Search

The International Classification of Diseases (ICD) code is a diagnostic classification standard that is frequently used as a referencing system in healthcare and insurance. However, it takes time and effort to find and use the right diagnosis code based on a patient's medical records. In response, deep learning (DL) methods have been developed to assist physicians in the ICD coding process. Our findings propose a deep learning model that utilized clinical notes from medical records to predict ICD-10 codes. Our research used text-based medical data from the outpatient department (OPD) of a university hospital from January to December 2016. The dataset used clinical notes from five departments, and a total of 21,953 medical records were collected. Clinical notes consisted of a subjective component, objective component, assessment, plan (SOAP) notes, diagnosis code, and a drug list. The dataset was divided into two groups: 90% for training and 10% for test cases. We applied natural language processing (NLP) technique (word embedding, Word2Vector) to process the data. A deep learning-based convolutional neural network (CNN) model was created based on the information presented above. Three metrics (precision, recall, and F-score) were used to calculate the achievement of the deep learning CNN model. Clinically acceptable results were achieved through the deep learning model for five departments (precision: 0.53–0.96; recall: 0.85–0.99; and F-score: 0.65–0.98). With a precision of 0.95, a recall of 0.99, and an F-score of 0.98, the deep learning model performed the best in the department of cardiology. Our proposed CNN model significantly improved the prediction performance for an automated ICD-10 code prediction system based on prior clinical information. This CNN model could reduce the laborious task of manual coding and could assist physicians in making a better diagnosis. [ABSTRACT FROM AUTHOR]

Currently, the International Classification of Diseases (ICD) codes are being used to improve clinical, financial, and administrative performance. Inaccurate ICD coding can lower the quality of care, and delay or prevent reimbursement. However, selecting the appropriate ICD code from a patient's clinical history is time-consuming and requires expert knowledge. The rapid spread of electronic medical records (EMRs) has generated a large amount of clinical data and provides an opportunity to predict ICD codes using deep learning models. The main objective of this study was to use a deep learning-based natural language processing (NLP) model to accurately predict ICD-10 codes, which could help providers to make better clinical decisions and improve their level of service. We retrospectively collected clinical notes from five outpatient departments (OPD) from one university teaching hospital between January 2016 and December 2016. We applied NLP techniques, including global vectors, word to vectors, and embedding techniques to process the data. The dataset was split into two independent training and testing datasets consisting of 90% and 10% of the entire dataset, respectively. A convolutional neural network (CNN) model was developed, and the performance was measured using the precision, recall, and F-score. A total of 21,953 medical records were collected from 5016 patients. The performance of the CNN model for the five different departments was clinically satisfactory (Precision: 0.50~0.69 and recall: 0.78~0.91). However, the CNN model achieved the best performance for the cardiology department, with a precision of 69%, a recall of 89% and an F-score of 78%. The CNN model for predicting ICD-10 codes provides an opportunity to improve the quality of care. Implementing this model in real-world clinical settings could reduce the manual coding workload, enhance the efficiency of clinical coding, and support physicians in making better clinical decisions. [ABSTRACT FROM AUTHOR]

The effect of early rehabilitation on the outcome of patients with chronic obstructive pulmonary disease (COPD) and acute respiratory failure (ARF) in intensive care units (ICUs) remains unclear. We examined the effect of early rehabilitation on the outcomes of COPD patients requiring mechanical ventilation (MV) in the ICU. This retrospective, observational, case-control study was conducted in a medical center with a 19- bed ICU. The records of all 105 ICU patients with COPD and ARF who required MV from January to December 2011 were examined. The outcomes (MV duration, rates of successful weaning and survival, lengths of ICU and hospital stays, and medical costs) were recorded and analyzed. During the study period, 35 patients with COPD underwent early rehabilitation in the ICU and 70 demographically and clinically matched patients with similar COPD stage, cause of intubation, type of respiratory failure, and levels of disease severity who had not undergone early rehabilitation in the ICU were selected as comparative controls. Multiple regression analysis showed that early rehabilitation was significantly negatively associated with MV duration. Early rehabilitation for COPD patients in the ICU with ARF shortened the duration of their MV. [ABSTRACT FROM AUTHOR]

