Development and Multicenter Validation of an Explainable System for Neonatal ARDS-Compatible Phenotyping
Development and Multicenter Validation of an Explainable System for Identifying Clinical Phenotypes Compatible With Neonatal Acute Respiratory Distress Syndrome
Neonatal acute respiratory distress syndrome (NARDS) can be difficult to identify consistently because relevant information is distributed across clinical notes, imaging reports, and respiratory support records. This study will develop and validate an explainable system that organizes routinely collected electronic health record information and identifies infants whose clinical findings are compatible with NARDS.
The study will involve three neonatal intensive care units in China. Historical records from the lead center will be used for system development. A later period at the lead center and independent records from the two collaborating centers will be used for temporal and geographic validation. After the system has been locked, newly eligible infants will be included in a prospective validation phase without changing their clinical care.
System results will be compared with an independent reference assessment by neonatal intensive care specialists. The specialists will classify each infant's first eligible respiratory event as a high-likelihood NARDS-compatible clinical phenotype, a non-compatible clinical phenotype, clinically uncertain, or insufficient information. The study will evaluate sensitivity, specificity, predictive values, review workload, and the ability to identify insufficient information. During prospective validation, system results will remain unavailable to treating clinicians. The system is being evaluated as a research screening and review tool; it is not intended to replace a full clinical diagnosis or to determine treatment.
研究概览
地位
条件
详细说明
Study design and objective This is a three-center observational cohort study combining retrospective system development and validation with prospective validation of a locked system. Its objective is to develop an explainable electronic health record-based system for identifying a NARDS-compatible clinical phenotype and prioritizing candidate records for specialist review.
Establishment of retrospective cohorts Historical NICU records dated January 1, 2018, through December 31, 2025, will provide the retrospective source population. Records from the lead center dated 2018-2022 will form the development cohort. Records from the lead center dated 2023-2025 will form an independent internal temporal validation cohort. Records from each collaborating center dated 2023-2025 will form two separate geographic external validation cohorts. The planned formal adjudication sample is approximately 1,600 candidate events for development and 800 candidate events in each of the three retrospective validation cohorts. Each infant's first eligible event will be used in the primary analysis.
Candidate screening and sampling Candidate records will be identified using prespecified evidence of respiratory support or escalation, bilateral or diffuse pulmonary imaging abnormalities, acute lung injury triggers, or relevant diagnostic expressions. Diagnostic codes will be used for screening and descriptive analyses.
System development and locking The system will extract traceable evidence from imaging reports and other permitted clinical records, including acute respiratory deterioration, acute lung injury triggers, pulmonary imaging abnormalities, and alternative explanations. It will assign high-priority review, routine review, or insufficient-information status and retain the supporting source and timestamp. The variable dictionary, text-processing rules, feature mappings, decision rules, thresholds, software version, and analysis plan will be locked before validation. No retraining, threshold selection, or center-specific tuning will use validation labels.
Reference standard Two qualified neonatal intensive care specialists will independently assess each evidence package using a prespecified adjudication manual. Disagreement will undergo independent arbitration and, when necessary, structured consensus. Adjudicators will be masked to system outputs, explanations, discharge diagnostic labels, and diagnostic codes. They will assign one of four categories: high-likelihood NARDS-compatible clinical phenotype, non-compatible clinical phenotype, clinically uncertain, or insufficient information. The high-likelihood phenotype requires an acute respiratory course, evidence of an acute lung injury trigger, bilateral or diffuse pulmonary parenchymal imaging abnormalities, and no single alternative explanation that fully accounts for the findings.
Prospective validation After retrospective temporal and geographic validation, the same locked system will be assessed in newly eligible infants at the participating centers. The proposed prospective phase will include consecutive eligible infants and will preserve the same index-event definition, evidence window, reference standard, and output categories. Results will be generated in silent mode and will not be displayed to treating clinicians or used to guide care. Independent adjudicators will remain masked to system outputs. Prospective sample size, center participation, recruitment dates, and consent arrangements will be finalized in the protocol and ethics documentation before this phase begins.
Performance analysis The primary measure will be sensitivity of high-priority review for the reference-standard high-likelihood phenotype in each independent validation cohort. Results will be presented separately for the lead-center temporal cohort, each external center, and the prospective phase, with center-specific prospective results when sample size permits. Ninety-five percent confidence intervals will accompany performance estimates. Sampling weights will be used when estimating performance in the historical candidate population. These categories will remain visible in study flow and sensitivity analyses. The primary analysis uses one event per infant.
Data governance Identifiable records, original free text, images, and identity linkage files will remain within each center's authorized environment. Locked code will preferentially be run locally at collaborating centers. Only approved aggregate results and the minimum permitted de-identified audit information will be transferred to the coordinating center. No research-specific treatment or additional biological sampling is planned.
研究类型
注册 (估计的)
联系人和位置
学习联系方式
- 姓名:Liyuan Hu, Ph.D.
