Johan Gustav Bellika

Techniques have been developed to compute statistics on distributed datasets without revealing private information except the statistical results. However, duplicate records in a distributed dataset may lead to incorrect statistical results. Therefore, to increase the accuracy of the statistical analysis of a distributed dataset, secure deduplication is an important preprocessing step. We designed a secure protocol for the deduplication of horizontally partitioned datasets with deterministic record linkage algorithms. We provided a formal security analysis of the protocol in the presence of semi-honest adversaries. The protocol was implemented and deployed across three microbiology laboratories located in Norway, and we ran experiments on the datasets in which the number of records for each laboratory varied. Experiments were also performed on simulated microbiology datasets and data custodians connected through a local area network. The security analysis demonstrated that the protocol protects the privacy of individuals and data custodians under a semi-honest adversarial model. More precisely, the protocol remains secure with the collusion of up to N − 2 corrupt data custodians. The total runtime for the protocol scales linearly with the addition of data custodians and records. One million simulated records distributed across 20 data custodians were deduplicated within 45 s. The experimental results showed that the protocol is more efficient and scalable than previous protocols for the same problem. The proposed deduplication protocol is efficient and scalable for practical uses while protecting the privacy of patients and data custodians.

We present a novel approach to the design of video conferencing (VC) systems, taking advantage of recent technological achievements in web-based implementation. Delivering VC functionality as a service over the Internet opens new grounds for easier integration, support, and application in many scenarios, since hardware-agnostic ad-hoc VC connections are a feature of the proposed architecture. Validity is demonstrated through latency measures in surgical telementoring service and comparing them to reported thresholds.

Systems for large-scale reuse of electronic health record data is claimed to have the potential to transform the current health care delivery system. In principle three alternative solutions for reuse exist: centralized, data warehouse, and decentralized solutions. This chapter focuses on the decentralized system alternative. Decentralized systems may be categorized into approaches that move data to enable computations or move computations to the where data is located to enable computations. We describe a system that moves computations to where the data is located. Only this kind of decentralized solution has the capabilities to become ideal systems for reuse as the decentralized alternative enables computation and reuse of electronic health record data without moving or exposing the information to outsiders. This chapter describes the Snow system, which is a decentralized medical data processing system, its components and how it has been used. It also describes the requirements this kind of systems need to support to become sustainable and successful in recruiting voluntary participation from health institutions.

Even after a decade of increased research into the problem of detecting disease outbreaks, we lack a system that can limit the number of patients affected by a potential epidemic by recognising its existence at an early stage. In this paper we suggest the use of a weighted graph representing symptoms with an exceptionally high prevalence. Cliques with high weighted edges in such a graph will represent groups of symptoms that occur together more often than usual. As a result each clique will represent the main symptoms of a disease with a high incidence rate. This will make it easier to diagnose the nature of an outbreak, to reach the affected patients at an early stage and to distinguish between outbreaks occurring simultaneously.

Diabetics are quite susceptible to infectious diseases and can easily spread them under certain circumstances. Their blood glucose levels are increased after infection and this can cause a hyperglycemic crisis. Our study indicates that this increase results in glucosylated hemoglobin elevation, even when a diabetic is monitored closely and his/her blood glucose is under tight control. Thus, it is important to detect infections at the very early stages of disease progression in order to aid the patient. For this purpose, an electronic Disease Surveillance System could be developed to collect and analyze blood glucose data. Generally, we could extend the use of blood glucose data to the implementation of disease surveillance systems for the general population.

The Norwegian Centre for Telemedicine (NST) has, over the past two decades, contributed to the development and implementation of telemedicine and ehealth services in Norway. From 2002, NST has been a WHO Collaboration Center for telemedicine. In August 1996, Norway became the first country to implement an official telemedicine fee schedule making telemedicine services reimbursable by the national health insurer. Telemedicine is widely used in Northern Norway. Since the late 1980's, the University Hospital of North-Norway has experience in the following areas: teleradiology, telepathology, teledermatology, teleotorhinolaryngology (remote endoscopy), remote gastroscopy, tele-echocardiography, remote transmission of ECGs, telepsychiatry, teleophthalmology, teledialysis, teleemergency medicine, teleoncology, telecare, telegeriatric, teledentistry, maritime telemedicine, referrals and discharge letters, electronic delivery of laboratory results and distant teaching for healthcare personnel and patients. Based on the result achieved, the health authority in North-Norway plans to implement several large-scale telemedicine services: Teleradiology (incl. solutions for neurosurgery, orthopedic, different kinds of surgery, nuclear medicine, acute traumatic and oncology), digital communication and integration of patient data, and distant education. In addition, the following services will also be considered for large-scale implementation: teledialysis, prehospital thrombolysis, telepsychiatry, teledermatology. Last in line for implementation are: pediatric, district medical center (DMS), teleophthalmology and ear-nose-throat (ENT).

An infected person may be contagious already before the first symptoms appear. This person can, in the period of disease evolution, infect several associated citizens before consulting a general practitioner (GP). Early detection of contagion is therefore important to prevent spreading of diseases. The Automatic Infection Detection (AID) System faces this problem through investigating the hypothesis that the blood glucose (BG) level increases when a person is infected. The first objective of the prototyped version of the AID system was to identify possible BG elevations in the incubation time that could be related to the spread of infectious diseases. To do this, we monitored two groups of people, with and without diabetes mellitus. The AID system analyzed the results and we were able to detect two cases of infection during the study period. The time of detection occurred simultaneous or near the time of onset of symptoms. The detection did not occur earlier for a number of reasons. The most likely one is that the evolution process of an infectious disease is both complicated and involves the immune system and several organs in the body. The investigation with regard to isolating the key relations is therefore considered as a very complex study. Nevertheless, the AID system managed to detect the infection much earlier than what is possible with today's early warning systems for infectious diseases.

As more people get cancer the need for medical guidance increases. In Norway, one of the providers of medical guidelines is the Norwegian Cancer Association where oncological nurses assist people with a cancer diagnosis or their relatives. The nurses search through both national and internal guide-books and web pages. The input to this process is mostly dis-charge letters. The whole process is time consuming. To serve more patients, PaSent, a web-based intelligent oncological nurse advisor, has been developed. Through using discharge letters as input to our neural network based information retrieval system PaSent, we have been able to provide relevant medical information to the patient as well as to the health personnel themselves. The PaSent search method uses predefined knowledge about the context, paired with the vocabulary of the input document, to compute a relevance measure for a potential result document. The system has been validated by oncological nurses and medical doctors. In the reported experiments, the achieved search results from PaSent have been comparable to the results achieved by the health personnel.