On last July 7th, in APTOS 2018 Singapore, Dr. Rim gave a presentation about his research, “Retinal Damage as the Window to Cardiovascular Organ Damage: Use of Big Data & Machine Learning”.
Dr. Rim, one of the co-founders of Medi-Whale Inc., is engaged in Yonsei University College of Medicine as a professor and ophthalmologist in Severance Hospital.
As a professional ophthalmologist, he suggested his idea that a retina is a window to investigate the association between microcirculation abnormalities and cardiovascular diseases.
However, among the researchers already studying the relationship between cardiovascular diseases and eye vessels, Dr. Rim focused on the question: What is the most important marker in cardiology?
He and Medi-Whale Inc. attempted to evaluate the association between retinal image and coronary artery calcium score using deep learning, as it can analyze and catch distinctive features of individual retinal fundus images and heart CT.
While processing this research, Dr. Rim used big data from Korea National Health Insurance Service (KNHIS) and stored a huge amount of data to enhance the accuracy of predicting cardiovascular risk factors.
Additionally, Dr. Rim mentioned deep convolutional network architectures, which can enhance the learning ability and reduce error rates between official results and research results.
Medi-Whale Co. sponsored the 3RD Asia Pacific Tele-Ophthalmology Symposium (APTOS) held in Singapore. In their exhibition booth the ‘Dr. Noon’, Medi-Whale’s product, was displayed on July 7-8, 2018.
APTOS was founded by tele-ophthalmologists in Asia-Pacific region in May 2016, aggregating professional researchers, technicians, and clinicians to share, collaborate, exchange individual perspectives, knowledge or ideas.
Along with Medi-Whale, Zeiss, Topcon, Novartis, and Alcon also sponsored APTOS 2018 and introduced technology which can precisely diagnose patient’s eye diseases.
At APTOS 2018, Medi-Whale opened a booth to introduce ‘Dr. Noon’, a deep learning based retinal fundus screening program, specially attracting companies from India, Philippine, and middle-east Asia.
By using red and green colored dots, this program will identify if a patient’s eye will contain glaucoma, opacity, or retina diseases that can be frequently triggered from elder or diabetes.
As Dr. Noon can assist basic eye examination for elderly and diabetic patients, by analyzing retinal fundus images, physicians are now expected to be able to decide if patients need further diagnosis from ophthalmologists or not.
Dr. Noon is expected to assist internal clinics to provide better service for patients, especially for those in area which professional ophthalmologists are not localized.
Medi-Whale is now planning to develop a program that predicts cardiovascular diseases via analyzing retinal fundus images.
In terms of heart diseases, researchers from Asan hospital, Seoul represented AI which can concisely predict ventricular tachycardia before 1 hour from when it strokes.
This increased the viability of patients from heart attack but required the human effort to set an artificial neural network which was based on specific feature.
Furthermore, researchers from Vuno institution, developed DeepEWS, which used RNN (Recurrent Neural Network) deep learning system to learn 7 types of information from individual patient.
RNN was used for this system as researchers wanted to predict heart disease before 24 hours and concentrate on data variance and reducing false warning alert.
Similarly, Cardiogram applied deep learning to the heartbeat sensor in wearable device to identify atrial fibrillation and atrial flutter as heartbeat’s distinctive rhythm was able to recognize some irregular pulse.
Irregular pulse specificity of wearable device was evaluated with two criteria (Sequence F1- figure out arrhythmia on proper time, Set F1- detect arrhythmia from whole data).
As a result, deep learning was showing much higher specificity with both sequence F1 and set F1 when it compared to cardiologist.
This research identified that AI could easily classify two types of atrioventricular block which most professional cardiologists were having difficulty to identify.
If data aggregation (electrocardiogram, heartbeat rate…etc), analyzing, and classifying can be constantly processed through wearable device or apple watch, predicting heart diseases with high accuracy will be developed.
In these days, breath, temperature, heartbeat rate, blood sugar level, and other human body signals can be analyzed by AI and consequently indicate or predict our health status and diseases.
Sepsis, a common deceasing factor of patients, is the best example which can be accurately recognized by varied temperature, blood pressure drop, reaction reduction, and raised breath rate.
According to researchers from University of Ontario Institute of Technology, premature infants who are about to be subjected to sepsis displayed the reduction of heart rate variability.
In terms of intensive care patients, TREWScore (Targeted Real-Time Early Warning Score) was developed with EHR big data and this allowed predicting sepsis shock about 28.2 hours earlier.
Additionally, Medtronic and IBM Watson displayed an AI, Sugar IQ, which allowed diabetic patients to constantly manage and predict their blood sugar level.
Sugar IQ suggests insight to control blood sugar level after when it analyze every monitored blood sugar and insulin level variance.
It makes patients to improve their good habit by providing proper information for individuals after when all of informative patterns are identified.
Although medical data is complicated, it can be analyzed and display new insight through AI. This can predict future disease attack and decrease readmission rate or reduce medical expense.
The guideline derived from ACC/AHA, is not a perfect model to predict disease as it does not include any individual’s life style, habits, or risk factors.
As AI can display risk factors of disease without any prejudice or preoccupation, it allows more accurate results than previous standard guideline.
Researchers from Nottingham University, England, identified that analyzed data via artificial intelligence included ethnicity, mental disorder, and oral corticosteroid as a critical risk factor while previous model included diabetes.
