Empowering Smart Aging: Insights into the Technical Architecture of the e-VITA Virtual Coaching System for Older Adults.

With a substantial rise in life expectancy throughout the last century, society faces the imperative of seeking inventive approaches to foster active aging and provide adequate aging care. The e-VITA initiative, jointly funded by the European Union and Japan, centers on an advanced virtual coaching methodology designed to target essential aspects of promoting active and healthy aging. This paper describes the technical framework underlying the e-VITA virtual coaching system platform and presents preliminary feedback on its use. At its core is the e-VITA Manager, a pivotal component responsible for harmonizing the seamless integration of various specialized devices and modules. These modules include the Dialogue Manager, Data Fusion, and Emotional Detection, each making distinct contributions to enhance the platform's functionalities. The platform's design incorporates a multitude of devices and software components from Europe and Japan, each built upon diverse technologies and standards. This versatile platform facilitates communication and seamless integration among smart devices such as sensors and robots while efficiently managing data to provide comprehensive coaching functionalities.

Interaction with a Virtual Coach for Active and Healthy Ageing.

Since life expectancy has increased significantly over the past century, society is being forced to discover innovative ways to support active aging and elderly care. The e-VITA project, which receives funding from both the European Union and Japan, is built on a cutting edge method of virtual coaching that focuses on the key areas of active and healthy aging. The requirements for the virtual coach were ascertained through a process of participatory design in workshops, focus groups, and living laboratories in Germany, France, Italy, and Japan. Several use cases were then chosen for development utilising the open-source Rasa framework. The system uses common representations such as Knowledge Bases and Knowledge Graphs to enable the integration of context, subject expertise, and multimodal data, and is available in English, German, French, Italian, and Japanese.

Potential of Artificial Intelligence to Accelerate Drug Development for Rare Diseases.

The growth in breadth and depth of artificial intelligence (AI) applications has been fast, running hand in hand with the increasing amount of digital data available. Here, we comment on the application of AI in the field of drug development, with a strong focus on the specific achievements and challenges posed by rare diseases. Data paucity and high costs make drug development for rare diseases especially hard. AI can enable otherwise inaccessible approaches based on the large-scale integration of heterogeneous datasets and knowledge bases, guided by expert biological understanding. Obstacles still exist for the routine use of AI in the usually conservative pharmaceutical domain, which can easily become disillusioned. It is crucial to acknowledge that AI is a powerful, supportive tool that can assist but not replace human expertise in the various phases and aspects of drug discovery and development.

Prognostic value of added stratification of circumferential resection margin status in oesophageal carcinoma.

AIMS: Involved circumferential resection margin (CRM) (R1) in oesophageal carcinoma (OC) has conflicting definitions. This study aimed to compare two such definitions applied to a cohort of OC resection specimens and also evaluated a novel three-tier CRM stratification. METHODS AND RESULTS: OC patients with pT3 disease were classified as R0 or R1 on the basis of Royal College of Pathologists (UK) (RCPath) and College of American Pathologists (CAP) criteria and group survivals were compared. Patients were then stratified into three groups on the basis of tumour distance from the CRM (>1 mm, 0.1-1 mm, 0 mm). A total of 195 patients were included. According to RCPath criteria, 50 resections were R0 and 145 R1; median survival was 72.0 and 18.1 months. Using CAP criteria, 137 resections were R0 and 58 R1; median survival was 30.1 and 12.6 months. Using three-tier stratification, tumour was clear by >1 mm (R0) in 50 cases, 0.1-1 mm from CRM (RCPath R1; CAP R0) in 87 cases and 0 mm (R1) in 58 cases; median survival was 72.0, 24.6 and 12.6 months, respectively. Survival difference was statistically significant using each binary system and also the three-tier system. CONCLUSIONS: Both RCPath and CAP criteria to define CRM have similar prognostic value. A novel three-tier classification of CRM status provides more detailed prognostication.

Pattern-based information extraction from pathology reports for cancer registration.

OBJECTIVE: To evaluate precision and recall rates for the automatic extraction of information from free-text pathology reports. To assess the impact that implementation of pattern-based methods would have on cancer registration completeness. METHOD: Over 300,000 electronic pathology reports were scanned for the extraction of Gleason score, Clark level and Breslow depth, by a number of Perl routines progressively enhanced by a trial-and-error method. An additional test set of 915 reports potentially containing Gleason score was used for evaluation. RESULTS: Values for recall and precision of over 98 and 99%, respectively, were easily reached. Potential increase in cancer staging completeness of up to 32% was proved. CONCLUSIONS: In cancer registration, simple pattern matching applied to free-text documents can be effectively used to improve completeness and accuracy of pathology information.

Predicting CYP2D6 phenotype from resting brain perfusion images by gradient boosting.

