A Comprehensive Evaluation of an Artificial Intelligence Based Digital Pathology to Monitor Large-scale Deworming Programs Against Soil-transmitted Helminths
试验速览
- 阶段
- 不适用
- 状态
- 尚未招募
- 发起方
- Enaiblers AB
- 入组人数
- 1,100
- 主要终点
- Diagnostic performance, P1.1-2
研究概览
简要总结
The goal of this observational study is to test a new AI diagnostic tool for detection, specification and quantification of parasitic infections (Ascaris, Trichuris, hookworm and S. Mansoni) in School aged children in Ethiopia and Uganda. The main questions it aims to answer are:
- Diagnostic Performance of the AI tool and compare to traditional manual microscopy
- Repeatability and reproducibility of the AI tool and compare to traditional manual microscopy
- Time-to-result for the AI tool
- Cost efficiency for the AI tool and traditional manual microscopy to inform programmatic decisions.
- Usability of the AI tool
Participants will be asked to provide a stool sample for examination by the AI tool and traditional manual microscopy. Participants with a positive test result will receive the proper treatment (Deworming drug).
详细描述
Manual screening of a Kato-Katz (KK) thick stool smear remains the current standard to monitor the impact of large-scale deworming programs against soil-transmitted helminths (STHs). To improve this diagnostic standard, the investigators recently designed an artificial intelligence based digital pathology system (AI-DP) for digital image capture and analysis of KK thick smears. Preliminary results of its diagnostic performance are encouraging, and a comprehensive evaluation of the AI-DP as a cost-efficient end-to-end diagnostic to inform STHs control programs against the target product profiles (TPP) of the World Health Organisation (WHO) is the next step for validation.
The study protocol describes a comprehensive evaluation of the AI-DP based on its (i) diagnostic performance, (ii) repeatability/reproducibility, (iii) time-to-result, (iv) cost-efficiency to inform large-scale deworming programs and (v) usability in both laboratory and field settings. For each of these five attributes, the investigators designed separate experiments with sufficient power to verify the non-inferiority of the AI-DP (KK2.0) over the manual screening of the KK smears (KK1.0). These experiments will be conducted in two STH endemic countries with national deworming programs (Ethiopia and Uganda), focusing on school-age children (SAC) only. Participants will be asked to provide a stool sample for examination by the AI tool and traditional manual microscopy. Participants with a positive test result will receive the proper treatment (Deworming drug).
This comprehensive and well-designed study and accompanying protocols will provide the necessary data to make an evidence-based decision on whether the AI-DP is indeed performant and a cost-efficient end-to-end diagnostic to inform large-scale deworming programs against STHs. Following the protocolized collection of high-quality data the investigators will seek approval by WHO. Through the dissemination of the methodology and statistics, the investigators hope to support additional developments in AI-DP technologies for other neglected tropical diseases in resource-limited settings.
研究设计
- 研究类型
- Observational
- 观察模型
- Cohort
- 时间视角
- Prospective
入排标准
- 年龄范围
- 5 Years 至 14 Years（Child）
- 性别
- All
- 接受健康志愿者
- 是
入选标准
- •Subject, male or female, is 5-14 years of age
- •Parent(s)/guardian(s) of subject signed an informed consent document indicating that they understand the purpose and procedures required for the study and that they are willing to have their child participate in the study
- •Subject of ≥6 (Ethiopia) /8 (Uganda) years old has assented to participate in the study*
- •Subject of ≥12 years old has signed an informed consent document indicating that they understand the purpose of the study and procedures required for the study, and are willing to participate in the study (Ethiopia only)*
- •Subject has provided a stool sample of minimum 5 grams
排除标准
- •Subject has active diarrhoea (defined as the passage of 3 or more loose or liquid stools per day) at baseline or follow-up.
- •Subject is experiencing a severe concurrent medical condition or has an acute medical condition
- •Subject has received anthelmintic treatment within 90 days prior to the start of the study
结局指标
主要结局
Diagnostic performance, P1.1-2
时间窗: up to 10 months
the clinical sensitivity of Kato-Katz 2.0 (KK2.0) and Kato-Katz 1.0 (KK1.0) to detect low, moderate and heavy intensity infections of Ascaris, Trichuris and hookworms
Cost Efficiency P4.2
时间窗: up to 10 months
The total survey cost to reliably inform a declaration that STH are eliminated as a public health problem for Kato-Katz 2.0 (KK2.0) and Kato-Katz 1.0 (KK1.0).
Time to Result P3
时间窗: up to 10 months
Time to result for the artificial intelligence digital pathology diagnostic (Kato-Katz 2.0 (KK2.0)) result.
Diagnostic Performance P1.3-4
时间窗: up to 10 months
The clinical specificity of Kato-Katz 2.0 (KK2.0) and Kato-Katz 1.0 (KK1.0) to detect low, moderate and heavy intensity infections of Ascaris, Trichuris and hookworms
Repeatability and Reproducibility Performance P2
时间窗: up to 10 months
The repeatability and the reproducibility of the scanning process, the AI verification process, the Kato-Katz 2.0 (KK2.0) system as a whole and the manual counting by a microscopist (Kato-Katz 1.0 (KK1.0)).
Cost Efficiency P4.1
时间窗: up to 10 months
The total survey cost to reliably inform a stop decision to the program for Kato-Katz 2.0 (KK2.0) and Kato-Katz 1.0 (KK1.0).
Usability observation P5
时间窗: up to 10 months
The ease-of-use of the complete AI-DP work process for the identified end-users assessed by observations of user groups and user interviews.
次要结局
- Diagnostic performance S1.3(up to 10 months)
- Cost Efficiency S4.1(up to 10 months)
- Diagnostic performance S1.2(up to 10 months)
- Diagnostic performance S1.4(up to 10 months)
- Usability observation S5.1(up to 10 months)
- Usability observation S5.3(up to 10 months)
- Repeatability and Reproducibility Performance S2.2(up to 10 months)
- Time to Result S3.3(up to 10 months)
- Usability observation S5.2(up to 10 months)
- Diagnostic performance S1.1(up to 10 months)
- Repeatability and Reproducibility Performance S2.1(up to 10 months)
- Time to Result S3.1(up to 10 months)
- Time to Result S3.2(up to 10 months)
- Cost Efficiency S4.3(up to 10 months)
- Cost Efficiency S4.4(up to 10 months)
- Cost Efficiency S4.5(up to 10 months)
- Cost Efficiency S4.2(up to 10 months)