Objectives To determine whether insomnia at baseline is a risk factor for new-onset asthma. Methods We recruited 48 871 patients with insomnia (insomnia group) newly diagnosed between 2002 and 2007, and 97 742 matched controls without insomnia (control group) from Taiwan's Longitudinal Health Insurance Database 2000. All of the patients were followed up for 4 years to see whether new-onset asthma developed. Patients with previous asthma or insomnia were excluded. The Poisson regression was used to estimate the incidence rate ratios (IRRs) and 95% CIs of asthma. Cox proportional hazard regression was used to calculate the risk of asthma between the two groups. Results After a 4-year follow-up, 424 patients in the insomnia group and 409 in the control group developed asthma. The incidence rate of asthma was significantly higher in the insomnia group (22.01vs10.57 per 10 000 person-years). Patients with insomnia have a higher risk of developing new-onset asthma during the 4-year follow-up (HR: 2.08, 95% CI 1.82 to 2.39). The difference remained significant after adjustment (adjusted HR: 1.89, 95% CI 1.64 to 2.17). Conclusions This large population-based study suggests that insomnia at baseline is a risk factor for developing asthma. [ABSTRACT FROM AUTHOR]

Among many antioxidants that are used for the repairing of oxidative stress induced skin damages, we identified the enriched astaxanthin extract (EAE) from Haematococcus pluvialis as a viable ingredient. EAE was extracted from the red microalgae through supercritical fluid carbon dioxide extraction. To compare the effectiveness, EAE wastreated on human dermal fibroblasts with other components, phorbol 12-myristate 13-acetate (PMA), and doxycycline. With sirius red staining and quantitative real-time polymerase chain reaction (qRT-PCR), we found that PMA decreased the collagen concentration and production while overall the addition of doxycycline and EAE increased the collagen concentration in a trial experiments. EAE increased collagen contents through inhibited MMP1 and MMP3 mRNA expression and induced TIMP1, the antagonists of MMPs protein, gene expression. As for when tested for various proteins through western blotting, it was seen that the addition of EAE increased the expression of certain proteins that promote cell proliferation. Testing those previous solutions using growth factor assay, it was noticeable that EAE had a positive impact on cell proliferation and vascular endothelial growth factor (VEGF) than doxycycline, indicating that it was a better alternative treatment for collagen production. To sum up, the data confirmed the possible applications as medical cosmetology agentsand food supplements. [ABSTRACT FROM AUTHOR]

Introduction: Patients with end-stage renal disease (ESRD(Pos)) usually have multiple comorbidities and are predisposed to acute organ failure and in-hospital mortality. We assessed the effect of ESRD on the poorly understood long-term mortality risk after a first-ever mechanical ventilation (1-MV) for acute respiratory failure.Methods: The data source was Taiwan's National Health Insurance (NHI) Research Database. All patients given a 1-MV between 1999 and 2008 from one million randomly selected NHI beneficiaries were identified (n = 38,659). Patients with or without ESRD (ESRD(Neg)) after a 1-MV between 1999 and 2008 were retrospectively compared and followed from the index admission date to death or the end of 2011. ESRD(Pos) patients (n = 1185; mean age: 65.9 years; men: 51.5 %) were individually matched to ESRD(Neg) patients (ratio: 1:8) using a propensity score method. The primary outcome was death after a 1-MV. The effect of ESRD on the risk of death after MV was assessed. A Cox proportional hazard regression model was used to assess how ESRD affected the mortality risk after a 1-MV.Results: The baseline characteristics of the two cohorts were balanced, but the incidence of mortality was higher in ESRD(Pos) patients than in ESRD(Neg) patients (342.30 versus 179.67 per 1000 person-years; P <0.001; covariate-adjusted hazard ratio: 1.43; 95 % confidence interval: 1.31-1.51). For patients who survived until discharge, ESRD was not associated with long-term (>4 years) mortality.Conclusions: ESRD increased the mortality risk after a 1-MV, but long-term survival seemed similar. [ABSTRACT FROM AUTHOR]

In this work, one of Zingiber officinale components, 10-shogaol, was tested with 1,1-diphenyl-2-picrylhydrazyl (DPPH) radical scavenging, metal chelating ability, and reducing power to show antioxidant activity. 10-Shogaol promoted human normal epidermal keratinocytes and dermal fibroblasts cell growths. 10-Shogaol enhanced growth factor production in transforming growth factor-β (TGF-β), platelet derived growth factor-αβ (PDGF-αβ) and vascular endothelial growth factors (VEGF) of both cells. In the in vitro wound healing assay for 12 or 24 h, with 10-shogaol, the fibroblasts and keratinocytes migrated more rapidly than the vehicle control group. Thus, this study substantiates the target compound, 10-shogaol, as an antioxidant for human skin cell growth and a migration enhancer with potential to be a novel wound repair agent. [ABSTRACT FROM AUTHOR]

Background and objective: Ciprofloxacin, moxifloxacin and levofloxacin are recognized immunomodulators. Their effects in acute lung injuries have not been tested. This study compared the immunoprotective effects of these agents in mice with lung injuries induced by LPS by measuring the cytokine profiles in the injured lung and the associated mortality. Methods: The development of lung injury and mortality was compared in mice pretreated with either ciprofloxacin, levofloxacin, moxifloxacin or saline (control group) after the intratracheal administration of LPS. BALF and serum were collected at 1, 3 and 6 h to measure the concentrations of tumour necrosis factor-α (TNF-α), IL-1β, IL-6, IL-10 and macrophage inflammatory protein-2 (MIP-2) using enzyme-linked immunoassay. Results: Levels of TNF-α, IL-1β and MIP-2 in the BAL of the ciprofloxacin group were significantly lower compared with those of controls (all P < 0.0083) at 3 and 6 h after LPS challenge. There were no significant differences in the levels of these cytokines in the moxifloxacin and levofloxacin groups compared with controls. Overall, the 96-h survival for the mice pretreated with ciprofloxacin, but not for those pretreated with moxifloxacin or levofloxacin, was significantly greater than that of the control animals ( P = 0.019). Conclusions: In the setting of LPS-induced lung injuries, ciprofloxacin appears to provide better anti-inflammatory properties and survival benefits than the other fluoroquinolones tested. [ABSTRACT FROM AUTHOR]

Background. The association of the magA gene with the hypermucoviscosity phenotype relevant to the pathogenesis of Klebsiella pneumoniae liver abscess has been reported in Taiwan. Similarly, the rmpA gene, known as a positive regulator of extracapsular polysaccharide synthesis that confers a mucoid phenotype, may be another candidate gene causing hypermucoviscosity. However, the association of rmpA with K. pneumoniae clinical syndromes is unreported. We aimed to investigate the clinical correlation between rmpA and primary Klebsiella abscess, focusing on sites other than the liver. Methods. From July 2003 through December 2004, a total of 151 K. pneumoniae isolates recovered from 151 patients with bacteremia were collected from 2 large medical centers in southern Taiwan. Clinical data were collected from medical records. The genes rmpA and magA were amplified by polymerase chain reaction using specific primers. Results. The prevalences of hypermucoviscosity, rmpA, and magA were 38%, 48%, and 17%, respectively. As determined by statistical multivariate analysis, strains carrying rmpA were significantly associated with the hypermucoviscosity phenotype, and there was a significant correlation with purulent tissue infections, such as liver abscess and lung, neck, psoas muscle, or other focal abscess. Conclusion. Our data support a statistical correlation between the rmpA gene and virulence in terms of abscess formation for these hypermucoviscous K. pneumoniae strains. Hypermucoviscosity associated with rmpA, together with a thorough physical examination, may be helpful as a guide to carry out appropriate diagnostic tests on patients with an initially unknown source of K. pneumoniae bacteremia, particularly when looking for the occurrence of an underlying abscess. [ABSTRACT FROM AUTHOR]

Established cancer cell lines are useful in the study of various cancers. We established a human gastric carcinoma cell line TMC-1 derived from the lymph node of a moderately differentiated adenocarcinoma of the stomach. TMC-1 cells grew in vitro as a mixture of attached and suspension cells, and exhibited spindle or ovoid morphology. They had a population doubling time of 15 h, a plating efficiency of 61%, formed colonies in semisolid agar, secreted the tumor marker CA 19-9, and were tumorigenic in athymic nude mice. The cells expressed E-cadherin and β-catenin. The karyotypic analysis demonstrated hyperdiploid features with a modal chromosome of 53. The cell had the deletion at chromosome 18q and gains at chromosome 2p13–25, 5p15, 5q21–35, 7, 8q24, 9q, 11, 12p, 14q24–32 and 20. Analysis by fluorescence in situ hybridization showed the deletion at 7qtel and duplication at 7q11.2 at the rearranged chromosome 7. Growth of TMC-1 cells was inhibited by 27–32% by interferon-α (2,000 U/ml) and by interferon-γ with an IC50 of 125 U/ml. The cell line is tumorigenic in vivo, and its growth is moderately inhibited by interferon-α and interferon-γ. It can be used to develop new modalities of human gastric cancer treatment. Copyright © 2004 S. Karger AG, Basel [ABSTRACT FROM AUTHOR]

A letter to the editor is presented in response to an article related to the application of polymerase chain reaction analysis to detect capsular serotype K2 of Klebsiella pneumoniae in the March 1, 2006 issue.

The article discusses a medical condition involving a patient with epiglottitis. A direct laryngoscopy revealed a swollen epiglottitis which caused a progressive respiratory distress on the patient. The patient was administered with parenteral therapy with amoxicillin - clavulanate and corticosteroids. The swelling ceased after five days of treatment.