A style that evolved out of Artificial Intelligence is Artificial Neural networks (ANN), often interchangeably known as Neural Networks. It is just a mathematical or computational model that processes interconnected data (artificial neurons) to discover a pattern in that data. In this process you’ve input data, that goes by way of a connectionist method of output data. The machine adapts and learns through the large number of data that flows through it. The effect is a professional decision making, as well as predicting system, with a near 100% accuracy. Small wonder, clinicians have been using AI and expert systems to provide better and timely healthcare with their patients.
In a study during the late 1990s, researchers Lars Edenbrandt, M.D, Ph.D., and Bo Heden, MD., Ph.D., of the University Hospital, Lund, Sweden, ventured to add 1,120 ECG records of Heart Attack patients, and 10,452 records of normal patients. The neural networks were found to be able to utilize this input data, and begin a relationship and pattern. This leaning phase was internalized by the system, and started identifying patients with abnormal ECGs with a 10% better accuracy than most clinicians/cardiologists on staff.
Speaking of other factors in determining Heart Attacks, an interesting research work had been published in a scientific journal from the Inderscience group, the International Journal of Knowledge Engineering and Soft Data Paradigms (IJKESDP) beneath the name “A computational algorithm for the chance assessment of developing acute coronary syndromes, using online analytical process methodology” (Volume 1, Issue 1, Pages 85-99, 2009). Four Greek researchers had ventured to produce a computational algorithm that evolved out of a far more current technique, namely Online Analytical Processing (OLAP). They used this methodology to construct the foundations of a “Heart Attack Calculator” ;.The main advantage of OLAP is so it supplies a multidimensional view of data, which allows patterns to discerned really large dataset, that could have been otherwise remained invincible. It takes under consideration numerous factors and dimensions, while making an analysis. The research team obtained data from about 1000 patients which have been hospitalized because of apparent symptoms of Acute Coronary Syndrome. This data included details on their family history, physical activities, body mass index, blood pressure, cholesterol, and diabetes level. This is then matched to some other group of similar multi dimensional data from several healthy individuals. All of this data were used as inputs to the OLAP process, to explore the role of the factors in assessing cardiovascular disease risk. best heart hospital in hyderabad At various levels of the factors, intelligence could possibly be gathered to be utilized as a combination of dimensions, for future diagnosis of the extent of risk.
The ANN is more a “teachable software”, that absorbs and learns from data input. When properly computed, even at an easy pace with a tried and tested algorithm, it develops patterns within the input data, or a combination of multiple data dimensions or factors, to which a given situation could be compared to, and a prognosis declared.
In 2009, some researchers in Mayo Clinic studied 189 patients with device related Endocarditis diagnosed between 1991 and 2003. Endocartitis is disease concerning the valves and at times the chambers of the heart, which can be often caused because of implanted devices in the heart. The mortality of because of the infection could possibly be as high as 60%. The diagnosis of this infection required transesophageal echocardiography, which will be an invasive procedure involving the usage of an endoscope and insertion of a probe down the esophagus. Naturally, this was a risky, uncomfortably and expensive procedure. The researchers at Mayo, fed the info from these 189 patients int the ANN, and had it undergo three separate “trainings” to master to gauge these symptoms. Upon being tested with various sample populations (only known cases, and then the overall sample of a combination of both known and unknown cases), the most effective trained ANN was able to identify Endocarditis cases very effectively, thus eliminating the requirement for this invasive procedure.
With present day e-health becoming more and more data centric, access to relevant patient data is gradually becoming extremely convenient. AI and Expert systems with its ANN and computational algorithms, has tremendous opportunities to increase diagnosis, and effect patient care with speed and more and more accuracy. As AI advances, it is going to be interesting to observe it marks its footprints in Cardiovascular, Neuro, Pulmonary, and Oncology diagnosis and care.