Using machine learning for concept extraction on clinical documents from multiple data sources

Objective

Concept extraction is a process to identify phrases referring to concepts of interests in unstructured text. It is a critical component in automated text processing. We investigate the performance of machine learning taggers for clinical concept extraction, particularly the portability of taggers across documents from multiple data sources.

Methods

We used BioTagger-GM to train machine learning taggers, which we originally developed for the detection of gene/protein names in the biology domain. Trained taggers were evaluated using the annotated clinical documents made available in the 2010 i2b2/VA Challenge workshop, consisting of documents from four data sources.

Results

As expected, performance of a tagger trained on one data source degraded when evaluated on another source, but the degradation of the performance varied depending on data sources. A tagger trained on multiple data sources was robust, and it achieved an F score as high as 0.890 on one data source. The results also suggest that performance of machine learning taggers is likely to improve if more annotated documents are available for training.

Conclusion

Our study shows how the performance of machine learning taggers is degraded when they are ported across clinical documents from different sources. The portability of taggers can be enhanced by training on datasets from multiple sources. The study also shows that BioTagger-GM can be easily extended to detect clinical concept mentions with good performance.     

Comprehensive temporal information detection from clinical text: medical events,time, and TLINK identification

Background

Temporal information detection systems have been developed by the Mayo Clinic for the 2012 i2b2 Natural Language Processing Challenge.

Objective

To construct automated systems for EVENT/TIMEX3 extraction and temporal link (TLINK) identification from clinical text.

Materials and methods

The i2b2 organizers provided 190 annotated discharge summaries as the training set and 120 discharge summaries as the test set. Our Event system used a conditional random field classifier with a variety of features including lexical information, natural language elements, and medical ontology. The TIMEX3 system employed a rule-based method using regular expression pattern match and systematic reasoning to determine normalized values. The TLINK system employed both rule-based reasoning and machine learning. All three systems were built in an Apache Unstructured Information Management Architecture framework.

Results

Our TIMEX3 system performed the best (F-measure of 0.900, value accuracy 0.731) among the challenge teams. The Event system produced an F-measure of 0.870, and the TLINK system an F-measure of 0.537.

Conclusions

Our TIMEX3 system demonstrated good capability of regular expression rules to extract and normalize time information. Event and TLINK machine learning systems required well-defined feature sets to perform well. We could also leverage expert knowledge as part of the machine learning features to further improve TLINK identification performance.     

Modeling Paradigms for Medical Diagnostic Decision Support: A Survey and Future Directions

Use of computer based decision tools to aid clinical decision making, has been a primary goal of research in biomedical informatics. Research in the last five decades has led to the development of Medical Decision Support (MDS) applications using a variety of modeling techniques, for a diverse range of medical decision problems. This paper surveys literature on modeling techniques for diagnostic decision support, with a focus on decision accuracy. Trends and shortcomings of research in this area are discussed and future directions are provided. The authors suggest that-(i) Improvement in the accuracy of MDS application may be possible by modeling of vague and temporal data, research on inference algorithms, integration of patient information from diverse sources and improvement in gene profiling algorithms; (ii) MDS research would be facilitated by public release of de-identified medical datasets, and development of opensource data-mining tool kits; (iii) Comparative evaluations of different modeling techniques are required to understand characteristics of the techniques, which can guide developers in choice of technique for a particular medical decision problem; and (iv) Evaluations of MDS applications in clinical setting are necessary to foster physicians' utilization of these decision aids.     

Research and applications: Formative evaluation of the accuracy of a clinical decision support system for cervical cancer screening

Objectives

We previously developed and reported on a prototype clinical decision support system (CDSS) for cervical cancer screening. However, the system is complex as it is based on multiple guidelines and free-text processing. Therefore, the system is susceptible to failures. This report describes a formative evaluation of the system, which is a necessary step to ensure deployment readiness of the system.

Materials and methods

Care providers who are potential end-users of the CDSS were invited to provide their recommendations for a random set of patients that represented diverse decision scenarios. The recommendations of the care providers and those generated by the CDSS were compared. Mismatched recommendations were reviewed by two independent experts.

Results

A total of 25 users participated in this study and provided recommendations for 175 cases. The CDSS had an accuracy of 87% and 12 types of CDSS errors were identified, which were mainly due to deficiencies in the system''s guideline rules. When the deficiencies were rectified, the CDSS generated optimal recommendations for all failure cases, except one with incomplete documentation.

Discussion and conclusions

The crowd-sourcing approach for construction of the reference set, coupled with the expert review of mismatched recommendations, facilitated an effective evaluation and enhancement of the system, by identifying decision scenarios that were missed by the system''s developers. The described methodology will be useful for other researchers who seek rapidly to evaluate and enhance the deployment readiness of complex decision support systems.     

Morphological changes in bile ducts following preoperative biliary stenting.

OBJECTIVES: To analyze the morphological changes in bile ducts following endobiliary stent insertion, and consequent technical problems encountered at surgery. METHODS: Data on bile duct morphology--gross (luminal diameter and wall thickness) and microscopic (histological changes in bile duct wall graded semiquantitatively)--and operative parameters related to bile duct dissection (grade of difficulty in dissection) were collected prospectively in 31 consecutive patients undergoing pancreatico-duodenectomy. These data were compared between patients who had undergone preoperative endoscopic biliary stent placement (n=17) and those who had not (n=14). RESULTS: Mean duration of stenting before surgery was 34 (range 10-120) days. Stented ducts were significantly narrower (luminal diameter 9 [7-12] mm vs. 17.5 [8-23] mm; p=0.0001) and had thicker walls (2.3 [1.3-3.5] mm vs. 1.85 [0.8-2.2] mm; p=0.004) compared to non-stented ones. On microscopy, stented ducts had advanced grades of submucosal gland hypertrophy, fibrosis and inflammatory cell infiltrate. Difficulty in bile duct dissection was encountered more often in patients who had been stented than in those without stents, though the difference was not statistically significant. CONCLUSION: Endobiliary stent placement results in significant morphological and fibroproliferative inflammatory changes in bile ducts, making dissection difficult.     

Study of socio-demographic factors affecting prevalence of hypertension among bank employees of Surat City

Cardiovascular diseases including hypertension are increasing in developing countries especially among high-risk group people like bank employees. A cross-sectional study of 1493 bank employees of Surat city was conducted during August, 2004 to September, 2005 to study the prevalence of hypertension among bank employees and the effects of socio-demographic factors on prevalence of hypertension. Data were analyzed using epi 6 software. The χ[2] -test was applied as a nonparametric test of statistical significance. Prevalence of hypertension was 30.4% and prehypertension was 34.5%. Out of 455 found as hypertensive, 258 (56.70%) were not having any symptoms at the time of examination. Prevalence was high among persons with age 50 years and above (48.5%); among male (32.5%) as compared to female (23.1%); among employees having small family size; among separated/divorcee person (40.0%). Prevalence of hypertension increased with seniority of the official position of bank employee with highest prevalence among managers (45.9%). Prevalence of hypertension was noted highest among the higher socioeconomic group; SEC I (35.0%) followed by class II (20.4%). Effects of different risk factors of hypertension were observed here. This study may help in identifying the common profile of hypertensive or persons at risk, which may further help in identifying the risk group and planning the group specific IEC interventions.     

Impacted denture causing tracheo-esophageal fistula.

We report a 35-year-old man with an impacted denture resulting in tracheo-esophageal fistula. In view of significant local fibrosis and esophageal stenosis distal to the fistula, he was managed by subtotal esophagectomy and cervical esophagogastric anastomosis.     

Large Brunneroma presenting with bleeding.

Brunner's gland adenoma (Brunneroma) is a rare entity. We report a patient who presented with severe anemia due to bleed from a large Brunneroma arising from the duodenal bulb, and was managed successfully by surgical excision of the tumor.