Prepared Data


Prepare your data as specified or use our professional services.

View details » CMS


Submit your data using this website. We process anomaly detection and send your report within minutes.

View details » CMS


Learn which factors highly associate with outcomes.

View details »


FoundationDx builds and automates innovative machine learning solutions in healthcare and underserved organizations that need to efficiently and effectively drive patient satisfaction, healthcare quality and process performance goals in complex data environments. 
We’re a small, self-funded company that’s led by its founders. Most importantly, we make services that we love, and it shows. Our subscribers are more than customers… they’re fans who share our passion for the opportunities that AI presents in their business and community. We’re growing at a quick but manageable pace, not because of big rounds of funding, but because we provide valuable early insights into process risk and performance improvement factors at modest cost.

Special programs are provided for 501(c)(3) organizations


Unsupervised learning for Anomaly Detection

FoundationDx is offering Quick Turnaround machine learning studies to evaluate the effectiveness of using automated anomaly detection for improving the efficiency and effectiveness of your data driven quality and outcome processes.
Examples that may lead to reduced healthcare costs, reduction in systemic risks, better outcomes or improved uniformity of care:
  • Identifying transactions that are potentially fraudulent.
  • Learning patterns that indicate that unususal network activity is occuring.
  • Finding abnormal clusters of patients.
  • Checking or unusual values or data patterns entered into a system


The healthcare industry has yet to seize the opportunity to optimize people, process and technology needed to drive patient experience and healthcare quality in an era of consumerism and precision medicine.

Complex data environments lead to useful information being lost because useful information, such as factors leading to outcomes of interest, are not easily identified.

Anomaly Detection in Population Health

  1. Disease Outbreak Detection:

    • Use Case: Identify unusual patterns of disease occurrence, such as spikes in the number of cases of a particular illness.
    • Example: Detecting an unexpected increase in flu cases in a specific region, which could indicate an outbreak.
  2. Fraud Detection:

    • Use Case: Identify fraudulent activities in healthcare claims and billing.
    • Example: Detecting unusual billing patterns from a healthcare provider that might indicate overbilling or billing for services not provided.
  3. Patient Health Monitoring:

    • Use Case: Monitor patient data for unusual changes that could indicate a deterioration in health.
    • Example: Detecting a sudden increase in blood glucose levels in diabetic patients, prompting early intervention.
  4. Adverse Drug Event Detection:

    • Use Case: Identify unexpected adverse reactions to medications.
    • Example: Detecting a higher-than-expected incidence of side effects from a new medication.
  5. Resource Utilization Monitoring:

    • Use Case: Monitor the usage of healthcare resources to identify unusual patterns that could indicate inefficiencies or issues.
    • Example: Identifying an unexpected increase in emergency room visits for non-emergency conditions.

Cluster Analysis in Population Health

  1. Identifying High-Risk Groups:

    • Use Case: Group populations based on risk factors to target interventions more effectively.
    • Example: Identifying clusters of individuals with high risk for cardiovascular diseases based on population patterns of age, SDOH, BMI and a constellation of clinical measures such as BP, BMI, HDL-C, ApoB, Triglycerides, HbA1c. 
  2. Disease Pattern Analysis:

    • Use Case: Understand the distribution and patterns of diseases within a population.
    • Example: Identifying geographic clusters of asthma cases that may be linked to environmental factors.
    • Example: Identifying clusters of cardiovascular risk that may be linked to modifiable factors.
  3. Healthcare Access and Utilization:

    • Use Case: Analyze patterns of healthcare access and utilization across different demographics and regions.
    • Example: Identifying areas with low healthcare utilization that might benefit from increased healthcare services or outreach programs.
  4. Behavioral Health Analysis:

    • Use Case: Group individuals based on behavioral health data to tailor public health interventions.
    • Example: Identifying clusters of individuals with similar smoking cessation success rates to develop targeted smoking cessation programs.
  5. Chronic Disease Management:

    • Use Case: Group patients with similar chronic disease profiles to optimize care plans.
    • Example: Identifying clusters of diabetes patients who respond similarly to a particular treatment regimen.
  6. Social Determinants of Health Analysis:

    • Use Case: Understand the impact of social determinants on health outcomes by clustering populations based on socioeconomic factors.
    • Example: Identifying clusters of populations with poor health outcomes linked to factors such as income, education, and housing conditions.

Combining Anomaly Detection and Cluster Analysis

  1. Early Warning Systems:

    • Use Case: Combine both techniques to create robust early warning systems for public health threats.
    • Example: Using cluster analysis to identify at-risk populations and anomaly detection to monitor real-time data for signs of emerging health threats.
  2. Personalized Medicine:

    • Use Case: Enhance personalized medicine approaches by identifying both common and outlier patterns in patient data.
    • Example: Clustering patients with similar genetic profiles and using anomaly detection to identify those who respond unusually to standard treatments.
  3. Public Health Surveillance:

    • Use Case: Improve public health surveillance by integrating cluster analysis for baseline patterns and anomaly detection for deviations.
    • Example: Regularly clustering disease incidence data and monitoring for anomalies that could indicate new or re-emerging health issues.



AI powered by


Philadelphia, PA.
Phone: (267) 358-0984


HTO Magazine