About Jaan Health: Chronic Health Management Platform for US

<h3><strong>Lead Data Scientist – Causal Inference &amp; Clinical Outcomes (Contract)</strong></h3> <p><strong>Location:</strong> Bolingbrook, IL: Hybrid Remote – United States<br><strong>Employment Type:</strong> Part-Time Contract (1099 Independent Contractor or W-2)<br><strong>Schedule:</strong> 10–15 hours per week initially, with the opportunity to increase hours based on project needs<br><strong>Compensation:</strong> $150 per hour<br><strong>Reports To:</strong> CFO<br><strong>Engagement Duration:</strong> Project-based, with potential for extension or expanded responsibilities</p> <h2>About Jaan Health / Phamily</h2> <p>Jaan Health is an innovative, AI-powered healthcare technology company focused on transforming proactive care management and improving patient outcomes.</p> <p>Through its proprietary Phamily platform, Jaan Health enables healthcare providers, medical groups, health systems, and Accountable Care Organizations (ACOs) to deliver scalable, high-quality care management services.</p> <p>Phamily leverages advanced technology and AI-enabled workflows to help providers manage chronic conditions, improve patient engagement, reduce avoidable healthcare utilization, and deliver measurable clinical and financial outcomes.</p> <p>Learn more at <strong>phamily.com</strong>.</p> <h2>Position Overview</h2> <p>Jaan Health is seeking a highly experienced <strong>Lead Data Scientist specializing in Causal Inference and Clinical Outcomes Research</strong> for a flexible, remote consulting engagement.</p> <p>This opportunity is ideal for a senior-level data scientist, biostatistician, health economist, or Healthcare Economics and Outcomes Research (HEOR) professional who has extensive experience evaluating the impact of healthcare interventions using real-world clinical data.</p> <p>The consultant will lead the design and execution of a rigorous clinical outcomes study evaluating the effectiveness of Jaan Health's <strong>Advanced Primary Care Management (APCM)</strong> and <strong>Chronic Care Management (CCM)</strong> programs.</p> <p>The primary objective is to establish statistically defensible evidence of program effectiveness, with particular emphasis on:</p> <ul> <li> <p><strong>Hospitalization and Readmission Rates:</strong> Determining whether patients enrolled in care management programs experience fewer hospitalizations or readmissions.</p> </li> <li> <p><strong>Post-Discharge Follow-Up:</strong> Evaluating whether enrolled patients demonstrate improved follow-up rates after hospital discharge.</p> </li> <li> <p><strong>Clinical and Financial Outcomes:</strong> Quantifying measurable improvements in patient care, healthcare utilization, and program performance.</p> </li> </ul> <p>The ideal candidate will bring deep expertise in causal inference methodologies, observational healthcare data, and advanced statistical modeling, with the ability to independently lead a high-impact analytical initiative.</p> <p>This position offers significant flexibility, beginning at approximately <strong>10–15 hours per week, with the opportunity to ramp up hours as the project progresses</strong>.</p> <h2>Key Responsibilities</h2> <h3>Clinical Outcomes Research &amp; Study Design</h3> <ul> <li> <p>Lead the development and execution of longitudinal, quasi-experimental clinical outcomes studies.</p> </li> <li> <p>Evaluate the effectiveness of APCM and CCM programs using healthcare claims and Electronic Health Record (EHR) data.</p> </li> <li> <p>Establish appropriate patient cohorts, comparison groups, outcome definitions, and analytical frameworks.</p> </li> <li> <p>Quantify differences in hospitalization rates, readmissions, and post-discharge follow-up outcomes.</p> </li> <li> <p>Develop statistically rigorous, reproducible methodologies capable of withstanding actuarial and clinical review.</p> </li> </ul> <h3>Causal Inference &amp; Advanced Statistical Modeling</h3> <ul> <li> <p>Apply advanced causal inference techniques to estimate the impact of healthcare interventions.</p> </li> <li> <p>Utilize methodologies such as propensity score matching, inverse probability weighting, difference-in-differences, and other appropriate quasi-experimental approaches.</p> </li> <li> <p>Identify and address confounding variables, selection bias, and other limitations associated with observational healthcare data.</p> </li> <li> <p>Develop high-dimensional statistical matching approaches for large, complex datasets.</p> </li> <li> <p>Conduct sensitivity analyses and validate the robustness of research findings.</p> </li> </ul> <h3>Healthcare Data Analysis &amp; Technical Execution</h3> <ul> <li> <p>Analyze complex healthcare claims, EHR, and patient utilization datasets.</p> </li> <li> <p>Develop and maintain analytical workflows using Python, R, and SQL.</p> </li> <li> <p>Work within existing data environments that may include dbt, Amazon Redshift, and Looker.