Sessions

The automatic de-identification of clinical narrative text offers efficient patient data privacy protection and eases reuse of clinical data. CliniDeID applies an ensemble method combining deep and shallow machine learning with rule-based algorithms and is released as free and open-source solution to de-identify unstructured clinical text with high accuracy. It was recently evaluated with a selection of clinical text corpora and reached high sensitivity and positive predictive value.

The introduction of healthtech solutions has proven, by now, that it is having an impact in the main challenges that healthcare systems have in front of them-Democratization of care at a fraction of the cost. However, it is still challenging to assess the contribution each and every healthtech solution brings to society in an aggregated way. Would a metric like QALY (Quality-Adjusted Life year) and its use in healthtech help tackle this challenge?  Come and participate in a discussion, where we will share QALY results obtained for a variety of HealthTech solutions (updated results of a test asking the same question) as food for thought. Let’s discuss together: Is QALY viable for decision making to implement healthtech solutions?  -What are the uses QALY could have and what’s its potential? - Could an aggregated QALY help us measure impact?  Let’s find a path towards the adoption of Healthtech together!

Autism spectrum disorder (ASD) is a developmental disability caused by differences in the brain regions. Analysis of differential expression (DE) of transcriptomic data allows for genome-wide analysis of gene expression changes related to ASD. De-novo mutations may play a vital role in ASD, but the list of genes involved is still far from complete. Differentially expressed genes (DEGs) are treated as candidate biomarkers and a small set of DEGs might be identified as biomarkers using either biological knowledge or data-driven approaches like machine learning and statistical analysis. In this study, we employed a machine learning-based approach to identify the differential gene expression between ASD and Typical Development (TD). The gene expression data of 15 ASD and 15 TD were obtained from NCBI GEO database. Initially, we extracted the data and used a standard pipeline to preprocess the data. Further, Random Forest (RF) was used to discriminate genes between ASD and TD. We identified the top 10 prominent differential genes and compared them with the statistical test results. Our results show that the proposed RF model yields 5-fold cross-validation accuracy, sensitivity and specificity of 96.67%. Further, we obtained precision and F-measure scores of 97.5% and 96.57%, respectively. Moreover, we found 34 unique DEG chromosomal locations having influential contributions in identifying ASD from TD. We have also identified chr3:113322718-113322659 as the most significant contributing chromosomal location in discriminating ASD and TD. Our machine learning-based method of refining DE analysis is promising for finding biomarkers from gene expression profiles and prioritizing DEGs. Moreover, our study reported top-10 gene signatures for ASD may facilitate the development of reliable diagnosis and prognosis biomarkers for screening ASD.Keywords: Gene expression data, NCBI, Autism Spectrum Disorder, Random Forest, Statistical test

Ökad patientsäkerhet är ett av de viktigaste målen med det nya EU-gemensamma regelverket för medicintekniska produkter, MDR. Efter två år med det nya regelverket och en förlängning av övergångsreglerna är det hög tid för tillverkare och användare att anpassa sig till de nya reglerna. Vad innebär övergångsreglerna för användare och tillverkare? Vad är de viktigaste skillnaderna mellan det nya och det gamla regelverket? Hur kan jag som inköpare/upphandlare använda MDR i mitt val av system? Hur gör tillverkare för att bli certifierade?Stefan Jernberg är Chief Regulatory Officer på Cuviva AB och han har tagit deras produkt, Cuviva Remote Patient Monitoring Platform, genom MDR-certifiering enligt klass IIa som en av de första medicintekniska programvarorna för egenmonitorering. Stefan har över 25 års erfarenhet från programvaruindustrin varav 10 inom medicinteknik.

The future success of moving to a smart hospital is understanding the risk. Risk should be an open transparent conversation between stakeholders of the future hospital. With an increase in interconnected devices that allow for more remote care the protection of the central brain of the hospital is critical. Change takes time and education. If we consider current cyber threats that healthcare as an industry faces one might ask what does it really mean to be secure? Security is not a permanent achievable state, it is temporal and fluid. Technology in healthcare is ever-changing and along with that there should be a clear understanding of the risks. Breaches happen almost daily around the world specifically within healthcare. As a highly targeted industry, how do we effectively deal with these breaches, what is the estimated downtime? This talk explores the current state of responses to breaches, and potential solutions with a focus on education and disaster planning for not if but when it happens.

The shortage of skilled nursing personnel is – among other reasons – due to the low attractiveness of the profession, comprising high workloads and atypical working hours. Studies show that speech-based documentation systems increase documentation efficiency and satisfaction of physicians. This paper describes the development process of a speech-based application to support nurses, according to the user-centered design approach. User requirements were collected based on interviews (n=6) as well as observations (n=6) in three institutions and were evaluated by means of qualitative content analysis. A prototype of the derived system architecture was implemented. Based on a usability test (n=3), further potentials for improvement were determined. The resulting application enables nurses to dictate personal notes, share them with colleagues and transmit notes to the existing documentation system. We conclude that the user-centered approach ensures the extensive consideration of the nursing staff’s requirements and shall be continued for further development.

Providing seamless health care to homeless people and refugees is a challenge. Established solutions of medical informatics for information sharing often do not work in these settings. Innovative solutions addressing not only technical issues, but also social and ethical issues are needed for building a trustful digital ecosphere for this vulnerable population. In this workshop, we want to explore the problem in more detail and discuss possible solutions from several perspectives. The workshop is intended to be the starting point to build a European expert consortium that is motivated to further work on this problem and to explore, develop, implement and evaluate possible solutions.

The MIE conference has always been a hub for innovation and cutting-edge technology. This year was no exception several demonstrators showcase their unique solutions to healthcare problems. Use the opportunity to take a closer look at some of the most striking demonstrators present at the conference, highlighting their diversity and the potential impact they could have on various healthcare-related challenges

Region Skåne startar införandet av det digitala verktyget 1177 direkt under våren 2023. En grupp skånska forskare med särskilt intresse i e-hälsoforskning har under flera år planerat studier som ska studera verktyget utifrån olika aspekter. Ett antal frågeställningar kring patientsäkerhet, vårdkonsumtion och vårdpersonals samt patienters uppfattningar av verktyget har formulerats i fyra delstudier som kommer att gå av stapeln under 2023. Presentationen kommer att sammanfatta samarbetet kring studieplanering mellan olika aktörer på regional och nationell nivå, samt öppna för diskussion om fallgropar och fördelar med olika studiedesign.

Välkomna till släppseminarium av #bättredelat nätverkets andra rapport där vi fördjupar oss i de positionsförflyttningar i attityd, kunskap, förmågor, samarbete och kultur som krävs för att välfärden ska dra nytta av ny teknik.

Process mining is a relatively new method that connects data science and process modelling. In the past years a series of applications with health care production data have been presented in process discovery, conformance check and system enhancement. In this paper we apply process mining on clinical oncological data with the purpose of studying survival outcomes and chemotherapy treatment decision in a real-world cohort of small cell lung cancer patients treated at Karolinska University Hospital (Stockholm, Sweden). The results highlighted the potential role of process mining in oncology to study prognosis and survival outcomes with longitudinal models directly extracted from clinical data derived from healthcare.