Health Ahead Comparative Effectiveness Study (HACE)

Health Ahead: Sequential Comparative-Effectiveness Studies Toward Automated, Universally Deployable Preventive Health Screening

The Health Ahead Comparative Effectiveness Study is a pragmatic, parallel-arm interventional platform that systematically compares successive changes to preventive health screening on the path toward a fully automated screening system deployable in any environment, including the most isolated and resource-limited communities. Each change is isolated as a single variable against current practice, and every comparison is evaluated with a common set of engagement, behavior-change, experience, cost, and longitudinal outcome measures, so results accumulate on a consistent yardstick across the life of the platform.

The first comparison evaluates AI-assisted versus human-only interpretation ("reads") of screening data. Subsequent pre-planned comparisons, added by protocol amendment, evaluate static versus interactive personalized report delivery; mobile community versus fixed laboratory screening; and a hybrid medical-droid-plus-human delivery model versus human-only screening.

Study Overview

• Status: Recruiting
• Conditions: Cardiovascular Diseases; Cognitive Dysfunction; Metabolic Syndrome; Frailty; Aging; Telemedicine; Patient Participation; Health Behavior; Activities of Daily Living; Health Services Accessibility; Health Related Quality of Life; Health Equity; Preventive Health Services; Rural Health; Medically Underserved Area
• Intervention / Treatment: Behavioral: Human-Only Screening Interpretation; Behavioral: AI-Assisted Screening Interpretation (AI Reads)

Detailed Description

Access to comprehensive preventive health screening is profoundly unequal. Geographic, economic, and systemic barriers leave medically underserved populations, including rural, frontier, and isolated communities, with little or no access to screening deep enough to identify disease before symptoms occur. The long-term aim is a fully automated preventive screening system deployable anywhere people live. Reaching it safely requires testing each change to the screening model one variable at a time, against current practice.

The study is therefore a standing sequential comparative-effectiveness platform. Each comparison isolates a single change, holds every other element of the screening experience constant, and is evaluated against the same core outcome set. As one comparison concludes, the next opens by protocol amendment.

Two principles govern every comparison. First, allocation is randomized wherever participant-level random assignment is feasible, non-randomized only where it is not, as in comparisons of screening location. Second, every comparison is registered with non-inferiority as the primary hypothesis: each step toward a more automated, more broadly deployable model must show it does not degrade outcomes relative to current practice by more than a pre-specified margin. Superiority is a pre-specified secondary in a hierarchical, gatekeeping sequence. No numeric margins are fixed at registration; each is set per comparison by a rule anchored to a validated minimal clinically important difference where one exists, and locked before that comparison's data are analyzed. Each non-inferiority comparison reports intention-to-treat and per-protocol analyses, and a conclusion requires agreement between them.

The active comparison and the planned comparison sequence are set out below. Comparison 1 (active): AI-assisted versus human-only interpretation ("reads") of screening data. Arms complete identical screening for their visit type and differ only in whether the acquired data receive an AI-generated read. A physician of record reviews and signs every released interpretation in all arms. The comparison runs in two strata by screening complexity, randomized 1:1 within each. The primary contrast combines the strata; each stratum is also analyzed separately. The primary hypothesis is that AI-assisted interpretation is non-inferior to human-only interpretation on health activation.

Planned comparison - static versus interactive personalized health report delivery. Both arms complete identical screening and differ only in the report received. The interactive report lets participants adjust their own behaviors and diagnostic inputs in real time and see the projected effect on composite scores, estimated biological age, and aging trajectory. Randomized.

Planned comparison - mobile community screening versus fixed laboratory screening in medically underserved populations. Because assignment follows the site at which a participant presents, this comparison is not randomized at the participant level.

Planned comparison - a hybrid delivery model combining medical droids, one registered nurse, and remote physician oversight, versus human-only screening.

Future comparison - fully automated screening performed by medical droids with remote physician review, versus the hybrid model.

