Iterative evaluation of mobile computer-assisted digital chest x-ray screening for TB improves efficiency, yield, and outcomes in Nigeria

Wellness on Wheels (WoW) is a model of mobile systematic tuberculosis (TB) screening of high-risk populations combining digital chest radiography with computer-aided automated detection (CAD) and chronic cough screening to identify presumptive TB clients in communities, health facilities, and prisons in Nigeria. The model evolves to address technical, political, and sustainability challenges.
Screening methods were iteratively refined to balance TB yield and feasibility across heterogeneous populations. Performance metrics were compared over time. Screening volumes, risk mix, number needed to screen (NNS), number needed to test (NNT), sample loss, TB treatment initiation and outcomes. Efforts to mitigate losses along the diagnostic cascade were tracked. Participants with high likelihood on CAD4TB (≥80) who tested negative on a single spot GeneXpert were followed-up to assess TB status at six months.
An experimental calibration method achieved a viable CAD threshold for testing. High-ris..., These are data from digital LP chest x-ray images read by CAD4TB version 5 merged with data from 2 G4 Genexpert machines, with a data variable to indicate screening date, cough status, as well as age and sex. 
Two large container trucks housing a lead-lined chest-x-ray suite, reading area, and mobile GeneXpert laboratory were sourced via competitive tendering. Solar panels, shade canopies, anti-theft features were added.
CAD4TB version 4 by Delft Imaging interprets a digital image in less than a minute and can do so consistently during day-long screening events.24–26 The software generates a TB likelihood score between 0 and 100, indicating the extent of lung abnormalities. CAD4TB displays a heatmap pinpointing the size and location affected. The scores are used to set a threshold above which persons are invited for TB testing. Each team had a radiology technologist, laboratory technologists, data clerks, truck driver, and a clinical supervisor. Training was conducted on standard operat..., , # Iterative evaluation of mobile computer-assisted digital chest x-ray screening for TB improves efficiency, yield, and outcomes in Nigeria

Rupert. A. Eneogu, Ellen M.H. Mitchell* , Chidubem Ogbudebe3 , Danjuma Aboki4 , Victor Anyebe3 , Chimezie B. Dimkpa3 , Daniel Egbule4 , Bassey Nsa5 , Emmy van der Grinten6 , Festus O. Soyinka7 , Hussien Abdur-Razzaq8 , Sani Useni3 , Adebola Lawanson9 , Simeon Onyemaechi9 , Emperor Ubochioma9 , Jerod Scholten6 , Johan Verhoef6 , Peter Nwadike6 , Nkemdilim Chukwueme9 , Debby Nongo1 , Mustapha Gidado6

These de-identified data are from routine program evaluation, not a study.

The evaluation was exempted from ethical review

It's an Excel file. There are 14 variables:

### Data dictionary

* PatientIDCAD: random ID
* phase: 1, 2, 3
* Cough_Code: 0= no cough, 1= cough < 2 weeks, 2= cough => 2 weeks
* CAD_Score: CAD SCORE is a number from 0-100 representing the likelihood of having present pulmonary TB.CAD4TB version 5 was used to score x-rays...

移动健康筛查项目（Wellness on Wheels, WoW）是针对尼日利亚社区、医疗机构及监狱中的高危人群开展的移动式系统化结核病（TB）筛查模式，该模式将数字化胸部X线摄影与计算机辅助自动检测（CAD）、慢性咳嗽筛查相结合，用于识别疑似结核病患者。该模式历经迭代以应对技术、政策及可持续性层面的挑战。
筛查方法经过反复优化，以在异质性人群中平衡结核病检出率与筛查可行性。研究对不同阶段的性能指标进行了对比，涵盖筛查总量、风险构成、需筛查人数（number needed to screen, NNS）、需检测人数（number needed to test, NNT）、样本丢失情况、结核病治疗启动情况及治疗结局。同时追踪了诊断流程各环节中针对样本丢失的缓解措施。对于CAD4TB评分≥80分且单次即时GeneXpert检测结果为阴性的参与者，将对其进行为期6个月的随访以评估结核病感染状况。
一种实验性校准方法确定了可用于检测的合理CAD阈值。针对高危人群的相关内容未完整呈现，本数据集包含由CAD4TB版本5读取的数字化LP位胸部X线影像，与两台G4型GeneXpert检测仪生成的数据合并，数据集包含用于标识筛查日期、咳嗽状态以及年龄与性别的变量。
项目通过竞争性招标采购了两辆大型集装箱卡车，车内搭载带铅防护的胸部X线摄影套件、阅片区及移动式GeneXpert实验室。车辆加装了太阳能板、遮阳棚及防盗装置。
代尔夫特成像（Delft Imaging）开发的CAD4TB版本4可在一分钟内完成单张数字化影像的分析，且可在全天的筛查活动中保持稳定的运行效果[24-26]。该软件可生成0至100分的结核病患病可能性评分，用以反映肺部异常程度；同时可生成热图，精准定位受影响区域的范围与位置。评分被用于设定阈值，高于该阈值的受试者将被邀请进行结核病检测。每个筛查小组配备放射科技师、实验室技师、数据录入员、卡车司机及临床督导。相关培训围绕标准操作流程展开……
# 尼日利亚移动式计算机辅助数字化胸部X线结核病筛查的迭代评估提升了筛查效率、检出率与临床结局
Rupert A. Eneogu、Ellen M.H. Mitchell*、Chidubem Ogbudebe³、Danjuma Aboki⁴、Victor Anyebe³、Chimezie B. Dimkpa³、Daniel Egbule⁴、Bassey Nsa⁵、Emmy van der Grinten⁶、Festus O. Soyinka⁷、Hussien Abdur-Razzaq⁸、Sani Useni³、Adebola Lawanson⁹、Simeon Onyemaechi⁹、Emperor Ubochioma⁹、Jerod Scholten⁶、Johan Verhoef⁶、Peter Nwadike⁶、Nkemdilim Chukwueme⁹、Debby Nongo¹、Mustapha Gidado⁶
本数据集为去标识化的常规项目评估数据，并非源自专门的研究项目。本评估已豁免伦理审查。
数据集采用Excel格式，共包含14个变量：
### 数据字典
* PatientIDCAD：随机生成的患者编号
* phase：阶段，取值为1、2、3
* Cough_Code：咳嗽状态编码，0=无咳嗽，1=咳嗽时长<2周，2=咳嗽时长≥2周
* CAD_Score：CAD评分，为0至100的数值，代表当前罹患肺结核的可能性。本次研究使用CAD4TB版本5对X线影像进行评分……