When we began consolidating our technology and AI predictions for 2019, what stood out to me were the ways in which artificial intelligence can be used for social good in 2019 and beyond.
In 2018 the CDC determined that approximately 1 in 59 children is diagnosed with an autism spectrum disorder (ASD). Autism-associated health problems extend across the lifespan and depression affects an estimated 7% of children and 26% of adults with autism. It is important to emphasize that individuals diagnosed with autism experience both competencies as well as difficulties as part of social groups and engaging with different cultures.
I will present here five ways where technologies like AI, edge computing, and data virtualization could help people with autism live a better and healthier life:
- Smart and early diagnosis: Current behavioral assessment methods and score-sheets with questions for the parent or the medical practitioner are time consuming. However, early diagnosis could tremendously provide positive impact on a child’s development. This is where AI algorithms like decision trees could help in identifying people with autism, thus, providing rapid detection and earlier treatment of diagnosed individuals.
- Predicting autism with neuroscience & AI: Brain connectivity is crucial to elucidating how neurons and neural networks process information. Machine learning could be used to analyze MRI brain imaging data and extract insights from these connections. These include the shape of individual neurons and their processes, as well as in the size, placement and interconnection of large-scale structures. A typical model would be to use feature selection, a tool for dimensionality reduction, to select the most relevant features from brain image data, and then a deep neural network classifier could be used to classify and predict autism by identifying multivariate and nonlinear functional connectivity patterns.
- Real-time behavioral tracking & analysis: In their homes, with the help of edge computing nodes and data virtualization to decipher data streams from the wearables of an autism patient, we can monitor their heart rates, anxiety levels, mood swings, and other activities like exercise or sleeping patterns. This will assist help practitioners improve on their teaching skills. Smart edge nodes equipped with self-organized coordination abilities act as low-resource clinical tool; they can make smart decisions based on the detection of alarming issues locally which is helpful for clinical prioritization of individuals with autism. A real time SMM (stereotypical motor movements) detection system could also be developed to analyze behavioral cues from the data.
- The rise of data-driven robots: The potential of these robots is huge. They can learn, interpret and recognize the child’s behavioral cues, helping to predict the child’s affective states and methods of engagement to different cultures and people. Robots equipped with sensory inputs including multimodal-sensory information, gaze estimation, human action recognition, facial expression recognition, and voice/tone analysis could help in classifying stereotypical behaviors of children with autism by transforming these inputs to features, and then analyzing them using machine learning algorithms.
- The recent advancements in voice assistants: AI will eventually allow these devices to inhabit anthropomorphistic features and conduct natural, human-sounding conversations. Numerous apps will evolve on top of these devices that will help autism patients improve their speech.
Artificial intelligence could play a very crucial role for the future of those diagnosed with autism, augmenting human friends and practitioners. Technologies like data virtualization will help to decipher data streams of wearables in real time while also ensuring the security and privacy of such health data.
Neuroscience and AI robots will help us understand behavioral cues of people with autism, virtual assistants will be able to help to improve their speech, and edge computing will help us act faster. Indeed, AI may well excel in understanding human behavior, achieving more results than we have ever seen before, it’s an exciting time for us all.
- If Trust is the Main Ingredient of Leadership, Is Trust the Main Ingredient of Successful AI? - November 18, 2020
- The Main Pillars of Future Polymer Factories, the Next Future Material for AI - November 15, 2019
- From the Bronze Age to Today’s AI-based Circular Economy, and How Data Virtualization and Federated Learning Make It Possible - August 13, 2019