Future comparison - reduced-capture screening versus the full screening battery, testing how far the acquired input can be reduced while preserving what the screening delivers.

This study is one of four that compound into one system. The 100-Year Human Aging Study (NCT07563777) supplies the clinical data and validates what it means for health, disease, disability, and death. The Human Observatory Study (NCT07646782) does the same with sociodemographic and environmental data, and receives each model's geographic residuals. The Longevity Metrics AI/ML Development Study (NCT pending approval) builds the models that make automation, prediction, and broad utilization possible. This study moves the screening toward increasing automation and mobility while maintaining quality.

• Study Type: Interventional
• Enrollment (Estimated): 1000000
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: William Brandenburg, MD; Phone Number: 13035010016; Email: info@longevitymetrics.org

Study Locations

• United States
  • Colorado
    • Boulder, Colorado, United States, 80301
      • Recruiting
      • Longevity Metrics
      • Contact: William Brandenburg, MD; Phone Number: 3035010016; Email: info@longevitymetrics.org

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• Age 18 years or older
• Willing and able to provide written informed consent, or enrollment with consent of a legally authorized representative
• Willing to participate in longitudinal follow-up.

Exclusion Criteria:

- Age under 18 years.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Health Services Research
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Active Comparator: Human-Only Screening Interpretation; Participants receive comprehensive preventive health screening under the standard of care for the comparison in progress. In the active comparison, all screening data, images, tracings, and laboratory results are interpreted by the physician of record and qualified clinical staff under physician supervision, without AI decision support.	Behavioral: Human-Only Screening Interpretation; All acquired screening data, images, tracings, and laboratory results are interpreted by the physician of record and qualified clinical staff under physician supervision, by standard practice and without AI decision support. This is the current standard of care and the active comparator.
Experimental: AI-Assisted Screening Interpretation (AI Reads); Participants receive identical screening with one element modified: the single variable under test in the comparison in progress. In the active comparison, models produce AI-generated reads of the acquired data, presented to the physician of record as a clinical aid. The physician reviews each read, records a structured judgment before sign-off, and produces and signs the released interpretation. The comparison runs in two screening-complexity strata, with a single general model in the simple stratum and a general model plus at least three domain-specific models in the comprehensive stratum.	Behavioral: AI-Assisted Screening Interpretation (AI Reads); An AI-generated read of the acquired screening battery is produced and presented to the physician of record as a clinical aid. All models used are third-party models, executed unmodified on Longevity Metrics clinical infrastructure. The physician reviews each read, records a structured judgment before sign-off, and then produces and signs the released interpretation, which may adopt, modify, or reject any read.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Health Awareness and Action (Non-Inferiority)	Change from baseline in health awareness and action score, measured by the Health Awareness and Action 6-item questionnaire (HAA-6) or its successor instrument, specified and locked in the comparison's Statistical Analysis Plan before first allocation. Change is compared between the experimental arm and the active comparator arm. Non-inferiority is assessed with a one-sided test at the 6-12-month timepoint against a margin pre-specified in the comparison's Statistical Analysis Plan and locked before any analysis of comparison data.	Baseline (intake, completed at home before the screening visit); 1-2 weeks after screening, at report delivery; 6-12-month follow-up; then periodically from enrollment until death, up to 100 years.

