Published By: IEEE Spectrum, 2/15/2017
>> View the Article <<
Researchers at the University of North Carolina, Chapel Hill have applied deep-learning algorithms to brain scans of children with a high risk of autism. Algorithms used three indicators, brain surface area, volume, and the gender of the child, to determine if 6- to 12-month-old infants were likely to develop autism. The results were 81% accurate at predicting later diagnosis. This improves over a 50% prediction rate from behavioral questionnaires.
Flesch-Kincaid Grade Level of Article: 12.1
The article contains a mild expletive, and the public comments section has an inflammatory remark.
Extended Discussion Questions
- How might earlier, more accurate detection of autism risk benefit both patients and their caretakers?
- Could similar algorithms be used for other medical purposes?
- How else might they be applied?
- Have you heard or read about any other uses of deep learning on images for medical diagnosis?
- What about in other disciplines?
- The lead researcher points out that this type of testing is expensive and not necessarily clinically useful in all cases. How can expensive, difficult testing like this complement other screening and diagnosis methods? Where do these algorithms fit in?
- Based on this story and others you’ve heard or read about, would you say that computer-aided medicine is more likely to make a similar quality of health care available to everyone everywhere, or is it more likely to widen the gap in health care between different places and different socio-economic groups? Why?
Global Impact Learning Objectives:
- LO 7.2.1 Explain how computing has impacted innovations in other fields.
- LO 7.4.1 Explain the connections between computing and real-world contexts, including economic, social, and cultural contexts.
Global Impact Essential Knowledge:
- EK 7.2.1A Machine learning and data mining have enabled innovation in medicine, business, and science.
- EK 7.2.1B Scientific computing has enabled innovation in science and business.
- EK 7.4.1C The global distribution of computing resources raises issues of equity, access, and power.
Other CSP Big Ideas:
- Idea 4 Algorithms
Banner Image: “Network Visualization – Violet – Offset Crop“, derivative work by ICSI. New license: CC BY-SA 4.0. Based on “Social Network Analysis Visualization” by Martin Grandjean. Original license: CC BY-SA 3.0.
Home › Forums › AI Predicts Autism From Infant Brain Scans
Tagged: 7.2.1 Impact in other fields, 7.2.1A Data impact, 7.2.1B Scientific computing, 7.4.1 Real-world contexts, 7.4.1C Equity and power