Extracting data from electronic medical records: validation of a natural language processing program to assess prostate biopsy results

Objective

The extraction of specific data from electronic medical records (EMR) remains tedious and is often performed manually. Natural language processing (NLP) programs have been developed to identify and extract information within clinical narrative text. We performed a study to assess the validity of an NLP program to accurately identify patients with prostate cancer and to retrieve pertinent pathologic information from their EMR.

Materials and methods

A retrospective review was performed of a prospectively collected database including patients from the Southern California Kaiser Permanente Medical Region that underwent prostate biopsies during a 2-week period. A NLP program was used to identify patients with prostate biopsies that were positive for prostatic adenocarcinoma from all pathology reports within this period. The application then processed 100 consecutive patients with prostate adenocarcinoma to extract 10 variables from their pathology reports. The extraction and retrieval of information by NLP was then compared to a blinded manual review.

Results

A consecutive series of 18,453 pathology reports were evaluated. NLP correctly detected 117 out of 118 patients (99.1 %) with prostatic adenocarcinoma after TRUS-guided prostate biopsy. NLP had a positive predictive value of 99.1 % with a 99.1 % sensitivity and a 99.9 % specificity to correctly identify patients with prostatic adenocarcinoma after biopsy. The overall ability of the NLP application to accurately extract variables from the pathology reports was 97.6 %.

Conclusions

Natural language processing is a reliable and accurate method to identify select patients and to extract relevant data from an existing EMR in order to establish a prospective clinical database.     

Evaluation of Streptococcus mutans adhesion to fluoride varnishes and subsequent change in biofilm accumulation and acidogenicity

Objectives

The aim of this study was to evaluate Streptococcus mutans adhesion to fluoride varnishes and subsequent change in biofilm accumulation and acidogenicity.

Methods

After producing fluoride varnish-coated hydroxyapatite discs using Fluor Protector (FP), Bifluorid 12 (BIF), Cavity Shield (CASH), or Flor-Opal Varnish White (FO), S. mutans biofilms were formed on the discs. To assess S. mutans adhesion to the discs, 4-h-old biofilms were analysed. To investigate the change in biofilm accumulation during subsequent biofilm formation, the biomass, colony forming units (CFU), and water-insoluble extracellular polysaccharides (EP) of 46-, 70-, and 94-h-old biofilms were analysed. To investigate the change in acidogenicity, pH values of the culture medium were determined during the experimental period. The amount of fluoride in the culture medium was also determined during the experimental period.

Results

BIF, CASH, and FO affected S. mutans adhesion (67–98% reduction) and subsequent biofilm accumulation in 46-, 70-, and 94-h-old biofilms. However, the reducing effect of the fluoride varnishes on the biomass, CFU count, water-insoluble EP amount, and acid production rate of the biofilms decreased as the biofilm age increased. These results may be related to the fluoride-release pattern of the fluoride varnishes. Of the fluoride varnishes tested, FO showed the highest reducing effect against the bacterial adhesion and subsequent biofilm accumulation.

Conclusions

Our findings suggest that if the results of these experiments are extrapolable to the in vivo situation, then reduced clinical benefit of using fluoride varnishes may occur with time.

Clinical significance

Fluoride varnish application can affect cariogenic biofilm formation but the anti-biofilm activity may be reduced with time.     

Radiographic assessment of clinical root-crown ratios of permanent teeth in a healthy Korean population

PURPOSE

The aim of this study was to determine the absolute value of the root/crown ratio (R/C ratio) using panoramic radiographs (PRGs) in a healthy Korean population.

MATERIALS AND METHODS

In total, 99 patient radiographs (of 50 males and 49 females subjects; aged 16 to 24 years old) were examined, and 2,770 teeth were analyzed. Crown lengths and root lengths were measured with modified Lind''s measurements using PACS tools by two examiners in two separate sessions two months apart. All data were analyzed using SPSS. The independent t-test was used to assess for gender differences, and the paired t-test was used to compare both arches with a significance level of P<.05.

RESULTS

The mean R/C ratios varied from 1.29 to 1.89 (male: 1.28-1.84; females: 1.31-1.94). The highest R/C ratios were recorded for the mandibular canines (1.89), followed by the maxillary canines (1.79). The lowest R/C ratios were recorded for the maxillary second molars (1.31). In comparison with the maxillary teeth (1.29-1.78), the mandibular teeth yielded the higher R/C ratio (1.47-1.89), and this difference was significant in the females (P<.05). The difference between the genders was not statistically significant, except for the maxillary central incisors, mandibular canines and mandibular first premolars.

CONCLUSION

These data may enhance the understanding of the clinical R/C ratio as a useful guideline for determining the status of teeth and the ethnic difference.     

Cross‐reactivity between decellularized porcine corneal lamellae for corneal xenobridging and subsequent corneal allotransplants

The purpose of this study is to investigate cross‐reactivity between hypertonic saline‐treated decellularized porcine corneal lamellae for corneal xenobridging and subsequent corneal allotransplants. Five Chinese rhesus macaques, which had undergone anterior partial thickness corneal transplantation using hypertonic saline‐treated decellularized porcine corneal lamellae in preceding experiments, were used as recipients for subsequent full‐thickness corneal allografts. To determine whether sensitization of recipients to xenoantigens leads to cross‐reactivity against alloantigens, we compared; (i) allogeneic one‐way mixed lymphocyte reaction (MLR) of peripheral blood mononuclear cells (PBMCs) from xeno‐sensitized recipients with that of PBMCs from naïve rhesus macaques, and (ii) amounts of IgG antibodies that bound to the PBMCs of a rhesus panel (five monkeys) before and after xeno‐sensitization. Graft survival and immunologic profiles including memory T‐cell subsets and donor rhesus‐specific antibodies were also evaluated. No hyperacute or acute rejection was observed within a month of subsequent allotransplantation in any recipient. Alloreactivity by MLR was not different between xeno‐sensitized rhesus recipients and naïve rhesus monkeys. Panel‐reactive IgG antibodies were unchanged after xeno‐sensitization, and no change in donor rhesus‐specific antibodies was observed in any recipient. No significant changes in memory T‐cell subsets were observed during the early post‐operative period in any recipient. Decellularized porcine corneal lamellae may not increase cross‐reactivity to alloantigens, and thus, porcine corneal lamellae may be used as a bridge to subsequent corneal allografting.