Future of AI in Healthcare (Part 1): Battling Alzheimer
Note: This article is the first part of a series, in which Savvycom Team will discuss the future of AI in healthcare – battling the world deadliest diseases.
We all want to live, as long and as healthy as possible. And thanks to the advancement in modern healthcare, almost every single organs in our body have the future of being repaired or replaced.
All except the brain.
That’s the reason behind Alzheimer condition. Ranking number 5 in WHO’s TOP 10 deadliest disease worldwide list, it is responsible for the $259 billion healthcare bill in 2017. According to Lisa Genova, a neuroscientist graduated from Harvard University, one in every two 85 years old citizens will have Alzheimer. So, either you will be a patient of Alzheimer or a caregiver to Alzheimer. There is no running away from it.
‘If you live long enough, Alzheimer seems to be your brain’s destiny’, said Lisa.
But, the world is changing in the blink of an eye, and there are words around the block that Artificial Intelligence (AI) – arguably the most consequential revolution in the history of humanity – may help.
Is there a future of AI in healthcare for Alzheimer patients?
1. Alzheimer: The Unavoidable Illness
Discovered in 1906 by Dr. Alois Alzheimer, the illness’ most common symptoms include sleeping issues, memory problems, drastic mood changes and constant confusion.
After decades of research, doctors and scientist across the globe are still debating about root causes for Alzheimer: They have a lead: ‘amyloid beta’ – a protein that is initially created where two neurons connecting.
Normally, this protein is cleared away routinely by microglia, the key cells in overall brain maintenance, and thereby keeping it at a stable level. However, due to unknown events or factors, during the first stage of Alzheimer, too much amyloid beta is released. At this point, the patients are blissfully unaware with no significant symptoms.
15 to 20 years later, the accumulation of amyloid beta reaches a peak, creating amyloid plaques. These plaques start breaking down the brain structure: generating tangles that block communication between cells while triggering the immune systems to kill off disabled nerve cells.
The destruction process often starts at the hippocampus – the part of the brain that responsible for forming new short-term memories. After that, the protein starts invade other parts and destroy the patient’s abilities to process logical thoughts, control emotion, perceive reality, remember long-term memories and lastly, govern heart rate and breathing rhythm – which result in death
2. Is there a cure?
Sadly, no. According to Forbes, due to the high monetary incentive associated with Alzheimer, many companies and corporations have devoted billions of dollars to researches and projects, with nearly zero returns. After approximately 400 clinical trials, the failure rate ranks nearly 100%. No new therapies have been approved in more than 12 years.
Many blame the lack of detailed information on Alzheimer, plus the fact that patient tends to suffer from multiple coexisting illnesses due to their old ages, making it very difficult to assess disease stages.
There aren’t any disease-modifying treatment or medications today that can slow down the neuronal damage either. Also according to Forbes, the drugs that are available in the market can only slightly improve the symptoms. The performances of those drugs are quite inconsistent – meaning varies from person to person.
But can we prevent it? So far, all medical recommendations tend to focus on making sure you having a good sleeping schedule, healthy low-cholesterol diets, frequent exercise routines and learn constantly. Several scientists are also betting big on a preventive medicine: keeping amyloid plaques level stable through chemical compounds in the forms of vaccine or pills. However, this kind of drugs has failed in clinical trials because the subjects in the trials are just too far down the road.
3. Future of AI in Healthcare: its abilities to help Alzheimer patients
With all that we know, early diagnosis seems to be the key to a patient’s ability to control their illness. And, based on the symptoms mentioned, the future of AI is clear – predicting Alzheimer as early on as possible. In fact, the process of how AI will conduct this task can be categorized into four sections below:
3.1. Speech Monitoring:
- How: Alzheimer’s patient tends to have long pauses between words, prefer pronouns to nouns (E.g: saying he or she rather than the person’s name), and give a simplistic description of things. These, in daily life, are quite difficult for the human to be objective and detect. As a result, AI can be used to analyze speech patterns to detect and monitor even the slightest dementia progression.
