Managing information and knowledge within maternity services: Privacy and consent issues.

OBJECTIVE: Electronic Patient Records have improved vastly the quality and efficiency of care delivered. However, the formation of single demographic database and the ease of electronic information sharing give rise to many concerns including issues of consent, by whom and how data are accessed and used. This paper examines the organizational and socio-technical issues related to privacy, confidentiality and security when employing electronic records within a maternity service hospital in England. METHODS: A preliminary questionnaire was administered (n = 52), in total, 24 responses were received. Sixteen responses were from personnel in the information technology department, 5 from health information department and 3 from midwifery managers. This was followed by a semi-structured interview with representatives from the clinical and technological side. RESULTS: A number of issues related to information governance (IG) have been identified, especially breaches on sharing personal information without consent from the patients have been identified as one immediate challenge that needs to be fixed. CONCLUSION: There is an immediate need for more robust, realistic, built-in accountability both locally and nationally on data sharing. A culture of ownership and strict adherence to IG principles is paramount. Focused training in the area of data, information and knowledge sharing will bring in a balance of legitimate usage against the individual's rights to confidentiality and privacy.

Predicting breast screening attendance using machine learning techniques.

Machine learning-based prediction has been effectively applied for many healthcare applications. Predicting breast screening attendance using machine learning (prior to the actual mammogram) is a new field. This paper presents new predictor attributes for such an algorithm. It describes a new hybrid algorithm that relies on back-propagation and radial basis function-based neural networks for prediction. The algorithm has been developed in an open source-based environment. The algorithm was tested on a 13-year dataset (1995-2008). This paper compares the algorithm and validates its accuracy and efficiency with different platforms. Nearly 80% accuracy and 88% positive predictive value and sensitivity were recorded for the algorithm. The results were encouraging; 40-50% of negative predictive value and specificity warrant further work. Preliminary results were promising and provided ample amount of reasons for testing the algorithm on a larger scale.

Improving uptake of a breast screening programme: A knowledge management approach for opportunistic intervention.

Reducing mortality from breast cancer through screening has been accepted as a viable tool and breast screening has attracted a lot of attention from healthcare organisations worldwide. Government funded screening programmes in Europe, the Americas and Australia have made good progress in diagnosing and treating breast cancer through effective screening programmes. The UK's National Health Service (NHS) National Screening Programme manages one of the biggest publicly funded breast screening programmes. In the UK, only 75% of the intended population is screened and a diverse set of efforts has attempted to identify and initiate countermeasures to improve screening attendance. This paper identifies how innovative use of information and communication technologies (ICTs) can be the focus for strategising not only improved screening attendance but also better quality of care for women.

Knowledge creation using artificial intelligence: a twin approach to improve breast screening attendance.

Knowledge management (KM) is rapidly becoming established as a core organizational element within the healthcare industry to assist in the delivery of better patient care. KM is a cyclical process which typically starts with knowledge creation (KC), progresses to knowledge sharing, knowledge accessibility and eventually results in new KC (in the same or a related domain). KC plays a significant role in KM as it creates the necessary "seeds" for propagating many more knowledge cycles. This paper addresses the potential of KC in the context of the UK's National Health Service (NHS) breast screening service. KC can be automated to a greater extent by embedding processes within an artificial intelligence (AI) based environment. The UK breast screening service is concerned about non-attendance and this paper discusses issues pertaining to increasing attendance.