As we can see heart patients are increasing day by day due to unhealthy eating habits and bad lifestyle. Situation becomes worse with increasing time if any precaution or medication is not taken regularly. This happens because people don't realise on time that they have diseased heart and even all manual practices are also not so much accurate which can accurately detect and diagnose the illness.
So keeping this in mind, we have developed IoT based devices which can check patient vitals such as heartbeat, pulse, temperature, ecg, haemoglobin and much more.
Based to the input provided to the device, it will send this input data to our server where our machine learning model will check whether patient is fit or not.
If patient vitals are above or below normal it will inform his doctor so that doctor can personally check his/her vital and assure everything is ok or not.
Consumer wearables and other medical devices equipped with AI technology is already being applied to oversee early - stage heart disease which enables doctors to better monitor and detect life - threatening diseases at earlier stage as well as more treatable stages.
Apart from scanning health records to help providers identify chronically ill individuals who may be at a risk of an adverse stage, AI can help doctors, clinicians take a more comprehensive approach for disease management, better care plans and help patients to better manage with their long-term treatment programmes.
Based on World Health organisation report blind people due to cataracts are about 20 million and will exceed 40 million by 2025. AI has astounding potential to perform much better than human beings such as in image recognition field.
Patients suffering from eye diseases are expected to increase steeply. Early detection and appropriate treatment of eye diseases should be done to prevent vision loss and promote living quality.
For the above problem we have created a software model which uses AI & Machine Learning algorithms to detect which level of cataract a person has and which cases should be referred for further investigation with just a single click of an image.
A computer-aided transfer learning-based automatic cataract detection method is proposed.
Automatic classification is done via pre-trained CNN for deep transfer learning.
The proposed method outperforms with the existing methods in evaluating the cataract.
This method also eliminates the burden of training a CNN from scratch.