- Highlighted project: Winterlight, a Canada-based startup, has decided to lead the future of AI in healthcare by apply machine learning and audio recording into a robot that observes speech patterns to identify possible indicators of dementia. The patient’s recorded audio file is transferred into a photographic form and then compared to 400 variables of speech on the cloud.
So far, the company has claimed a high record of accuracy, ranging from 82 to 100 percent in detection.
3.2. Machine Image Analysis:
- How: Since of the hallmarks of Alzheimer’s disease is shrinkage of brain tissue, especially at the hippocampus region. With continuous improvement in computer vision, AI can assist doctors in ‘rinding’ MRI scan data and analyze the brain deterioration rate.
- Highlighted project: BRAINIQ is another the one that is striving to push forward the future of AI in healthcare. Stands as a collaborative project between Quantib, the Erasmus University Medical Centre, and Biomediq, BRAINIQ is trained to measure how the volume of the hippocampus and the overall texture of brain tissue changes as the disease advances, which help with detection and prognosis.
The software has been certified by the American FDA, received a European CE mark and is already installed on MRI scanners made by GE Healthcare.
3.3. Visual Indicators:
- How: Keith Rayner, an awarded cognitive psychologist, had established a field of study regarding how eye movement can paint a picture of how well the brain is working. Using that theory as the foundation, computer vision – a sector of AI – can assess eye movement patterns to track brain activity and then, measure the level of cognitive function.
- Highlighted project: NeuroTrack, a 6-year-old American company, has established a 5 minutes memory test that uses a computer vision algorithm to track the speed, direction, and pattern of eye movements through the client’s computer webcam. From that, it generates a baseline score – indicating the current memory strength.
It is reported that the company just landed a $13.7 millions funding package in March 2018.
3.4. Genetic Analysis:
- How: DNA play a non-decisive but influential role in measuring a patient risk of having Alzheimer. To be specific, there is a range of genetic mutations or gene variants that crank up the amount of amyloid beta that one’s body produces, such as APOE4. With the power of Big Data and machine learning on its side, AI can create an inclusive genetic database from a large population, detect patterns and predict the onset of Alzheimer.
- Highlighted project: Aequa Sciences, a part of the University Cambridge network, claims to use machine learning and artificial neural network to forecast the Alzheimer’s starting point. The company’s database consists of both healthy individual and those affected by Alzheimer. Through that, the machine learning algorithms are trained to recognize patterns and potential indicators of the disease, thereby organize the patients into distinct categories with quantified risk level and personal consultation.So far, the company is currently seeking collaborative partners through its Cambridge network. The most recent one is with Shuguang Hospital in Shanghai.
After decades of research, not much is known about Alzheimer. But early diagnosis means more data, more data means better research, and better research means we are one step closer to the cure. So far, Artificial Intelligence and its ability to connect the dots appears to be vital in predicting Alzheimer, long before it is obvious to the patient and their family.
Future of AI in Healthcare is bright. Hence, healthcare institutions need to catch up with this first wave of AI development, not only to remain sustainable and profitable but to ensure that they are doing their parts in the making of needed medical progression. It is not an easy task, and that’s why we are here help.
Striving to be a key software developer for the healthcare industry worldwide, Savvycom founded a new AI Lab back in March 2018. Leading by Dr. Long Tran, our team have developed three AI applications (Visual Search, Object Identification, and AskFred – an AI Chatbot) and are now in the process of commercialization.
These technologies are developed with the hope that it will become the foundation of our future healthcare-related products. For example, while AskFred can be used as a very dedicated assistant to Alzheimer’s patient – providing answers even to the most basic and repetitive questions, object identification can help them process their surrounding environment – describe and identify the things that they might not familiar with in real time, 24/7.
If you have any request for further information regarding our service, please send us a quick email here.
For further enquiries, please do not hesitate to contact Savvycom at: