Supervised machine learning and active learning in classification of radiology reports.

OBJECTIVE: This paper presents an automated system for classifying the results of imaging examinations (CT, MRI, positron emission tomography) into reportable and non-reportable cancer cases. This system is part of an industrial-strength processing pipeline built to extract content from radiology reports for use in the Victorian Cancer Registry. MATERIALS AND METHODS: In addition to traditional supervised learning methods such as conditional random fields and support vector machines, active learning (AL) approaches were investigated to optimize training production and further improve classification performance. The project involved two pilot sites in Victoria, Australia (Lake Imaging (Ballarat) and Peter MacCallum Cancer Centre (Melbourne)) and, in collaboration with the NSW Central Registry, one pilot site at Westmead Hospital (Sydney). RESULTS: The reportability classifier performance achieved 98.25% sensitivity and 96.14% specificity on the cancer registry's held-out test set. Up to 92% of training data needed for supervised machine learning can be saved by AL. DISCUSSION: AL is a promising method for optimizing the supervised training production used in classification of radiology reports. When an AL strategy is applied during the data selection process, the cost of manual classification can be reduced significantly. CONCLUSIONS: The most important practical application of the reportability classifier is that it can dramatically reduce human effort in identifying relevant reports from the large imaging pool for further investigation of cancer. The classifier is built on a large real-world dataset and can achieve high performance in filtering relevant reports to support cancer registries.

A knowledge discovery and reuse pipeline for information extraction in clinical notes.

OBJECTIVE: Information extraction and classification of clinical data are current challenges in natural language processing. This paper presents a cascaded method to deal with three different extractions and classifications in clinical data: concept annotation, assertion classification and relation classification. MATERIALS AND METHODS: A pipeline system was developed for clinical natural language processing that includes a proofreading process, with gold-standard reflexive validation and correction. The information extraction system is a combination of a machine learning approach and a rule-based approach. The outputs of this system are used for evaluation in all three tiers of the fourth i2b2/VA shared-task and workshop challenge. RESULTS: Overall concept classification attained an F-score of 83.3% against a baseline of 77.0%, the optimal F-score for assertions about the concepts was 92.4% and relation classifier attained 72.6% for relationships between clinical concepts against a baseline of 71.0%. Micro-average results for the challenge test set were 81.79%, 91.90% and 70.18%, respectively. DISCUSSION: The challenge in the multi-task test requires a distribution of time and work load for each individual task so that the overall performance evaluation on all three tasks would be more informative rather than treating each task assessment as independent. The simplicity of the model developed in this work should be contrasted with the very large feature space of other participants in the challenge who only achieved slightly better performance. There is a need to charge a penalty against the complexity of a model as defined in message minimalisation theory when comparing results. CONCLUSION: A complete pipeline system for constructing language processing models that can be used to process multiple practical detection tasks of language structures of clinical records is presented.

Trace elements in wild and orchard honeys.

The present study aims the identification and quantification of trace elements in two types of honey samples: Orchard honey and Wild honey from mainland Portugal. Chemical elements content was assessed by Instrumental Neutron Activation Analysis (INAA). Concentrations were determinated for Ag, As, Br, Ca, Cl, Cs, Cu, Fe, K, La, Mg, Mn, Na, Rb, Sb, Sc, U, V and Zn. The nutritional values of both honey types were evaluated since this product contains some elements that are essential dietary nutrients for humans. Physical properties of the honey samples, such as electrical conductivy and pH, were assessed as well.

Air pollution at an urban traffic tunnel in Lisbon, Portugal: an INAA study.

In this study, the results of chemical concentrations inside and outside of a Lisbon (Portugal) traffic tunnel were compared, during one week. They were obtained by Instrumental Neutron Activation Analysis (INAA). The tunnel values largely exceed the Air Ambient legislated values and the Pearson Correlations Coefficients point out to soil re-suspension/dispersed road dust (As, Ce, Eu, Hf, Fe, Mo, Sc, Zn), traffic-markers (Ba, Cr), tire wear (Cr, Zn), break wear (Fe, Zn, Ba, Cu, Sb), exhaust and motor oil (Zn) and sea-spray (Br, Na). On all days these elements inside the tunnel were more enriched than outside; significant statistical differences were found for Co (p=0.005), Br (p=0.008), Zn (p=0.01) and Sb (p=0.005), while enrichment factors of As and Sc are statistically identical. The highest values were found for As, Br, Zn and Sb, for both inside and outside the tunnel.