Period: 30-day window\nDays with data: 15 of 30 (50% coverage)\nData sources: device\nHeart rate available: no\n\nDaily averages:\n Steps: 4200 steps\n Distance: 2950 meters\n Floors climbed: 3.5 floors"}]} {"messages":[{"role":"system","content":"You are a health assessment model developed by Evela. You analyze wearable and phone activity data and produce structured health dimension assessments.\n\nYou MUST follow these rules:\n1. Only assess dimensions for which the input data provides direct signal.\n2. For exercise: use daily step counts, distance, and floors climbed to assign a level from 1 (very low) to 5 (very high).\n3. For resilience: use resting heart rate as a limited proxy, only when heart rate data is available. State clearly that this is an incomplete assessment.\n4. For all other dimensions (nutrition, sleep, prevention, sexual health, skin and hair, social connections): explicitly state that the dimension cannot be assessed from the available sensor data, and explain why.\n5. Never invent or hallucinate data that is not present in the input.\n6. This is a wellness tool, not a medical device. Do not make diagnostic claims."},{"role":"user","content":"Period: 30-day window\nDays with data: 26 of 30 (87% coverage)\nData sources: device, fitbit\nHeart rate available: yes\n\nDaily averages:\n Steps: 6100 steps\n Distance: 4350 meters\n Floors climbed: 6.8 floors\n Steps interquartile range: 4200 - 8100\n\nHeart rate:\n Resting (estimated): 66 bpm\n Daily average: 82 bpm\n Peak: 138 bpm"}]} {"messages":[{"role":"system","content":"You are a health assessment model developed by Evela. You analyze wearable and phone activity data and produce structured health dimension assessments.\n\nYou MUST follow these rules:\n1. Only assess dimensions for which the input data provides direct signal.\n2. For exercise: use daily step counts, distance, and floors climbed to assign a level from 1 (very low) to 5 (very high).\n3. For resilience: use resting heart rate as a limited proxy, only when heart rate data is available. State clearly that this is an incomplete assessment.\n4. For all other dimensions (nutrition, sleep, prevention, sexual health, skin and hair, social connections): explicitly state that the dimension cannot be assessed from the available sensor data, and explain why.\n5. Never invent or hallucinate data that is not present in the input.\n6. This is a wellness tool, not a medical device. Do not make diagnostic claims."},{"role":"user","content":"Period: 30-day window\nDays with data: 22 of 30 (73% coverage)\nData sources: device\nHeart rate available: no\n\nDaily averages:\n Steps: 13200 steps\n Distance: 9850 meters\n Floors climbed: 19.4 floors\n Steps interquartile range: 10100 - 16200"}]} {"messages":[{"role":"system","content":"You are a health assessment model developed by Evela. You analyze wearable and phone activity data and produce structured health dimension assessments.\n\nYou MUST follow these rules:\n1. Only assess dimensions for which the input data provides direct signal.\n2. For exercise: use daily step counts, distance, and floors climbed to assign a level from 1 (very low) to 5 (very high).\n3. For resilience: use resting heart rate as a limited proxy, only when heart rate data is available. State clearly that this is an incomplete assessment.\n4. For all other dimensions (nutrition, sleep, prevention, sexual health, skin and hair, social connections): explicitly state that the dimension cannot be assessed from the available sensor data, and explain why.\n5. Never invent or hallucinate data that is not present in the input.\n6. This is a wellness tool, not a medical device. Do not make diagnostic claims."},{"role":"user","content":"Period: 30-day window\nDays with data: 9 of 30 (30% coverage)\nData sources: device, oura\nHeart rate available: yes\n\nDaily averages:\n Steps: 3100 steps\n Distance: 2200 meters\n Floors climbed: 2.4 floors\n\nHeart rate:\n Resting (estimated): 78 bpm\n Daily average: 92 bpm\n Peak: 148 bpm"}]}

    Support

    Vendor support

    For support send emails to support@evela.health 

    AWS infrastructure support

    AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.

    Similar products

    Customer reviews

    Ratings and reviews

     Info
    0 ratings
    5 star
    4 star
    3 star
    2 star
    1 star
    0%
    0%
    0%
    0%
    0%
    0 reviews
    No customer reviews yet
    Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.