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Unintended Consequences and Psychological Impact	Participant-reported emotional response to receiving personalized risk estimates (estimated biological age, predicted age at death, and predicted causes of death), compared between arms, rated on three bipolar 1-10 scales: anxious or overwhelmed (1) to empowered (10); distressed (1) to motivated (10); and confused (1) to informed (10).	Baseline, 6-12-month follow-up, then periodically from enrollment until death, up to 100 years.
Completion of Provider-Recommended Health Behavior Changes	On the personalized screening report, the provider specifies the three highest-priority recommended changes, spanning lifestyle, environmental, and medical domains. At each follow-up, participants report for each of the three whether they completed or adhered to it. The primary metric is the number of provider-recommended changes completed (0-3), compared between arms.	Baseline, 6-12-month follow-up, then periodically from enrollment until death, up to 100 years.
Primary Barrier to Non-Completion of Recommended Changes	For each provider-recommended change a participant reports not completing, the participant identifies the single main barrier using a fixed-choice item adapted to that recommendation ("What is the main thing getting in the way of [recommendation]?"). Response options: Time; Money or cost; Access to care or services; Stress or mental health; Sleep; Addiction or substance use; Physical limitations, pain, or symptoms; Knowledge (not sure what to do); Motivation; Habits or routines; Family or relationship demands; Other (free text). The metric is the distribution of selected barriers across non-completed recommendations, compared between arms.	Baseline, 6-12-month follow-up, then periodically from enrollment until death, up to 100 years.
Participant Satisfaction - Longevity Metrics Post-Screening Satisfaction Questionnaire (6-item), Composite Score	Participant satisfaction measured with the Longevity Metrics Post-Screening Satisfaction Questionnaire, a 6-item self-report instrument administered after the participant receives their screening report. Each item is rated on a 1-10 linear scale; items cover perceived value of the report, satisfaction with the tester, the screening, and the data/report/recommendations, and likelihood to recommend Longevity Metrics. A composite score is calculated as the sum of all items (minimum 6, maximum 60); higher scores indicate greater satisfaction. Compared between groups.	1 to 2 weeks after health screening (at report delivery)
Complexity-Adjusted Cost-Effectiveness	Complexity-adjusted cost, computed as total direct costs ÷ (screening complexity weight × participants completing screening), where the complexity weight reflects the scope and intensity of the screening battery delivered (e.g., single-modality DEXA versus the full multi-system report-card battery), so that a simpler, lower-cost screen is not credited as artificially more efficient than a broader battery that delivers more. An incremental cost-effectiveness ratio compares complexity-adjusted cost against improvement in the primary endpoint.	6-12-month follow-up, then periodically from enrollment until death, up to 100 years.
Participant Follow-up and Retention	Retention and follow-up completion across the lifelong cohort, compared between arms, assessed by: study retention (proportion of enrolled participants remaining active versus withdrawn or lost to follow-up); follow-up questionnaire completion (proportion completing each scheduled follow-up survey); and in-person re-screening return (proportion returning to the laboratory or mobile site for scheduled repeat testing). Initial follow-up occurs at 6-12 months; follow-up continues for life thereafter, enabling longitudinal ascertainment of chronic disease, adverse health outcomes, and mortality. Differential retention between arms is monitored as a potential source of bias in non-inferiority comparisons.	6-12-month follow-up, then periodically from enrollment until death, up to 100 years.
Longitudinal Health Outcomes and Mortality	All-cause mortality, cause-specific mortality, incident serious health events, and incident chronic disease development, compared between arms as follow-up accumulates through the 100-Year Human Aging Study protocol.	Baseline, 6-12-month follow-up, then periodically from enrollment until death, up to 100 years.
Operational Throughput and Screening Completion	Operational equivalence across arms, assessed by: capacity utilization (time slots filled ÷ total available time slots); no-show rate (proportion of scheduled appointments not attended); and screening completion status (proportion of screenings fully completed, partially completed, or unable to be performed, with reason for non-completion recorded as patient declined, equipment failure, operator failure, or other [free text]). Compared between arms.	6-12-month follow-up, then periodically from enrollment until death, up to 100 years.