The cytochrome P450 enzyme 2D6 is involved in the metabolism of 20% of all commonly used drugs, including many psychotropic drugs and CNS-active substances. CYP2D6 is among the CYP enzymes with the highest expression levels in the brain, suggesting a role in the local brain metabolism of psychotropic drugs and the existence of endogenous substrates. The genetic polymorphism of CYP2D6, which causes individual differences in activity levels of the enzyme, has also been characterized functionally in human brain imaging studies. Here we explore the feasibility of predicting CYP2D6 phenotype using component-wise gradient boosting on fMRI resting brain perfusion images. The images belonged to subjects showing a range of genetic CYP2D6 variants. We achieved sensitivity and specificity values between 85% and 87% for the classification of ultrarapid metabolisers, and between 71% and 79% for poor metabolisers. An extension of the boosting algorithm, developed to improve the clinical plausibility of the inherently sparse models, produced enhanced models in agreement with the results of previous studies, showing some brain regions as positively associated with genotypic variation, most prominently in the prefrontal white matter and the corpus callosum. With further development, such a probabilistic method might constitute a valuable, non-invasive alternative to actual genotyping.

Machine learning classification of surgical pathology reports and chunk recognition for information extraction noise reduction.

BACKGROUND AND AIMS: Machine learning techniques for the text mining of cancer-related clinical documents have not been sufficiently explored. Here some techniques are presented for the pre-processing of free-text breast cancer pathology reports, with the aim of facilitating the extraction of information relevant to cancer staging. MATERIALS AND METHODS: The first technique was implemented using the freely available software RapidMiner to classify the reports according to their general layout: 'semi-structured' and 'unstructured'. The second technique was developed using the open source language engineering framework GATE and aimed at the prediction of chunks of the report text containing information pertaining to the cancer morphology, the tumour size, its hormone receptor status and the number of positive nodes. The classifiers were trained and tested respectively on sets of 635 and 163 manually classified or annotated reports, from the Northern Ireland Cancer Registry. RESULTS: The best result of 99.4% accuracy - which included only one semi-structured report predicted as unstructured - was produced by the layout classifier with the k nearest algorithm, using the binary term occurrence word vector type with stopword filter and pruning. For chunk recognition, the best results were found using the PAUM algorithm with the same parameters for all cases, except for the prediction of chunks containing cancer morphology. For semi-structured reports the performance ranged from 0.97 to 0.94 and from 0.92 to 0.83 in precision and recall, while for unstructured reports performance ranged from 0.91 to 0.64 and from 0.68 to 0.41 in precision and recall. Poor results were found when the classifier was trained on semi-structured reports but tested on unstructured. CONCLUSIONS: These results show that it is possible and beneficial to predict the layout of reports and that the accuracy of prediction of which segments of a report may contain certain information is sensitive to the report layout and the type of information sought.

Methods of calculating prostate-specific antigen velocity.

OBJECTIVES: Numerous methods of calculating PSA velocity (PSAV) are used and have the potential to produce differing PSAV results from the same PSA data. We calculated PSAV using three common methods and compared differences between the methods and their predictive value for prostate cancer diagnosis. METHODS: From a population-based database of PSA results, men with initial PSA<10.0 ng/ml and a subsequent diagnosis of prostate cancer or benign histology were identified. Those with > or =3 PSA tests before diagnosis carried out over a minimum of 18 mo were included. PSAV was calculated by using three methods: The differences between the methods and test characteristics of each method were compared. RESULTS: Of the 2204 men included, 716 (32.5%) were diagnosed with prostate cancer and 1488 (67.5%) benign histology. PSAV differed markedly in each method of calculation. The LR and FL methods had similar predictive values, which were higher than the AE method. There was strong agreement for cancer diagnosis between LR and FL (kappa=0.85), with weaker agreement between LR/AE and FL/AE (kappa=0.69 and 0.66, respectively). CONCLUSIONS: Methods used to calculate PSAV using the same PSA data can produce markedly different results. Linear regression should be the method of choice for calculating PSAV. Using first and last PSA values only may be adequate for everyday clinical use, as long as measurements are separated by a sufficiently long time period.

Electronic patient data confidentiality practices among surgical trainees: questionnaire study.

INTRODUCTION: The objective of this work was to evaluate the safeguards implemented by surgical trainees to protect the confidentiality of electronic patient data through a structured questionnaire sent to Northern Ireland surgical trainees. PARTICIPANTS AND METHODS: A group of 32 basic and higher surgical trainees attending a meeting of the Northern Ireland Association of Surgeons-in-Training were invited to complete a questionnaire regarding their computer use, UK Data Protection Act, 1988 registration and electronic data confidentiality practices. RESULTS: Of these 32 trainees, 29 returned completed questionnaires of whom 26 trainees regularly stored sensitive patient data for audit or research purposes on a computer. Only one person was registered under the Data Protection Act, 1988. Of the computers used to store and analyse sensitive data, only 3 of 14 desktops, 8 of 19 laptops and 3 of 14 hand-held computers forced a password logon. Of the 29 trainees, 16 used the same password for all machines, and 25 of 27 passwords were less than 8 characters long. Two respondents declined to reveal details of their secure passwords. Half of all trainees had never adjusted their internet security settings, despite all 14 desktops, 16 of 19 laptops and 5 of 14 hand-helds being routinely connected to the internet. Of the 29 trainees, 28 never encrypted their sensitive data files. Ten trainees had sent unencrypted sensitive patient data over the internet, using a non-secure server. CONCLUSIONS: Electronic data confidentiality practices amongst Northern Ireland surgical trainees are unsafe. Simple practical measures to safeguard confidentiality are recommended.