This prospective multicenter observational study will evaluate whether an electronic nose that analyzes patterns in exhaled breath can be developed as a noninvasive tool for early risk prescreening across several disease areas. The study will enroll up to 20,000 adults from hospitals and health examination centers. It will first establish a standardized breath-sampling and quality-control procedure and assess repeatability across breathing maneuvers, devices, centers, and time. It will then develop and independently evaluate risk prescreening models for prespecified disease modules, including lung cancer/clinically significant pulmonary nodules, chronic respiratory diseases, and metabolic/endocrine diseases, with additional exploratory modules involving liver, kidney, cardiovascular, and systemic inflammatory/infectious/immune conditions. The electronic-nose results are for research only and will not be reported to participants or clinicians or used to change routine screening, diagnosis, or treatment. Disease reference status will be determined from examinations, laboratory tests, imaging, pathology, pulmonary function testing, specialist assessments, or follow-up that are already performed as part of routine care. The study will evaluate screening sensitivity, specificity, false-negative rate, predictive values, calibration, and performance across different centers, devices, and time periods.
This is an investigator-initiated, prospective, multicenter, observational, staged platform cohort study involving hospitals and health examination centers. The study is designed to establish a standardized and traceable exhaled-breath electronic-nose platform and to evaluate its potential role as a first-line risk prescreening tool rather than as a stand-alone diagnostic test. Up to 20,000 participants will be prospectively enrolled. The first stage is a methodological standardization and cross-center consistency cohort of approximately 500 clinically stable participants. Each participant will complete three predefined breathing maneuvers in randomized order: end-expiratory sampling without breath holding, sampling after a 5-second breath hold, and sampling after a 10-second breath hold. Each maneuver will be repeated twice. At least 250 participants will undergo repeat sampling at 7±3 days and 30±7 days, and selected participants will undergo cross-device or cross-center bridge sampling. Repeatability, within-participant variability, sample validity, tolerability, and device/center consistency will be evaluated to determine the locked sampling and quality-control procedure for the subsequent large cohort. The second stage is a multi-disease risk prescreening cohort of approximately 19,500 participants. Prespecified major disease modules include lung cancer/clinically significant pulmonary nodules, chronic respiratory diseases, and metabolic/endocrine diseases. Liver, kidney, cardiovascular, and systemic inflammatory/infectious/immune conditions will be evaluated as secondary or exploratory modules. Because participants may have more than one condition, disease outcomes will be modeled using a multi-label rather than mutually exclusive classification framework. Approximately 12,000 participants will be used for model development, approximately 3,000 for temporally independent evaluation, and approximately 4,500 from prespecified held-out centers for whole-center external evaluation. Preprocessing procedures, model architecture, features, module-specific screening thresholds, and the overall screening rule will be locked before evaluation data are analyzed. Temporal and whole-center external evaluation datasets will not be used for model tuning or threshold selection. Reference status for each disease module will be determined from routine clinical or health-screening information, including laboratory testing, pulmonary function testing, imaging, pathology, specialist assessment, and routine follow-up as applicable. The study will not require additional CT scans, blood sampling, endoscopy, surgery, or other invasive procedures solely to establish the reference standard. Participants with insufficient reference information will not be included in the corresponding primary accuracy analysis. Primary evaluation of the locked risk prescreening models will include sensitivity, specificity, false-negative rate, and 95% confidence intervals at fixed thresholds. Positive predictive value, negative predictive value, and screening-positive rate will also be reported in consecutively recruited intended-use populations without case enrichment. Secondary analyses will assess AUROC, AUPRC, likelihood ratios, Brier score, calibration, decision-curve net benefit, subgroup performance, and transportability across centers, devices, and acquisition periods. A nested longitudinal/repeat-sampling cohort of approximately 600-1,000 participants, with an upper limit of 3,000, may undergo repeat breath sampling at routine preoperative/postoperative, treatment, follow-up, or health examination visits to explore within-person temporal changes in breath profiles. These analyses are exploratory and are not part of the primary risk prescreening conclusions.
Study Type
OBSERVATIONAL
Enrollment
20,000
Participants will provide standardized exhaled-breath samples for electronic-nose analysis. The electronic-nose system records multichannel gas-sensor responses together with flow, temperature, humidity, and process information. In the methodological standardization cohort, participants will undergo repeated sampling using three predefined breathing maneuvers to assess repeatability and cross-center/device consistency. In the multi-disease risk prescreening cohort, participants will undergo the locked standardized sampling procedure for development and independent evaluation of disease risk prescreening models. Electronic-nose results are for research purposes only and will not be reported to participants or clinicians or used to alter routine screening, diagnosis, or treatment.
Same-Day Repeatability of the Locked Exhaled-Breath Sampling Method
Same-day repeatability of electronic-nose measurements obtained using the locked exhaled-breath sampling method will be assessed using the intraclass correlation coefficient (ICC) with 95% confidence intervals based on repeated measurements collected from the same participant during the same visit.
Time frame: During the baseline sampling visit; repeated samples are collected approximately 3-5 minutes apart.
Screening Performance of the Locked Multi-Disease Risk Prescreening Models
For each prespecified major disease module meeting the required event-number threshold, sensitivity, specificity, false-negative rate, and corresponding 95% confidence intervals will be estimated at the locked screening threshold. Positive predictive value, negative predictive value, and screening-positive rate will additionally be reported in consecutively recruited, non-enriched intended-use populations. Temporal and whole-center external evaluations will be reported separately.
Time frame: From index breath sampling to completion and adjudication of the corresponding routine reference screening or clinical assessment, up to 16 months after index breath sampling.
Area Under the Receiver Operating Characteristic Curve of the Locked Risk Prescreening Models
For each prespecified major disease module meeting the required event-number threshold, discrimination of the locked risk prescreening model will be assessed using the area under the receiver operating characteristic curve (AUROC) with 95% confidence intervals. Temporal and whole-center external evaluations will be reported separately.
Time frame: From index breath sampling to completion and adjudication of the corresponding routine reference screening or clinical assessment, up to 16 months after index breath sampling.
Downstream Examination Burden of the Any-Major-Module-Positive Rule
The downstream examination burden of the prespecified "any major module positive" rule will be estimated as the number of participants per 1,000 individuals screened who would be referred for further disease-specific screening or clinical assessment under the locked rule.
Time frame: From index breath sampling to completion and adjudication of the corresponding routine reference screening or clinical assessment, up to 16 months after index breath sampling.
Valid-Sample Rate of Standardized Exhaled-Breath Sampling
The valid-sample rate will be defined as the proportion of completed exhaled-breath sampling procedures that meet the prespecified locked quality-control criteria for a valid electronic-nose sample.
Time frame: During each exhaled-breath sampling visit.
Short-Term Stability of the Locked Exhaled-Breath Sampling Method
Short-term stability of electronic-nose measurements obtained using the locked sampling method will be assessed using the intraclass correlation coefficient (ICC) with 95% confidence intervals across baseline and repeat measurements at 7±3 days and 30±7 days.
Time frame: From baseline sampling through the 30±7-day repeat-sampling visit.
Adverse Event Rate During or Immediately After Exhaled-Breath Sampling
The adverse event rate will be defined as the proportion of participants experiencing one or more adverse events during or immediately after exhaled-breath sampling, including cough, dyspnea, chest tightness, dizziness, nausea, syncope, hypoxemia, or other adverse events recorded in association with the sampling procedure.
Time frame: During and immediately after each exhaled-breath sampling procedure.
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.