)

Storm Rhoda from Camps Bay High School won numerous awards at Eskom Expo International Science Fair

Last year, Camps Bay High School’s Deputy Head Prefect, Storm Rhoda, was in the news for his science project:  Machine Learning to assist in Pneumonia Diagnosis.  He won a silver medal and numerous other awards at the Eskom Expo for Young Scientists International Science Fair and he was selected to represent South Africa at Regeneron International Science and Engineering Fair this year.

Unfortunately, due to the Covid-19 Pandemic, the Expo had to be held virtually. Storm’s project was one of the 52 global finalists in the Robotics and Intelligent Machines Category at the Regeneron ISEF Virtual 2020 Expo. The project received the Official Intel ISEF 2020 Abstract and Certification and was approved by the Scientific Review Committee.

Storm’s algorithm makes it quicker and more accurate for a health professional to identify and distinguish the difference between lungs that are  infected by pneumonia in an efficient manner.

Pneumonia is among the leading causes of death in the world and it is ranked sixth-leading cause of premature death in South Africa. The people at risk of dying from pneumonia are children younger than 5 years, adults over 65 years and immunocompromised individuals.

Radiological diagnosis is the most common way of diagnosing patients and radiograph qualities are easily compromised due to the sensitivity and specificity of diagnosis. Compromised x-rays make it difficult to establish a diagnosis.

Two machine learning models were created in Storm’s project to identify and distinguish pneumonia in adult patients and paediatric patients. The general and paediatric-specific pneumonia diagnosis models were tested against x-ray images and predictions were validated against validated data and a radiologist.

The general pneumonia diagnosis model focused on adult patients and achieved an accuracy of 90.3%. While the paediatric- specific model focused on paediatric patients and achieved an accuracy of 83.03%.

The algorithm created is able to identify and distinguish the difference between a pair of infected pneumonia lungs and a pair of lungs that are not infected in an efficient manner for adult patients and paediatric patients.

Become a Sponsor
  • Related Posts

    KZN Marlins Basketball – St John’s D.S.G. outstanding

    KZN Marlins Basketball. Lamia Amod Joins the KZN Marlins! St John’s D.S.G. is thrilled to celebrate Lamia Amod, whose exceptional talent and determination have earned her a coveted place in…

    Gedagte vir die Week – Thought of the Week

    Gedagte vir die Week – Here, U is my lewe, U sorg vir my. Wat ek ontvang, kom alles van U af. Psalms 16: 5-7 Thought of the Week –…

    Leave a Reply

    You Missed

    KZN Marlins Basketball – St John’s D.S.G. outstanding

    KZN Marlins Basketball – St John’s D.S.G. outstanding

    Gedagte vir die Week – Thought of the Week

    Gedagte vir die Week – Thought of the Week

    Teemane Karateklub Winter Challenge – Hoërskool Kalahari

    Teemane Karateklub Winter Challenge – Hoërskool Kalahari

    EP U18 youth rugby – Pearson High School outstanding

    EP U18 youth rugby – Pearson High School outstanding

    Sharks U18B Team Selection – St Charles College delighted

    Sharks U18B Team Selection – St Charles College delighted

    Vrystaat Provinsiale Danskampioenskap – Hoërskool Sentraal

    Vrystaat Provinsiale Danskampioenskap – Hoërskool Sentraal