Improving AI/ML-readiness of Synthetic Data in a Resource-Constrained Setting

在资源受限的环境中提高合成数据的 AI/ML 准备度

• 批准号: 10841728
• 负责人: Amina Abubakar Ali
• 金额: $ 25.44万
• 依托单位: AGA KHAN UNIVERSITY (KENYA)
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-15 至 2026-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10841728
• 关键词: Address; Administrative Supplement; Africa; Artificial Intelligence; Big Data; Cellular Phone; Child Health; Cloud Computing; Computational Technique; Country; Data; Data Science; Data Set; Data Sources; Development; Disease; Disparity population; Documentation; Environment; Event; FAIR principles; Funding; Goals; Graph; Health; Health Policy; Health Sciences; Heterogeneity; Individual; Investments; Kenya; Knowledge; Laws; Machine Learning; Maternal Health; Mental Health; Methods; Michigan; Modeling; Nature; Outcome; Penetration; Politics; Population; Privacy; Readiness; Research; Research Personnel; Resource-limited setting; Resources; Rural; Statistical Distributions; System; Techniques; Testing; Training; United States National Institutes of Health; Universities; Validation; Work; career; data management; data preservation; data sharing; improved; innovation; machine learning method; machine learning model; marginalized population; multimodal data; neonatal health; novel strategies; parent project; population based; preservation; response; social; social determinants; student training

PROJECT SUMMARY / ABSTRACT The parent project, UZIMA-DS (UtiliZing Health Information for Meaningful Impact in East Africa through Data Science), aims to create a scalable and sustainable platform to apply novel approaches to data assimilation and advanced artificial intelligence (AI)/machine learning (ML)-based methods to improve health outcomes in two health domains: maternal, newborn and child health; and mental health. Led by the Aga Khan University in East Africa (AKU) and the University of Michigan, UZIMA-DS is a U54 Research Hub funded under the NIH Data Sci- ence for Health Discovery and Innovation in Africa Initiative. During these first two years, UZIMA-DS has focused on acquiring and harmonizing multimodal data sources. However, we and many other DS-I Africa awardees have encountered several barriers to efficiently and effectively creating AI-ready data sets, which include: 1) regulatory concerns around privacy and confidentiality, 2) heterogeneity in data laws across countries limiting the accessibil- ity of data, and 3) a lack of sufficient datasets not only for training ML models and validation but also for training students and early career investigators for capacity building. Synthetic data, or data that is generated artificially using computational techniques such as AI, is a promising technique that could address these barriers and ena- ble the broad sharing of AI-ready data sets. As part of this administrative supplement, we propose to create an AI-ready synthetic data set using one of our real UZIMA-DS data sets from Kenya: the Kaloleni-Rabai Health and Demographic Surveillance Systems (KRHDSS). KRHDSS is a population-based demographic and health surveil- lance system established in 2017 by AKU. Information is collected at least annually on ~40 demographic, health, social determinants of disease, and vital events from a resident population of about 99,000 individuals. Leverag- ing our preliminary work using a Microsoft Azure instance, we will create AI-ready synthetic datasets for research and training and evaluate whether causal relationships in real data are preserved in synthetic datasets. The overarching goal of this proposal is to “put data to work” by developing a roadmap for the curation and use of AI-ready synthetic data using FAIR principles (findable, accessible, interoperable, and re‑usable) that can be eas- ily accessed and shared for research and training purposes across the globe. Ultimately, this work has the poten- tial to promote more effective and efficient sharing of AI-ready data globally. Using cloud infrastructure and Health and Demographic Surveillance Systems data from rural Kenya as a use case, this work has immediate implications for how AI-ready data can be leveraged in resource-constrained settings to improve data driven health policy decisions for traditionally disadvantaged and marginalized groups.

