Intraductal hepatocellular carcinoma with normal liver--case report.

Hepatocellular carcinoma commonly invades the portal vein but is rarely seen in the bile duct. When seen, a minor intraductal component usually accompanies a prominent hepatic involvement. We report a case of hepatocellular carcinoma that entirely involved the common bile duct, the hepatic involvement was undiscernible at operation or ultrasonography. The patient had obstructive jaundice both at first presentation and at recurrence. The liver was normal at both explorations. The elevated AFP levels returned to normal after second resection. The diagnosis was confirmed by electron microscopy.     

Clinical decision support with automated text processing for cervical cancer screening

Objective

To develop a computerized clinical decision support system (CDSS) for cervical cancer screening that can interpret free-text Papanicolaou (Pap) reports.

Materials and Methods

The CDSS was constituted by two rulebases: the free-text rulebase for interpreting Pap reports and a guideline rulebase. The free-text rulebase was developed by analyzing a corpus of 49 293 Pap reports. The guideline rulebase was constructed using national cervical cancer screening guidelines. The CDSS accesses the electronic medical record (EMR) system to generate patient-specific recommendations. For evaluation, the screening recommendations made by the CDSS for 74 patients were reviewed by a physician.

Results and Discussion

Evaluation revealed that the CDSS outputs the optimal screening recommendations for 73 out of 74 test patients and it identified two cases for gynecology referral that were missed by the physician. The CDSS aided the physician to amend recommendations in six cases. The failure case was because human papillomavirus (HPV) testing was sometimes performed separately from the Pap test and these results were reported by a laboratory system that was not queried by the CDSS. Subsequently, the CDSS was upgraded to look up the HPV results missed earlier and it generated the optimal recommendations for all 74 test cases.

Limitations

Single institution and single expert study.

Conclusion

An accurate CDSS system could be constructed for cervical cancer screening given the standardized reporting of Pap tests and the availability of explicit guidelines. Overall, the study demonstrates that free text in the EMR can be effectively utilized through natural language processing to develop clinical decision support tools.     

Oesophageal dilatation on high‐resolution CT chest in systemic sclerosis: What does it signify?

Objective: To evaluate the significance of oesophageal dilatation on high‐resolution CT (HRCT) chest in patients with systemic sclerosis. Methods: We retrospectively retrieved the database of patients with systemic sclerosis seen at our hospital between January 2008 and January 2009. A total of 50 patients (46 women and four men) who had HRCT chest, pulmonary function testing and echocardiography within 1 month were included in the study. Peak pulmonary artery (PA) pressures and pulmonary function testing were charted. The HRCT chest was interpreted by a chest radiologist. Oesophageal dilatation was defined as a luminal coronal diameter of ≥9 mm in infra‐aortic oesophagus. Extent of ground glass, reticulation and honeycombing was objectively scored. Results: Statistical analysis using independent t‐test showed that diffusion capacity of carbon monoxide was significantly lower (P = 0.042) and peak PA pressures were significantly higher (P = 0.045) in patients with oesophageal dilatation (n = 29) as compared with those without oesophageal dilatation (n = 21). The two cohorts had no significant difference in their total lung capacity and HRCT determined extent of interstitial lung disease. Conclusion: Patients with oesophageal dilatation on HRCT chest had significantly lower diffusion capacity of carbon monoxide and higher peak PA pressures, which suggest that these patients tend to have more severe pulmonary vascular disease.     

Xanthogranulomatous pyelonephritis in children and adults--an 8 year study

20 cases of Xanthogranulomatous Pyelonephritis (XPN) were encountered over an 8 year period, constituting 0.4 percent of the total of 47,370 surgical biopsies, 10 percent of the total of 188 nephrectomy specimens removed for various reasons and 35 percent of the nephrectomy specimens associated with chronic pyelonephritis. This is the largest single series, reported in Indian literature. 16 patients were adults and 4 were children, thus 25 percent of our cases were children, a significantly high proportion. Our youngest patient a 5 1/2 month old male, is to the best of our knowledge, the youngest case reported from India. Males predominated in our series, the M:F ratio being 3:1, this contrasts with western literature in which there is a definite female preponderance. The common presenting symptoms were lumbar pain, fever and palpable non-functioning kidney. 4 cases were complicated by cutaneous sinuses. There was a slight predominance of affectation of the left side over the right side. On gross examination, diffuse lesions were commoner than focal lesions and were seen in children as well. An accurate pre-operative diagnosis was made in only 2 cases, in the rest, the diagnosis was either tuberculosis or pyonephrosis. Thus XPN is quite frequently seen in the adult Indian population and is not as rare in children, as it was once thought to be.     

A clinical algorithm for the diagnosis of malaria: results of an evaluation in an area of low endemicity

We conducted a study of 1945 children and 2885 adults who presented with fever to a hospital outpatients clinic in an urban area of India order to develop and evaluate a clinical algorithm for the diagnosis of malaria. Only 139 (7%) children and 349 (12%) adults had microscopically confirmed malaria. None of the symptoms or signs elicited from the respondents were good predictors of clinical malaria. Simple scores were derived through combining clinical features which were associated with slide positivity or were judged by clinicians to be important. The best-performing algorithms were a score of 4 clinical features in children (sensitivity 60.0% and specificity 61.2%) and a score of 5 in adults (sensitivity 54.6% and specificity 57.5%). The clinical features differed and algorithm performances were poorer than in previous studies in highly endemic areas. The conclusion is that malaria diagnosis in areas of low endemicity requires microscopy to be accurate.     

Bouveret's syndrome--an unusual cause of spontaneous resolution of gastric outlet obstruction.

Gastric outlet obstruction due to a gallstone impacted in the duodenal bulb (Bouveret's syndrome) is a rare complication of gallstones. We report a 47-year-old man with this syndrome in whom the impacted stone migrated uneventfully.     

Improving self-care of patients with chronic disease using online personal health record

Background

Effective management of chronic diseases such as prostate cancer is important. Research suggests a tendency to use self-care treatment options such as over-the-counter (OTC) complementary medications among prostate cancer patients. The current trend in patient-driven recording of health data in an online Personal Health Record (PHR) presents an opportunity to develop new data-driven approaches for improving prostate cancer patient care. However, the ability of current online solutions to share patients’ data for better decision support is limited. An informatics approach may improve online sharing of self-care interventions among these patients. It can also provide better evidence to support decisions made during their self-managed care.

Aims

To identify requirements for an online system and describe a new case-based reasoning (CBR) method for improving self-care of advanced prostate cancer patients in an online PHR environment.

Method

A non-identifying online survey was conducted to understand self-care patterns among prostate cancer patients and to identify requirements for an online information system. The pilot study was carried out between August 2010 and December 2010. A case-base of 52 patients was developed.

Results

The data analysis showed self-care patterns among the prostate cancer patients. Selenium (55%) was the common complementary supplement used by the patients. Paracetamol (about 45%) was the commonly used OTC by the patients.

Conclusion

The results of this study specified requirements for an online case-based reasoning information system. The outcomes of this study are being incorporated in design of the proposed Artificial Intelligence (Al) driven patient journey browser system. A basic version of the proposed system is currently being considered for implementation.     

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.