When AI, big data, and deep learning are combined together, it will more accurately display result rather than human as people are having limitation of concisely analyzing data.
In our past medical society, some researchers expected AI will replace professional physicians as it is based on big data and derive more accurate results than human without any bias.
Machine learning, which learns data via math equations and setting rules like a human, is commonly used in filtering spam mails, face and voice recognition in our presented society.
Since AI is still developing on broad area and playing critical roles much faster and clearer than human, unemployment is becoming a serious issue.
Furthermore, deep learning has been developed since 2010 by using artificial neural network. It is similar to human brain as several layers and different algorithms can process learning in depth.
As an amount of high quality data has been increased and accumulated in medical field, deep learning became compatible with medical field.
Artificial intelligence can be classified to three types (narrow, general, super) and all of these are focused on solving problem which humans are having difficulty.
When general AI is compared to narrow AI, general AI can think and analyze information or data like human can do.
Moreover, super AI is not clearly developed yet but it will become available to develop itself even more than human can develop with their brain. This is the reason why super AI is controversial in our society.
In our presented medical society, professional physicians and researchers are more focused on developing pattern recognition, memorizing, and classifying knowledge of AI.
Best way for us to develop AI is combining with human ability and deriving new profit. If people can regulate and apply rules to AI in medical field, AI application can effectively work.
Medi Whale Co. signed a side agreement of ‘Dr. Noon’ demonstration agreement with Khanty-Mansiysk Hospital (Russia).
Last December of 2017, Medi Whale have signed an agreement with Khanty-Mansiysk District for appliance of AI eye examination software based on deep learning artificial intelligence. The agreement of this December is a side agreement of the previous agreement, in which included the demonstration of ‘Dr. Noon’ in Khanty-Mansiysk District Hospital. In this new side agreement, Ugra Institution of Information Technology (URIIT) is also involved for cooperation for technical implementation.
Kyanty-Mansiysk Hospital agreed to provide 1,000 patient samples in minimum following the agreement. Medi Whale is planning to ensure the reliability of the product by comparing the diagnosis result from Khanty-Mansiysk Hospital and the result diagnosed by this ‘Dr. Noon’. his demonstration the first time for Korean AI eye examination product to be presented abroad. CEO Kevin Choi said ‘We are planning to expand the market of AI examination from domestic level to global level’.
Google displayed the AI technology which can predict individual patient’s medical treatment results by analyzing their electronic health record (EHR) through deep learning system.
It was difficult to analyze EHR as several complicated data such as the quantity of patients, different type of diseases, prescriptions, and surgical operations are presented.
Moreover, since some data is not being presented in EHR, limitations are still remaining in usage of deep learning process.
To solve this problem, professional physician needed to select critical cases from whole EHR database to increase specificity of prediction model until deep learning process developed.
As deep learning learned the whole data of EHR and identified the important source by itself, it allowed physicians to predict patient’s health status while processing or after medical treatment and presented the diagnostic name when patients discharged from hospital.
Deep learning was able to recognize the important source of whole EHR data, and this led researchers to find out that AI regarded impatient mortality as the first critical factor.
It also “scale up” the prediction model as deep learning could emit every process such as preparing and adding supplemental academic data.
An AI technology which Google has been presented is very efficient to predict and prevent patient’s risk as deep learning can analyze complex medical data and provide prospective results.
Medi Whale and its product, Dr. Noon, was introduced to media by the Korea Economic Daily. The article is based on interview of Choi, the CEO of Medi Whale. Choi said that their program Dr. Noon can “diagnose disease risk of cardiovascular, macular, and optic nerve with 95% reliability by analyzing the fundus image”.
The article introduces that Choi started the company with an ophthalmology doctor of Yonsei college of medicine. As it says, Medi Whale has collected 0.1million fundus images for AI training and made a technology agreement with Yonsei college of Medicine.
Dr. Noon is useful for diabetic patients, according to the article. Diabetic retinopathy, which is one of the most popular complication of diabetics, can lead patient to blindness if the patient do not go through regular eye examination. Medi whale is on its way starting the clinical trials next month for medical use approval.
Medi Whale is also working on a AI diagnosis supporting program for cardiovascular disease examination. Choi said that by fundus image examination, previous cardiovascular disease examination CT can be replaced with cost decrease from USD 500~600 to USD 10.
Link to the full article as below.
Along with the study of evaluating diabetic retinopathy by applying deep learning to retinal fundus image, predicting cardiovascular risk factor also became focused in medical field.
As identified retinal fundus images can display distinctive features of optic disc or blood vessels, correlation between heart diseases and retinal disease, it allowed to predict the cardiovascular risk factors via deep learning.
Other parameters like age, gender, blood pressure, body mass index, glucose, and cholesterol levels can critically impact different phenotype of retinal images and suggest additional signals of the risk.
Every additional signals can be rapidly derived from various retinal images via spending cheap price (Very Efficient).
Ophthalmologists used the methods of highlighting different anatomical location of retinal by markers to identify and predict the risk factors. Blood vessels were highlighted to predict risk factors such as age, smoking, and SBP.
To predict HbA1c, perivascular surroundings were highlighted, and for gender prediction, optic disc was primarily highlighted.
For other predictions, such as diastolic blood pressure and BMI, the circular border of the image was highlighted and suggested that the signals will be distributed more throughout the image.