What is A.I. ? Will A.I. take over the world? Why should it matter to me? These are the few questions that will pop up in every curious mind out there who listens to the term Artificial Intelligence, commonly known as AI. Well, if we go by the book, the definition of AI seems boring and often discourages the reader to delve further into the topic so today we will try to understand the basics of AI lucidly and effectively i.e. using a case study.
The simplest definition of AI which can be given without losing its essence is:
Artificial intelligence is the process of TEACHING the machine and the machine becoming SMART.
Our case study begins in a small town in southern India named Madurai. Ms Shanthi, 63 lives there with her family. For the past year, she has been constantly complaining about her Eyesight. She says that she is not able to see things clearly.
She lives in a rural area where getting access to a doctor is not an easy task. One has to take the day off from fields, travel to the city on a train or city, get to the primary healthcare centre and wait. She gets her appointment there and is suspected of Diabetic retinopathy but to confirm this suspicion She is referred to an ophthalmologist. As per official statistics, there are about 18,000 ophthalmologists in the country, the no. may sound convincing but the harsh truth is, it’s not. With such a large population, there are only 11 ophthalmologists per Million persons in India. So she has to wait. This wait could be anywhere between 2 days or 2 months, nobody knows.
Meanwhile, let us discuss Diabetic retinopathy. It’s a dangerous but preventable disease, caused by damage to the blood vessels in the tissue at the back of the eye (retina). If went undiagnosed it could lead to irreversible blindness and the only form of treatment available for this is early detection and surgery.
But how will this be possible when there are only 11 ophthalmologists per million patients in India?
This is where Artificial Intelligence comes to the rescue.
Remember those colourfully-lit weighing machines on railway platforms that would take a coin and give out a small cardboard ticket with the person’s weight and fortune? The Chief Medical Officer at Madurai’s Aravind Eye Hospital (AEH), Dr Ramasamy Kim, uses this analogy to explain how people could get a preliminary eye check-up done instead of visiting an ophthalmologist in the future.
“In one look, the machine will predict the condition of the retina and advise on the next step of action in seconds,” he says. All thanks to artificial intelligence (AI) in ophthalmology. He has been working on the technology with Google since 2013.
“The impact,” he says, “will be seen in patient care and diabetes management.” He imagines a scenario where the scope of algorithms on smartphones will not require the consumer to even go near a machine. “People can take selfies of the eye on their phone cameras and have instant access to ophthalmic care.”
But how is the AI involved?
Step 1: Collecting and analysing the Data
Dr Kim has spent the last four years working on 10,000 retinal images, drawing every lesion, distinctive spots, bleeding in the retina due to diabetes that could occur in various permutations and combinations, to help Google develop the algorithm that would recognise the signs of the disease early.
Google has created a database of 1,28,000 images from different sight centres around the globe, including two more in India — Sankara Nethralaya in Chennai and Narayana Nethralaya in Bengaluru.
Step 2: Creating An Algorithm
“If the captured image of the eye shows negative for DR, then the person will be advised to rescreen after 12 months. And in case of a positive result, the person would be asked to see an ophthalmologist for further evaluation and immediate treatment,” explains Dr Kim.
Step 3: Machine Learning
Now the machine works on the created algorithm and decides if the person has Diabetic retinopathy or not and it’s all done by the machine so here are we teaching a machine and machine becoming smart. Now the machine can work automatically without any human assistance.
Step 4: Deep Learning
Based on the images which have been collected now the machine also tries to recognise patterns and predict other ailments besides Diabetic retinopathy by collecting more data and start analysing and relating patterns. Google has already débuted an algorithm to 97% accuracy that can identify a person’s age, sex, ethnicity and smoking status and predict the five-year risk of a heart attack, all based on retinal imagery. The AI for DR is 87% sensitive and 90% specific for detecting more than mild diabetic retinopathy.
“The AI will throw up huge numbers and accurately spot the vision status and detect multiple problems or vision-killing conditions. It only means I will get many more patients to treat and reduce the several rounds of redundant tests.” Says Dr Kim.
By studying this case study I hope that these 3 terms namely Artificial Intelligence, Deep Learning and Machine learning are now clear to the reader.
When a person can avoid hospital visits up to the stage of detection of DR, it may appear healthcare is lending itself to the risk of machine calculations instead of relying on human knowledge and experience. But Dr Kim argues in favour of using technology effectively and efficiently in times when computers are available everywhere and to everybody but healthcare is not.
From June this year, Aravind Hospital started supplementing its DR grading process with the Google AI “The results are accurate,” says Dr Kim, who is now working on 60,000 retinal images for matching the grading results from the machine and the human eye to fine-tune the algorithm.
.
Though the challenge of a machine may lie in any false-negative and deprive a patient of consultation, Dr Kim says AI is superior to anything that he has seen in DR screening. “The machine can see something beyond the human eye,” he says, “and as a doctor, my only interest is in getting a greater number of patients at an early detected stage for successful treatment.”
“Collaboration is how everyone, every species here gets to advance. We generally say 1 and 1 makes 11 But here we are collaborating a machine that has the power to revolutionise the whole world ”
A.I is not here to Replace Humans. It’s here to enhance us! But the single most important question which we have to ask ourselves is ‘How ready are we to embrace it ?’
Innovators Quest VIT 