Data Quality and Test Validity	Objective data quality and test validity across arms, reported as the proportion of assessments meeting pre-specified quality thresholds, across three categories: (a) CPET test validity - proportion of cardiopulmonary exercise tests with peak respiratory exchange ratio (RER) at or above a pre-specified threshold (>~1.10); (b) instrument calibration - proportion of screening sessions in which the CPET metabolic cart, spirometer (PFT), and DEXA passed calibration/QC within manufacturer-specified thresholds; and (c) effort adequacy - proportion of effort-dependent tests for which provider-rated effort met or exceeded a pre-specified adequacy cutoff (e.g., ≥7 of 10). Compared between arms.	Baseline, 6-12-month follow-up, then periodically from enrollment until death, up to 100 years.
Screening-Related Adverse Events	Participant-reported adverse events attributed to the screening, captured after each screening visit by a single mark-all-that-apply item: "Did you experience any of the following as a result of your health screening?" Options: musculoskeletal injury; other injury; a fall; dizziness, lightheadedness, or fainting; chest pain or palpitations; shortness of breath; excessive muscle soreness or fatigue; bruising, bleeding, or pain at the blood draw site; pain or discomfort during a test; distress; anxiety; confusion; feeling overwhelmed; trouble sleeping; none; other adverse health event (free text). The metric is the proportion of participants reporting each event category, compared between arms; events are also captured in the trial's standard adverse-event reporting.	Baseline, 6-12-month follow-up, then periodically from enrollment until death, up to 100 years.
Change in peak oxygen uptake (VO2peak) measured by cardiopulmonary exercise testing	VO2peak is the highest rate of oxygen consumption achieved during a symptom-limited cardiopulmonary exercise test (CPET), expressed in mL/kg/min. Higher values indicate greater cardiorespiratory fitness. Change is calculated as the difference between successive screenings (follow-up minus baseline) and compared between arms. Unit of Measure: mL/kg/min	Baseline, 6-12 months, then periodically through study completion (up to 100 years)
Change in heart rate recovery at 2 minutes post-exercise	Heart rate recovery (HRR) at 2 minutes is the difference between peak heart rate at the end of cardiopulmonary exercise testing and the heart rate measured 2 minutes into recovery, expressed in beats per minute (bpm). A larger drop indicates better autonomic function. Change is the difference between successive screenings, compared between arms. Unit of Measure: bpm	Baseline, 6-12 months, then periodically through study completion (up to 100 years)
Change in maximal handgrip strength by hand dynamometer	Maximal handgrip strength measured with a hand dynamometer, recorded as the single highest value obtained across 2-3 trials in either hand, expressed in kilograms (kg). Higher values indicate greater strength. Change is the difference between successive screenings, compared between arms. Unit of Measure: kg	Baseline, 6-12 months, then periodically through study completion (up to 100 years)
Change in Sit-to-Rise score	The Sit-to-Rise Test assesses lower-body strength, mobility, flexibility, and balance by requiring the participant to sit on and rise from the floor with minimal support. Scored 0-5 for sitting and 0-5 for rising, summed to a 0-10 composite; higher scores indicate better musculoskeletal function. Change is the difference between successive screenings, compared between arms. Unit of Measure: Units on a scale (0-10)	Baseline, 6-12 months, then periodically through study completion (up to 100 years)
Change in appendicular lean mass index (ALMI) by DEXA	Appendicular lean mass index is the sum of lean soft-tissue mass in the arms and legs measured by dual-energy X-ray absorptiometry (DXA), divided by height squared, expressed in kg/m². Higher values indicate greater skeletal muscle mass. Change is the difference between successive screenings, compared between arms. Unit of Measure: kg/m²	Baseline, 6-12 months, then periodically through study completion (up to 100 years)
Change in visceral adipose tissue (VAT) mass by DEXA	Visceral adipose tissue mass estimated by dual-energy X-ray absorptiometry (DXA), expressed in grams (g). Lower values indicate less visceral fat. Change is the difference between successive screenings, compared between arms. Unit of Measure: grams	Baseline, 6-12 months, then periodically through study completion (up to 100 years)
Change in fasting serum triglycerides	Fasting serum triglyceride concentration measured by a CLIA-certified reference laboratory, expressed in mg/dL. Lower values indicate a more favorable lipid profile. Change is the difference between successive screenings, compared between arms. Unit of Measure: mg/dL	Baseline, 6-12 months, then periodically through study completion (up to 100 years)
Change in 2-hour post-load glucose during oral glucose tolerance test, measured by continuous glucose monitor	Glucose measured 120 minutes after a 75 g oral glucose load (OGTT) using a continuous glucose monitor (CGM), expressed in mg/dL. Lower values indicate better post-load glucose disposal. Change is calculated as the difference between successive screenings, compared between arms. Unit of Measure: mg/dL	Baseline, 6-12 months, then periodically through study completion (up to 100 years)
Change in resting mean arterial pressure (MAP)	Resting mean arterial pressure derived from resting brachial systolic (SBP) and diastolic (DBP) blood pressure using MAP = (2 × DBP + SBP) / 3, expressed in mmHg; a single value is reported per assessment. Change is the difference between successive screenings, compared between arms. Unit of Measure: mmHg	Baseline, 6-12 months, then periodically through study completion (up to 100 years)
Change in number of patient-reported symptoms (Longevity Metrics symptom checklist)	Symptom burden via the Longevity Metrics 24-item self-report checklist; participants mark all that apply: (1) chest pain or pressure; (2) shortness of breath on minimal/moderate exertion; (3) dizziness or fainting; (4) fever or night sweats; (5) fatigue; (6) erectile dysfunction; (7) persistent cough; (8) coughing up blood; (9) difficulty swallowing; (10) unexplained weight loss; (11) excessive thirst/urination; (12) abdominal pain; (13) nausea or vomiting; (14) diarrhea; (15) constipation; (16) blood in stool or urine; (17) headaches; (18) weakness or numbness; (19) vision changes; (20) memory problems; (21) new lump or swelling; (22) non-healing wound or sore; (23) skin rash; (24) a fall from loss of balance, dizziness, or weakness in the last 6 months (not during sports/recreation). Each item and "Other" score 1; "None of the above" scores 0. Change is the difference between successive screenings, compared between arms. Unit of measure: number of symptoms marked	Baseline, 6-12 months, then periodically through study completion (up to 100 years)
Health Awareness and Action (Superiority)	Conditional on non-inferiority being established in the primary analysis, superiority of the experimental arm over the active comparator arm on change from baseline in health activation score is tested within a pre-specified hierarchical (gatekeeping) sequence, on the same contrasts as the primary analysis, and reported whenever the data support a superiority claim.	Baseline (intake, completed at home before the screening visit); 1-2 weeks after screening, at report delivery; 6-12-month follow-up; then periodically from enrollment until death, up to 100 years.
Report Efficacy and Utilization	Participant-reported efficacy and utilization of the personalized report, compared between arms, using two items each rated 1-10: (a) "This report helped me understand my health better"; (b) "This report helped me understand what to do to improve my health". Items (a) and (b) are compared across arms.	Baseline, 6-12-month follow-up, then periodically from enrollment until death, up to 100 years.
Population Characterization by Arm	Baseline characterization by arm across sociodemographic, geographic, environmental, health history and healthcare utilization domains. Functions as a randomization-balance check where assignment is randomized, and as a substantive between-population comparison in any comparison in which arms draw from different settings.	Baseline, 6-12-month follow-up, then periodically from enrollment until death, up to 100 years.
Interpretation Agreement (Physician Rating of AI Read)	Description: Distribution of the physician's 1-10 rating of agreement with each AI-generated read, recorded before sign-off. Reported overall and by model, including the proportion in the 8-10 agreement band. Scale runs from 1, complete disagreement, to 10, complete agreement. Arm B only	At report generation for each participant, across the index screening and any repeat screening within the Comparison 1 intervention period.
Interpretation Divergence	Proportion of AI-generated reads rated at or below a pre-specified agreement threshold, reported by model together with the accompanying distribution of safety ratings. Arm B only.	At report generation for each participant, across the index screening and any repeat screening within the Comparison 1 intervention period.
Safety Profile of AI Reads	Distribution of the physician's 1-10 rating of the potential for patient harm had the AI read been acted upon as written, recorded before sign-off. Reported overall and by model, including the proportion in the 1-3 band and the disposition of every read so rated. Scale runs from 1, high potential for serious harm, to 10, no potential for patient harm. Arm B only.	At report generation for each participant, across the index screening and any repeat screening within the Comparison 1 intervention period.
Override Rate	The proportion of reads the physician changed. At sign-off the physician records whether the released interpretation differs substantively from each read; override rate is the share where it does, reported overall and by model, and reported against the safety ratings for the same reads. The agreement rating captures what the physician thought of a read; this measure captures what the physician did with it. Arm B only.	At report generation for each participant, across the index screening and any repeat screening within the Comparison 1 intervention period.
Complexity of the Released Interpretation	Finding counts, referral recommendations, and total word count appearing in the released interpretation (impression and 3 recommendations), compared between arms.	At report generation for each participant, across the index screening and any repeat screening within the Comparison 1 intervention period.
Physician Review Burden	Time to physician sign-off per read and per participant, compared between arms.	At report generation for each participant, across the index screening and any repeat screening within the Comparison 1 intervention period.

Collaborators and Investigators

• Sponsor: William Brandenburg, MD
• Investigators: Principal Investigator: William Brandenburg, MD, Longevity Metrics

Publications and helpful links

Helpful Links

• Longevity Metrics Research

Study record dates

Study Major Dates

• Study Start (Actual): June 9, 2026
• Primary Completion (Estimated): December 31, 2099
• Study Completion (Estimated): December 31, 2099

Study Registration Dates

• First Submitted: June 9, 2026
• First Submitted That Met QC Criteria: June 20, 2026
• First Posted (Actual): June 25, 2026

Study Record Updates

• Last Update Posted (Actual): September 8, 2026
• Last Update Submitted That Met QC Criteria: September 2, 2026
• Last Verified: September 1, 2026

More Information

Terms related to this study

• Keywords: Clinical Decision Support; Health Services Research; Body Composition; Artificial Intelligence; Longevity; Health Equity; Chronic Disease; Comparative Effectiveness; Machine Learning; Cost-Effectiveness; Patient Engagement; Preventive Medicine; DEXA; Rural Health; Healthspan; Cardiopulmonary Exercise Testing; Biological Age; Medically Underserved; Life Expectancy; Sequential Platform Trial; Interactive Health Report; Health Activation; Mobile Health Screening; Health Ahead Bus; Mobile Clinic; Automated Screening; Medical Droids; Diagnostic Interpretation
• Additional Relevant MeSH Terms: Mental Disorders; Pathologic Processes; Disease Attributes; Metabolic Diseases; Neurocognitive Disorders; Glucose Metabolism Disorders; Cognition Disorders; Insulin Resistance; Hyperinsulinism; Pathological Conditions, Signs and Symptoms; Behavior; Nutritional and Metabolic Diseases; Treatment Adherence and Compliance; Patient Acceptance of Health Care; Frailty; Cognitive Dysfunction; Cardiovascular Diseases; Metabolic Syndrome; Chronic Disease; Health Behavior; Patient Participation
• Other Study ID Numbers: HealthAheadCE; IORG0012336; IRB00014601 (Other Identifier: OHRP)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Individual participant data are not shared. The complete participant record includes facial and voice recordings, genomic data, and neighborhood-resolution geography, and cannot be de-identified; it is never released. Identifiable data are accessed only by approved researchers working within Longevity Metrics secure facilities under data use agreements, with no data removed. Specific derived, aggregate, and statistical outputs are de-identified to HIPAA Safe Harbor standards and may be published, shared with collaborators, or contributed to open-access research databases. Models, risk estimates, and analytic findings derived from the research data may be provided to external organizations or used commercially; no participant record and no dataset containing participant data is transferred.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No