FDA approved AI tools

 two AI-based tools related to liver disease that have received regulatory milestones by the U.S. Food and Drug Administration (FDA). Note: the list is small because few liver-AI tools have full diagnostic clearance yet.

---

1. AIM‑NASH (by PathAI)

• This is a cloud-based AI system that analyses digital images of liver biopsy histology to score features like steatosis (fat infiltration), lobular inflammation, ballooning and fibrosis according to the NASH Clinical Research Network scoring system. (U.S. Food and Drug Administration)

• The FDA qualified AIM-NASH as a Drug Development Tool (DDT) for use in clinical trials of Metabolic Dysfunction‑Associated Steatohepatitis (MASH) / formerly NASH. (U.S. Food and Drug Administration)

• Important limitations: This qualification does not indicate clearance/approval for standalone diagnostic use in routine clinical practice. A pathologist must still review and approve the results. (Fierce Biotech)

• Intended context: clinical trial endpoints and histology scoring standardisation. (pharmaphorum)

---

2. Velacur ONE (by Sonic Incytes Medical Corp.)

• This is a point-of-care ultrasound elastography device with AI-guided features, intended to assess liver stiffness (fibrosis), attenuation (fat), and a proprietary fat fraction metric (VDFF) for management of chronic liver disease (including MASLD/MASH). (DI Europe)

• The FDA granted 510(k) clearance to the Velacur ONE for features supporting liver disease assessment. (DI Europe)

• This tool is more in the imaging/point-of-care device side, rather than purely software-AI histology scoring.

---

Summary Table

Tool	Regulatory Status	Purpose/Use Case	Key Notes
AIM-NASH	FDA qualified as DDT	Histology scoring in MASH drug trials	Not cleared for general clinical diagnosis
Velacur ONE	FDA 510(k) clearance	POC ultrasound elastography for liver disease	Device + AI guidance, non-biopsy mode

---

Freed AI scribe HIPPA

 

https://www.getfreed.ai/?utm_source=google&utm_campaign=21013154313&utm_content=medical%20scribe&utm_medium=g&adgroup=158262325425&gclid=CjwKCAjwtNi0BhA1EiwAWZaANAXnB_sxKkn0qZsodpAsmiJrmfPbtrsFY7AAFfrM_41Fh_DSj1bF8xoCTWcQAvD_BwE&gad_source=1#about

data sources for AI in heathcare

https://www.nimhd.nih.gov/resources/schare/

1. Jackson Heart Study (JHS):

   • The JHS focuses on cardiovascular disease (CVD) causes among African Americans.
   • With over 5,300 African American participants in Jackson, Mississippi, it’s one of the largest initiatives in this field.
   • The dataset covers diverse domains relevant to CVD, including demographics, anthropometrics, medication usage, conditions (e.g., hypertension, diabetes), lipid profiles, biomarkers, genetics, and more.

2. ScHARe Data Ecosystem:

   • This ecosystem merges JHS data with area-level SDoH variables.
   • SDoH factors (like community resilience, socioeconomic status, and environmental conditions) play a crucial role in health outcomes.
   • By incorporating these factors, your AI/ML models can account for biases and enhance fairness.

1. **Social determinants of health data**:

   - URL: [Social Determinants of Health Data](https://healthdata.gov/dataset/social-determinants-health)

2. **Genomic data**:

   - URL: [National Center for Biotechnology Information (NCBI)](https://www.ncbi.nlm.nih.gov/)

   - URL: [Ensembl Genome Browser](https://www.ensembl.org/)

3. **Data on PTSD and burnout among clinicians**:

   - URL: [National Institute of Mental Health (NIMH) Data Archive](https://nda.nih.gov/)

4. **Referral networks data**:

   - This data may be more specific and proprietary, typically found through healthcare providers or specific research collaborations.

5. **Psychiatric patient data**:

   - URL: [National Institute of Mental Health (NIMH) Data Archive](https://nda.nih.gov/)

6. **Health records**:

   - URL: [HealthData.gov](https://www.healthdata.gov/)

   - URL: [Centers for Medicare & Medicaid Services (CMS)](https://www.cms.gov/Research-Statistics-Data-and-Systems/Research-Statistics-Data-and-Systems)

7. **Clinical trial data**:

   - URL: [ClinicalTrials.gov](https://clinicaltrials.gov/)

8. **Population health data**:

   - URL: [World Health Organization (WHO) Global Health Observatory](https://www.who.int/data/gho)

   - URL: [HealthData.gov](https://www.healthdata.gov/)

9. **Electronic health records**:

   - Typically proprietary, but some de-identified data sets can be found at:

     - URL: [MIMIC-III Clinical Database](https://mimic.physionet.org/)

10. **Survey data**:

    - URL: [CDC Behavioral Risk Factor Surveillance System (BRFSS)](https://www.cdc.gov/brfss/index.html)

    - URL: [National Health Interview Survey (NHIS)](https://www.cdc.gov/nchs/nhis/index.htm)

11. **Public health datasets**:

    - URL: [HealthData.gov](https://www.healthdata.gov/)

    - URL: [Centers for Disease Control and Prevention (CDC) Data and Statistics](https://www.cdc.gov/datastatistics/)

12. **Machine learning datasets**:

    - URL: [UCI Machine Learning Repository](https://archive.ics.uci.edu/ml/index.php)

    - URL: [Kaggle Datasets](https://www.kaggle.com/datasets)

13. **Biomedical data**:

    - URL: [Bioinformatics.org](https://www.bioinformatics.org/)

    - URL: [NIH Database of Genotypes and Phenotypes (dbGaP)](https://www.ncbi.nlm.nih.gov/gap)

14. **Hospital records**:

    - Typically proprietary, but aggregated data can be found at:

      - URL: [HealthData.gov](https://www.healthdata.gov/)

      - URL: [American Hospital Association (AHA) Data](https://www.aha.org/data)

15. **Mental health data**:

    - URL: [National Institute of Mental Health (NIMH) Data Archive](https://nda.nih.gov/)

16. **AI-generated data**:

    - This data is typically generated within research projects or specific AI applications, but some examples can be found in open repositories:

      - URL: [OpenAI](https://openai.com/)

      - URL: [Hugging Face Datasets](https://huggingface.co/datasets)