Summary

AI-generated

This summary is written by a language model reading the source document. It is not the publisher's words and is not a substitute for the original.

Learn more about AI enrichment

The report details seven AI and ML research projects aimed at improving African healthcare, most notably demonstrating that a hybrid verbal autopsy model has already influenced how the government of Tanzania reports mortality statistics.

Key insights

AI-generated

These insights are written by a language model reading the source document. They are not the publisher's words and are not a substitute for the original.

Learn more about AI enrichment
  • A hybrid approach to verbal autopsy for determining causes of death has been implemented in Tanzania, leading the Ministry of Health to integrate medically certificated reports and model-generated verbal autopsy data into a single national mortality statistics report.
  • Research into Chronic Obstructive Pulmonary Disease (COPD) is developing a predictive model and decision support system using wearable pulse oximeters to enable early detection of exacerbations and reduce hospitalizations.
  • An agent-based model for the surveillance of dengue fever and Chikungunya in Sub-Saharan Africa, specifically Tanzania, aims to improve early detection and resource allocation to reduce mortality and morbidity.
  • The use of ensemble convolutional neural networks for multi-class, multi-label retinal disease detection is proposed to provide an affordable diagnostic solution for resource-constrained healthcare environments.
  • Research on Internet of Things (IoT) security for e-health in developing countries focuses on using light cryptographic techniques and blockchain to protect sensitive medical data and foster trust in digital health platforms.
  • A speech improvement framework using long short-term memory neural networks and dynamic time warping was developed to expedite the retrieval of health records at Kenyatta National Hospital.
  • The project is developing a captioning model for biomedical images using generative adversarial networks (GAN) and Encoder-Decoder architectures to reduce the time and cost of radiology analysis and mitigate human error.

Cite the original document

APA
Oduor, A., Bwire, C., Ogada, T., Ojenge, W., Ayub, M., Wanjau, S., Makayoto, F., & Obunga, P. (n.d.). Nurturing well-being. African Centre for Technology Studies. https://acts-net.org/wp-content/uploads/AI4D-Africa-Research-Projects-in-Health-2023.pdf
Chicago
Oduor, Alfred, Caroline Bwire, Tom Ogada, Winston Ojenge, Mercy Ayub, Sam Wanjau, Fiona Makayoto, and Patrick Obunga. Nurturing well-being. African Centre for Technology Studies, n.d. https://acts-net.org/wp-content/uploads/AI4D-Africa-Research-Projects-in-Health-2023.pdf.
Wikipedia
{{cite report |last1=Oduor |first1=Alfred |last2=Bwire |first2=Caroline |last3=Ogada |first3=Tom |last4=Ojenge |first4=Winston |last5=Ayub |first5=Mercy |last6=Wanjau |first6=Sam |last7=Makayoto |first7=Fiona |last8=Obunga |first8=Patrick |title=Nurturing well-being |publisher=African Centre for Technology Studies |url=https://acts-net.org/wp-content/uploads/AI4D-Africa-Research-Projects-in-Health-2023.pdf |access-date=5 November 2026 |via=Climate Insights Directory (document actsnet-000040)}}
BibTeX
@techreport{oduorndnurturing, author = {Oduor, Alfred and Bwire, Caroline and Ogada, Tom and Ojenge, Winston and Ayub, Mercy and Wanjau, Sam and Makayoto, Fiona and Obunga, Patrick}, title = {{Nurturing well-being}}, institution = {African Centre for Technology Studies}, url = {https://acts-net.org/wp-content/uploads/AI4D-Africa-Research-Projects-in-Health-2023.pdf}, urldate = {2026-11-05}, note = {Indexed by Climate Insights Directory, document actsnet-000040} }

Full text

Collected · Record updated