While millions of diagnostic examinations are carried out annually, chest X-rays play a vital role in diagnosing several diseases. But the usefulness of the same can be limited due to the challenges in interpretation that need thorough and rapid evaluation of 2D image depicting complex, 3D organs, and disease processes. Sometimes, major details can be missed by chest X-rays resulting in adverse outcomes for patients.

Recent efforts have improved lung cancer detection in radiology, differential diagnosis in dermatology, and prostate cancer grading in pathology. And, obtaining accurate clinical labels for the deep learning models for X-ray interpretation.

Most efforts have applied rule-based natural language processing to radiology reports or based on image review by readers. Eventually, both might introduce inconsistencies, that can be problematic at the time of model evaluation.

Deep learning models to resolve challenges!

In an effort to resolve this, researchers at Google devised Artificial Intelligence models to spot four findings on human chest X-rays. Advances in machine learning present an opportunity to create new tools to help experts interpret medical images. In the journal Radiology, the deep learning models for chest radiograph were published.

The team developed deep learning models for four important clinical finds such as pneumothorax (collapsed lungs), nodules, and masses, airspace opacities (filling of the pulmonary tree with material), and fractures. These were chosen in consultation with clinical colleagues and radiologists to focus on conditions that are critical for patient care.

These deep learning models were evaluated using several thousands of held out images from the dataset for which the high-quality labels have been collected using a panel-based adjudication process among radialogists who are certified by the board. Later, the held-out images have been reviewed independently by separate radiologists to make sure these are accurate.

The team leveraged more than 600,000 images sourced from two de-identified datasets. The first one was developed along with co-authors at the Apollo Hospitals and has a diverse set of chest X-rays gathered over several years from the hospital network across locations. The second one has been released publicly by the National Institutes of Health and served as a vital resource for machine learning efforts. But the same has limitations related to accuracy and clinical interpretation of available labels.

High-quality reference standard labels

In order to generate high-quality reference standard labels for model evaluation, the team has used a panel-based adjudication process. In this process, three radiologists reviewed the final tune and test set images and addressed disagreements via discussion. It let difficult findings that were only detected by a single radiologist to be detected and documented. Later, the discussions took place anonymously via an adjudication or online discussion system.

Google notes that while the models achieved an overall expert-level accuracy, the performance varied based on the corpora. For instance, the sensitivity to detect penumothorax among radiologists was nearly 79% for ChestX-ray14 images and just 52% for the same radiologists in other datasets.

The team hopes to lay the groundwork for exceptional methods with a corpus of the adjudicated labels for the ChestX-ray14 dataset that they have made available in open source. This comprises 2,412 training and validation set images and 1,962 test set images or 4,372 images in total.

The post Google’s AI team classifies chest X-rays with superior levels of accuracy appeared first on Artificial Intelligence.

Every year, around 50,000 individuals graduate to become certified doctors. In order to maintain the minimum doctor-patient ratio, as suggested by WHO, India will need 2.3 Mn doctors by 2030. If there was ever a requirement to push healthcare in India into the future, it is now! Today is the time when we can see significant disruption in the Indian healthcare industry. Much of this is credited to the level of involvement of artificial intelligence, big data, cloud, machine learning and deep learning, and wearables or fitness trackers which are connecting the organizations with the individuals.

To start with, Artificial Intelligence or AI as we call it has the potential to transform the diagnosis and cure of multiple diseases which were considered incurable a decade ago. Artificial intelligence in Indian healthcare industry rely on a paradigm shift in the way the machines read electronic data of patients, including their age, medical history, tests, medical images, DNA sequences, and other factors to fuel treatment.

Dr. Eric Topol in his book, Deep Medicine, has sited organisations and their role in developing tools to analyse health conditions. One such tool that Google has developed can precisely detect diabetes relatively accurate. The software has a sensitivity score of 87-90% and an accuracy of 98% while detecting diabetic retinopathy.

A team of advanced doctors in London have come up with a treatment approach for more than 50 eye diseases having 94% accuracy. To understand the level of precision, their results were compared to that of international eye specialists. As per the reports of this experiment, the doctors missed a dew reference points but the machine didn’t, any.

In China, on the other hand, Artificial Intelligence is being used to diagnose the presence polyps on the colon during a colonoscopy. When the diagnosis of a gastroenterologist was compared to that of a machine, the latter had 9% more chances of early detection. The beauty of this experiment was that the machine didn’t miss the tiny polyps, even the ones with a size less than 5mm which were otherwise easier for the doctors to miss.

Our mobile phones are not only performing functions they were designed for but also collecting our digital footprints and analysing our behavior on screen. Not just the obvious audio snooping, even our eye-tracking data collected while we freely watch TV can determine neurodegenerative eye diseases, as cited in an article by Artificial Intelligence in Medicine (2018) Journal.

In India, young startups are coming together to help doctors diagnose chronic diseases at an early stage. With the help of predictive analytics and machine learning, these startups are creating diagnostic tools that could help specialists diagnose faster and more accurately. A medical wearable startup, ten3T, has developed medical-grade wearable devices attached with a Cicer (device embedded with multiple sensors) to help monitor patient’s health, even at home. mFine, Bengaluru based healthcare startup has close to 1200 diseases in the system to give 85% of accurate diagnosis.

AI does the hard work of compiling the complex identification trigger points and creating a pattern out of this data on an intensity level and speed beyond any human being’s capability. AI has the capacity to take charge of rural areas with a mobile device, without having the doctors to travel from village to village. Evidently, artificial intelligence and deep learning are the hope of new-age technology, which if correctly harnessed, can help doctors and scientists make better decisions in growing Indian healthcare industry further.

The post Incorporating Artificial Intelligence In Indian Healthcare Sector appeared first on Artificial Intelligence.