项目摘要 /摘要 母公项目Uzima-DS（利用健康信息通过数据对东非有意义的影响 科学），旨在创建一个可扩展且可持续的平台，以将新颖的方法应用于数据同化和 高级人工智能（AI）/机器学习（ML）基于两个改善健康结果的方法 卫生领域：物物，新生儿和儿童健康；和心理健康。由东部的阿加汗大学领导 非洲（AKU）和密歇根大学的Uzima-DS是根据NIH Data Sci-资助的U54研究中心 非洲倡议中的健康发现和创新。在最初的两年中，Uzima-DS专注于 关于加速和协调多模式数据源。但是，我们和许多其他DS-I非洲奖项已有 遇到了有效有效地创建AI-Ready数据集的几个障碍，其中包括：1）监管 对隐私和机密性的担忧，2）跨国数据法的异质性，限制了Accessibil- 数据和3）缺乏足够的数据集，不仅用于培训ML模型和验证，还用于培训 学生和早期职业调查人员的能力建设。合成数据或人为生成的数据 使用诸如AI之类的计算技术是一种有希望的技术，可以解决这些障碍和ENA- BLE的广泛共享AI-Ready数据集。作为此行政补充的一部分，我们建议创建一个 AI-Ready合成数据集使用我们来自肯尼亚的真正的Uzima-DS数据集之一：Kaloleni-Rabai Health和 人口监视系统（KRHDSS）。 KRHDSS是一项基于人群的人口统计和健康调查 - 兰斯系统由Aku于2017年建立。至少每年收集有关约40个人口统计，健康， 疾病的社会决定者，以及来自约99,000人的居民人口的重要事件。杠杆 使用Microsoft Azure实例为我们的初步工作，我们将创建AI-Ready合成数据集用于研究 培训并评估合成数据集中是否保留实际数据中的因果关系。这 该提案的总体目标是通过开发策划和使用路线图“将数据运行” 使用公平原理（可访问，可互操作和可重复使用）的AI-Ready合成数据，可以缓解 ILY访问并共享全球研究和培训目的。最终，这项工作具有潜在的 在全球范围内促进AI-Ready数据的更有效和有效共享。使用云基础架构和 来自肯尼亚的健康和人口监视系统作为用例，这项工作立即进行 对如何在资源约束设置中利用AI-Ready数据的含义，以改善数据驱动器 传统上受到干扰和边缘化群体的健康政策决策。

项目成果

Obesity and Risk of Hypertension in Preadolescent Urban School Children: Insights from a Developing Country.

青春期前城市学童的肥胖和高血压风险：来自发展中国家的见解。

• DOI: 10.21203/rs.3.rs-4213965/v1
• 发表时间: 2024
• 期刊: Research square
• 作者: Akhtar,Samina;Khan,Shahid;Aziz,Namra;Magsi,MuhammadImran;Samad,Zainab;Iqbal,Romaina;Almas,Aysha
• 通讯作者: Almas,Aysha

COVID-19 vaccination refusal trends in Kenya over 2021.

• DOI: 10.1016/j.vaccine.2022.12.066
• 发表时间: 2023-01-27
• 期刊: VACCINE
• 影响因子: 5.5
• 作者: Rego, Ryan T.;Kenney, Brooke;Ngugi, Anthony K.;Espira, Leon;Orwa, James;Siwo, Geoffrey H.;Sefa, Christabel;Shah, Jasmit;Weinheimer-Haus, Eileen;Delius, Antonia Johanna Sophie;Pape, Utz Johann;Irfan, Furqan B.;Abubakar, Amina;Shah, Reena;Wagner, Abram;Kolars, Joseph;Boulton, Matthew L.;Hofer, Timothy;Waljee, Akbar K.
• 通讯作者: Waljee, Akbar K.

Comparison of logistic regression with regularized machine learning methods for the prediction of tuberculosis disease in people living with HIV: cross-sectional hospital-based study in Kisumu County, Kenya.

逻辑回归与正则化机器学习方法预测艾滋病毒感染者结核病的比较：肯尼亚基苏木县医院的横断面研究。

• DOI: 10.21203/rs.3.rs-3354948/v1
• 发表时间: 2023
• 期刊: Research square
• 作者: Orwa,James;Oduor,Patience;Okelloh,Douglas;Gethi,Dickson;Agaya,Janet;Okumu,Albert;Wandiga,Steve
• 通讯作者: Wandiga,Steve

Mental health and psychological well-being of Kenyan adolescents from Nairobi and the Coast regions in the context of COVID-19.

• DOI: 10.1186/s13034-023-00613-y
• 发表时间: 2023-05-19
• 期刊: CHILD AND ADOLESCENT PSYCHIATRY AND MENTAL HEALTH
• 影响因子: 5.6
• 作者: Mbithi, Gideon;Mabrouk, Adam;Sarki, Ahmed;Odhiambo, Rachel;Namuguzi, Mary;Dzombo, Judith Tumaini;Atukwatse, Joseph;Kabue, Margaret;Mwangi, Paul;Abubakar, Amina
• 通讯作者: Abubakar, Amina

Use of Mobile Technology to Identify Behavioral Mechanisms Linked to Mental Health Outcomes in Kenya: Protocol for Development and Validation of a Predictive Model.

使用移动技术识别与肯尼亚心理健康结果相关的行为机制：预测模型的开发和验证协议。

• DOI: 10.21203/rs.3.rs-2458763/v1
• 发表时间: 2023
• 期刊: Research square
• 作者: Njoroge,Willie;Maina,Rachel;Elena,Frank;Atwoli,Lukoye;Wu,Zhenke;Ngugi,Anthony;Sen,Srijan;Wang,Jian;Wong,Stephen;Baker,Jessica;Haus,Eileen;Khakali,Linda;Aballa,Andrew;Orwa,James;Nyongesa,Moses;Merali,Zul;Akbar,Karim;Abubak
• 通讯作者: Abubak