PubMed-supported clinical term weighting approach for improving inter-patient similarity measure in diagnosis prediction.

BACKGROUND: Similarity-based retrieval of Electronic Health Records (EHRs) from large clinical information systems provides physicians the evidence support in making diagnoses or referring examinations for the suspected cases. Clinical Terms in EHRs represent high-level conceptual information and the similarity measure established based on these terms reflects the chance of inter-patient disease co-occurrence. The assumption that clinical terms are equally relevant to a disease is unrealistic, reducing the prediction accuracy. Here we propose a term weighting approach supported by PubMed search engine to address this issue. METHODS: We collected and studied 112 abdominal computed tomography imaging examination reports from four hospitals in Hong Kong. Clinical terms, which are the image findings related to hepatocellular carcinoma (HCC), were extracted from the reports. Through two systematic PubMed search methods, the generic and specific term weightings were established by estimating the conditional probabilities of clinical terms given HCC. Each report was characterized by an ontological feature vector and there were totally 6216 vector pairs. We optimized the modified direction cosine (mDC) with respect to a regularization constant embedded into the feature vector. Equal, generic and specific term weighting approaches were applied to measure the similarity of each pair and their performances for predicting inter-patient co-occurrence of HCC diagnoses were compared by using Receiver Operating Characteristics (ROC) analysis. RESULTS: The Areas under the curves (AUROCs) of similarity scores based on equal, generic and specific term weighting approaches were 0.735, 0.728 and 0.743 respectively (p < 0.01). In comparison with equal term weighting, the performance was significantly improved by specific term weighting (p < 0.01) but not by generic term weighting. The clinical terms "Dysplastic nodule", "nodule of liver" and "equal density (isodense) lesion" were found the top three image findings associated with HCC in PubMed. CONCLUSIONS: Our findings suggest that the optimized similarity measure with specific term weighting to EHRs can improve significantly the accuracy for predicting the inter-patient co-occurrence of diagnosis when compared with equal and generic term weighting approaches.

Heat transport by fluid flows with prescribed velocity fields.

We study the problem of heat transport by fluid flows with prescribed velocity fields. The advection-diffusion equation in two dimensions is solved for two velocity fields: (i). a circulation and (ii). a shear flow. These two flows focus separately on the two dominant features of the mean large-scale flow observed in turbulent convection experiments. We find that the Nusselt number, which measures the heat transport, scales respectively for the two velocity fields.

Lack of effect of co-trimoxazole on the pharmacokinetics of orally administered theophylline.

Eight healthy, male subjects participated in a balanced randomized crossover study to investigate the effect of a course of co-trimoxazole (CT; combination of sulphamethoxazole 800 mg and trimethoprim 160 mg, twice daily for 5 days) on the pharmacokinetics and urinary metabolite profile of an orally administered dose of theophylline (TH). There were no significant differences (p greater than 0.05) between the control and treatment phases with respect to any of the following pharmacokinetic parameters of TH: area under the plasma total TH concentration time curve; fraction unbound in plasma; area under the plasma unbound TH concentration time curve; terminal half-life; apparent volume of distribution; apparent total plasma clearance and renal clearance. The urinary recoveries of 1-methyluric acid, 1.3-dimethyluric acid and of theophylline were not significantly different (p greater than 0.05) between the two study phases. There was a significant difference (p less than 0.05), however, in the urinary recovery of 3-methylxanthine (11.3 +/- 2.6 per cent TH alone versus 13.9 +/- 3.6 per cent TH-CT) and in the total urinary recovery of TH and its metabolites (76.5 +/- 8.2 per cent versus 85.3 +/- 7.0 per cent), the latter finding suggesting that CT may have caused a small increase in the extent of TH absorption. The results of the study indicated that CT did not inhibit the biotransformation of TH.