legacy

The legacy of artificial intelligence: changing rolesIntroduction International conference over past 30 years on artificial intelligence in medicine across Europe has been organized. Different themes were published and papers were presented. Invo de lotto and Mario Stefanelli organized a conference which was a 2 day conference on artificial intelligence in medicine in September 1985. There were 8 special issues which were having a extend version of the papers presented in AIME. Computer science and artificial intelligence technique were the points on which it main focus was. Papers which were presented in AIME conference were selected with different methods and solutions were proposed and further what are their effectiveness or leading healthcare problems. They deliberately focuses on journals and papers which were published in AIME conference and the future challenge were described and the opportunities in future which has to come.Till today, the digitalization effect in the medicine field has been relying to electronic health records. But in the coming next 5 years, there is going to be a huge transformation. Moore in his law predicted in 1965 that there would be double transistors in a chip happening every 2 years. Now if we look close to it today every 5 years there is doubling of the number of mobile devices connected to the internet which will approximately in 2020 leads to 50 billion. Sensors are a part of exponential growth of internet of things which are increasingly embedded into smart phones and wearables. Literature ReviewArtificial intelligence took its turn into healthcare with many roles and responsibilities which are to be imparted in the systems to make systems seamless and to improve the quality of care we are providing. It is acting as a game changer. The day it came into existence it transformed the lives of the people. Doctor’s roles are changing, nurses are more attentive and managers are not that stressful. All credits goes to artificial intelligence.Nursing staff and decision-makingNursing staff is known as the front line staff of clinical roles and responsibilities. It acts as a safeguard for patient safety. A nursing decision plays a key role in the determining health problems. In Taiwan, one nurse on average takes care of 7-12 patients in a day shift and 12-30 patients in a night shift. The nurse ratio is comparatively lower in Taiwan than in other developing countries. Due to this particular fact, nurses are stressed due to workload and quit their jobs. According to the previous research, the junior nurses quit more often than other professionals. The reason being lack of clinical experience, poor coordination and work overload. In the clinical healthcare process, the first stage includes assessment of patient’s vital signs along with major complaints and physical examination by nurses. Second stage is analysis of data for the nursing diagnosis. Third stage and fourth stage consists of the nursing care targets, scheduling and applying treatment methods. Finally, the providers evaluate the targets achieved and the problems resolved.Many of the nursing records revealed all the issues that nurses face. Medical tools and techniques are constantly evolving because patients develops unpredictable symptoms. Therefore, the ratio of nursing staff is declining and is not easy to improve nursing decisions and maintain accurate records for a particular time period. However, due to this poor judgement, and a shortening recording procedure and it endup making the remaining staff experience stress. This gave rise to decision support system which is a type of information system that helps the staff to make decisions by investing in databases and computation capability of AI. Artificial Intelligence technologyThe rise of field of informatics, over the recent years has become frequent in applications to nursing practices. The main goal of introducing the recording model is to enhance patient safety and to provide patient-centric care. As expected the model will develop data-based nursing information by the support of AI technology so as to help the nursing staff to establish a nursing guidance for different patients. Thus, the algorithm can be utilized in an effective way to enhance nursing practices for patient care and prioritizing work to lower the healthcare providers load. Majority of Artificial intelligence is based on exploring new things, study and design for machines and equipments which can stimulate human behaviors. At present, the most important model is back-propagation neutral network (BPN) wherein training data as an evidence is provided during the learning sessions to make sure that the load in network can be regularly adjusted within the learning process. As per the research outcomes, the application of BPNs could enhance the overall accuracy as well as consistency in determining the prioritize period of emergency department.The rise of devices achieved the capacity of digitalizing human beings with the use of wearable sensors to evaluate the physiologic metrics e.g. vital signs or relevant view of a person’s environment. Thus imaging to enhance the explanation of the anatomy and sequencing of genetic material. However, sequencing has not yet been used for possible indications in clinical practice which includes initial diagnosis of cancer management, matching treatment and doses with each individual’s profile. In contrast, US Smartphone using population (1 in 4 individuals) is already using activity tracking which have sensors. However, the use of sensors is not proven as durable, but it represents the important precedent for potential adoption. In the coming next 5 years, there’s a prediction that monitoring glucose levels and blood pressure continuously would be through the