Collection of cancer stage data by classifying free-text medical reports.

Cancer staging provides a basis for planning clinical management, but also allows for meaningful analysis of cancer outcomes and evaluation of cancer care services. Despite this, stage data in cancer registries is often incomplete, inaccurate, or simply not collected. This article describes a prototype software system (Cancer Stage Interpretation System, CSIS) that automatically extracts cancer staging information from medical reports. The system uses text classification techniques to train support vector machines (SVMs) to extract elements of stage listed in cancer staging guidelines. When processing new reports, CSIS identifies sentences relevant to the staging decision, and subsequently assigns the most likely stage. The system was developed using a database of staging data and pathology reports for 710 lung cancer patients, then validated in an independent set of 179 patients against pathologic stage assigned by two independent pathologists. CSIS achieved overall accuracy of 74% for tumor (T) staging and 87% for node (N) staging, and errors were observed to mirror disagreements between human experts.

Towards automated observational analysis of leadership in clinical networks.

Clinical networks are being increasingly employed to drive innovation in health services by encouraging multi-disciplinary clinical engagement in management processes. The effectiveness of a network, however, depends critically on the ability of its leader to coordinate group interactions. This paper discusses leadership of clinical networks, and in this context reviews technologies for analyzing the way team members interact in group conversations. This review will form the foundation for ongoing research to develop the profile of an effective clinical network leader, along with techniques and tools for evaluation and professional development.

Automatic analysis of multimodal group actions in meetings.

This paper investigates the recognition of group actions in meetings. A framework is employed in which group actions result from the interactions of the individual participants. The group actions are modeled using different HMM-based approaches, where the observations are provided by a set of audiovisual features monitoring the actions of individuals. Experiments demonstrate the importance of taking interactions into account in modeling the group actions. It is also shown that the visual modality contains useful information, even for predominantly audio-based events, motivating a multimodal approach to meeting analysis.

Unsupervised clustering of free-living human activities using ambulatory accelerometry.

This paper investigates unsupervised pattern recognition approaches to segment raw accelerometer signals into a sequence of events, for activity monitoring in a free-living environment. Ambulatory devices, such as accelerometers, have made it possible to classify movement, measure long-term trends in activity, and detect unexpected events such as falls. While such technologies are gaining acceptance for use in controlled clinical settings, their use in varying and unrestricted environments is still problematic. This is principally due to the difficulty of obtaining sufficient annotated data to train supervised event classification models, exacerbated by the fact that the most significant events are likely to be extremely rare. To address these limitations, this paper researches two unsupervised event segmentation techniques to (1) coherently cluster free-living activities and (2) detect unspecified unusual events, without requiring labelled data for prior learning. Experiments are presented for the clustering of data collected from a subject in free-living conditions using a triaxial accelerometer attached to the waist. Results show high overall cluster purity performances of 0.81 for the coherent clustering of activities, and ;intuitive' clusters that suggest atypical activities for the unusual event experiments.

Multi-class classification of cancer stages from free-text histology reports using support vector machines.

Multi-class machine learning techniques using support vector machines (SVM) are proposed to classify the TNM stage of lung cancer patients from analysis of their free-text histology reports. Stages obtained automatically can be used for retrospective population-level studies of lung cancer outcomes. While the system could in principle be applied to stage different cancer types, the paper focuses on staging lung cancer due to data availability. Experiments have quantified system performance on a corpus of reports from 710 lung cancer patients using four different SVM architectures for multi-class classification. Results show that a system based on standard binary SVM classifiers organised in a hierarchical architecture show the most promise with overall accuracy results of 0.64 and 0.82 across T and N stages, respectively.