- 电话号码:+86-13816060888
- 邮箱:nowadays921@126.com
参与标准
资格标准
适合学习的年龄
接受健康志愿者
有资格学习的性别
取样方法
研究人群
Infants in NICU at 3 participating hospitals before 44 weeks' postmenstrual age whose records meet ≥1 prespecified screening criterion for possible acute pulmonary injury. Historical candidates are sampled from prespecified center/calendar strata. The prospective phase consecutively enrolls newly eligible infants after system locking and retrospective validation. Separately identified screen-negative infants are reviewed if included in the registered screening audit. TTN, RDS, PPHN, pneumonia, and pulmonary hemorrhage are not automatic exclusions by diagnosis alone. Independent adjudication determines whether an alternative condition fully explains findings. Missing key evidence yields an uncertain/insufficient-information assessment, not automatic exclusion or a negative disease label.
描述
Inclusion Criteria:
- Receiving care in the NICU of a participating hospital before 44 weeks of postmenstrual age at the index event.
- Meeting at least one prespecified candidate screening criterion, including a relevant acute lung injury or NARDS/ARDS expression, respiratory support or support escalation, bilateral or diffuse pulmonary parenchymal abnormalities in an imaging report, or a prespecified acute lung injury trigger.
- Having records within the prespecified center and calendar-period cohort, or being newly eligible during the approved prospective validation period.
- Availability of an appropriate legal basis for use of the records, including parental or guardian consent or an ethics-approved waiver when applicable.
Exclusion Criteria:
- Structural lung or airway malformations, complex congenital heart disease, or clearly established cardiac dysfunction or fluid overload that fully explains the respiratory failure and imaging abnormalities.
- Short-term postoperative mechanical ventilation without evidence of acute pulmonary injury.
- Duplicate or unresolvable records that prevent reliable identification of the infant or index event.
学习计划
研究是如何设计的?
设计细节
- 观测模型:COHORT
- 时间观点:OTHER
研究衡量的是什么?
主要结果指标
结果测量 |
措施说明 |
大体时间 |
|---|---|---|
|
Sensitivity of high-priority review for the high-likelihood NARDS-compatible clinical phenotype
大体时间:One assessment per first eligible respiratory event, using records from 48 hours before to 48 hours after the first screening trigger (T0).
|
We will calculate the high-priority proportion among expert-adjudicated NARDS-compatible infants, excluding routine-review and insufficient-information outputs, and report performance with 95% CIs by cohort, with uncertain assessments reported separately. |
One assessment per first eligible respiratory event, using records from 48 hours before to 48 hours after the first screening trigger (T0).
|
次要结果测量
结果测量 |
措施说明 |
大体时间 |
|---|---|---|
|
Positive predictive value of high-priority review
大体时间:One assessment per first eligible respiratory event, using records from 48 hours before to 48 hours after T0.
|
Among high-priority infants with determinate reference, report adjudicated high-likelihood NARDS-compatible proportion and 95% CI by cohort. Enriched samples yield sampling-weighted candidate estimates if permitted. It is not NICU-wide incidence. |
One assessment per first eligible respiratory event, using records from 48 hours before to 48 hours after T0.
|
|
Negative predictive value for the high-priority triage policy
大体时间:One assessment per first eligible respiratory event, using records from 48 hours before to 48 hours after T0.
|
Among determinate-reference non-high-priority infants, report non-compatible phenotype proportion and 95%CI by cohort; describe routine-review and insufficient-information outputs separately, to avoid concealment. Weight historical estimates if possible. |
One assessment per first eligible respiratory event, using records from 48 hours before to 48 hours after T0.
|
|
Proportion of infants with a determinate reference-standard assessment
大体时间:At reference adjudication of the first eligible event, using the same records from 48 hours before to 48 hours after T0.
|
Assessed infants with high-likelihood NARDS-compatible or non-compatible phenotype divided by all assessed; uncertain and insufficient-information assessments reported separately with reasons and 95% CIs, not relabeled negative or removed from flow. |
At reference adjudication of the first eligible event, using the same records from 48 hours before to 48 hours after T0.
|
合作者和调查者
合作者
调查人员
- 学习椅:Liyuan Hu, Ph.D.、Guangzhou Women and Children's Medical Center
研究记录日期
研究主要日期
学习开始 (估计的)
初级完成 (估计的)
研究完成 (估计的)
研究注册日期
首次提交
首先提交符合 QC 标准的
首次发布 (实际的)
研究记录更新
最后更新发布 (实际的)
上次提交的符合 QC 标准的更新
最后验证
更多信息
此信息直接从 clinicaltrials.gov 网站检索,没有任何更改。如果您有任何更改、删除或更新研究详细信息的请求,请联系 register@clinicaltrials.gov. clinicaltrials.gov 上实施更改,我们的网站上也会自动更新.