sensors. Similarly, most laboratory tests are likely to be obtained by individual by Smartphone kits. Thus, dataization of individual’s medical essence gives them a new array of challenges and new opportunities. Majority of the examinations made today by physicians could be replaced by data and algorithms. Hence, it is quite acceptable to have improvements in diagnostic accuracy giving rise to remote monitoring of the patients by the physicians. Whether for cancer, diabetes, or any other significant illness, the growth of new information system at the population level may increase the understanding and also enhance the management of the illness. At last, for any such transformation in the medical community, it is the greatest and the biggest challenge since the profession’s origin is alteration by pervasive embracement of technology.Methods Methods used in thirty years of artificial intelligence in medicine conference;•Both qualitative and quantitative methods are used.•Firstly themes used in conference and their occurence over a years are addressed and than a systematic data was collected from the same and than from that importance of topic and their impact over a period of time is measured.•secondly the different papers presented in AIME are takenAnd scientific process of arraigning things into groups is done in artificial intelligence,health informatics and computational biology.At the end we form the relativity of topics used in research and take their frequency occurrence and their trends by taking their frequency over the years.MethodsMethods used by artificial intelligence technology to support decision making in nursing.In research technique a process we have chosen is in which data mining and probability to forecast outcomes is variables are taken as predictions which will influence our outcomes. Following steps were taken:• From last year No. of patients hospitalized and of same medical specialty were measured.•Data to preliminary processing was done • On the basis of relevant literature and input variables factor affecting nursing diagnosis were identified and then investigated.•K subject clusters were form of group samples.• Prediction model was build and different models were used for comparison.Method used in digital medical tools and sensors is Moore’s law. It is not a physical neither a natural law but it is law based on observations and projections used in history.Result DESCRIPTIVE ANALYSISFor the 105 cases collected, most of the patients were males with an average age of 51 ± 2.53 years.Among the 11 functional health patterns, health perception, nutrition, activity, and sleep–rest were found to be statistically significant influencing factors. Among nursing diagnoses, acute pain, dis-comfort, and activity intolerance were most common. The average age of the 36 nursing staff members was 28.92 ± 4.02 years, and the average work experience was 5.95 ± 1.8 years. Half of the nurses were university educated and the other half were college educated. They all have good self-perception.EFFECTIVENESS OF ARTIFICIAL TECHNOLOGYWe selected only the first three targets generated by the BPN as our first choices in screening the problems of nursing diagnoses. When consolidating the 18 related factors that could affect the nursing diagnoses, we created a forecasting model of the BPN for the 123 sets of training data by using the Clementine software and then used 93 sets of patient data for testing purposes. After using Clementine to determine the accuracy of the aforementioned training data, we achieved an87.41 percent accuracy rate in predicting patients’ nursing diagnoses. This nursing information system can enhance the capability of nurses to provide accurate nursing diagnoses. We conducted a clinical test in one teaching hospital in northern Taipei by collecting54 medical records that were reviewed by senior nurses. The percentage of nursing diagnoses suggested by the information system that coincide with those made by the nursing staff over the total samples is as much as 87 percent. The percentage of the nursing diagnoses made by both the sys-tem and the nursing staff that are concurrently in the top three possible results over the 54 samples is 74 percent.The nursing information system could also improve the job satisfaction of nurses. Results showed that overall patient healthcare was improved, work satisfaction concerning nursing diagnoses was enhanced from 41.1 percent to 75 percent, and the time spent on decision-making was reduced from 35.5 to 19.8 minors of their computer operation skills. Conclusion We have seen in these paper they reviewed about 30 years of research in AI in medicine on the basis of research theme in AIME. After some decades data driven method come from shifting of knowledge based data driven method and assessment being done through this method. There are some research theme which are unchanged since 1990 some of them are uncertainty management, imagine and signal processing, natural processing. For future research there is some method which come in limelight few of them are big data, personalized medicine, evidence based medicine, business process modelling and process mining.The AI models helps nursing staff to derive deferent guidelines for similar disease symptoms and diagnoses. The Gordon’s 11 functional health patterns ware used to reduce unnecessary time and the chances of missing major points when completing records, enhance the accuracy of data disclosure however improve the quality and timeliness of responses to patients health issues and this method is done simply by using touch panels. One the common problem which researchers and IT person is facing is communication. So IT guy should design a common language software that results IT could enhance the accuracy of collecting and recording data.