1.Analysis of Adverse Drug Reactions Identified in Nursing Notes Using Reinforcement Learning
Eunjoo JEON ; Youngsam KIM ; Hojun PARK ; Rae Woong PARK ; Hyopil SHIN ; Hyeoun-Ae PARK
Healthcare Informatics Research 2020;26(2):104-111
Electronic Health Records (EHRs)-based surveillance systems are being actively developed for detecting adverse drug reactions (ADRs), but this is being hindered by the difficulty of extracting data from unstructured records. This study performed the analysis of ADRs from nursing notes for drug safety surveillance using the temporal difference method in reinforcement learning (TD learning). Nursing notes of 8,316 patients (4,158 ADR and 4,158 non-ADR cases) admitted to Ajou University Hospital were used for the ADR classification task. A TD(λ) model was used to estimate state values for indicating the ADR risk. For the TD learning, each nursing phrase was encoded into one of seven states, and the state values estimated during training were employed for the subsequent testing phase. We applied logistic regression to the state values from the TD(λ) model for the classification task. The overall accuracy of TD-based logistic regression of 0.63 was comparable to that of two machine-learning methods (0.64 for a naïve Bayes classifier and 0.63 for a support vector machine), while it outperformed two deep learning-based methods (0.58 for a text convolutional neural network and 0.61 for a long short-term memory neural network). Most importantly, it was found that the TD-based method can estimate state values according to the context of nursing phrases. TD learning is a promising approach because it can exploit contextual, time-dependent aspects of the available data and provide an analysis of the severity of ADRs in a fully incremental manner.
2.Clinical Utility of Bronchial Washing PCR for IS6110 and Amplicor for the Rapid Diagnosis of Active Pulmonary Tuberculosis in Smear Negative Patients.
Jungu LEE ; Youngsam KIM ; Jaemin PARK ; Wonki KO ; Donggoo YANG ; Sekyu KIM ; Joon CHANG ; Sungkyu KIM ; Jongrak CHOI
Tuberculosis and Respiratory Diseases 2001;50(2):213-221
BACKGROUND: There is a well recognized interlaboratory variation in the results using the polymerase chain reaction(PCR) to detect the IS6110 sequence. The clinical utility of a commercially developed PCR test(Amplicor) in bronchial washings for detecting pulmonary tuberculosis in smear negative patients was evaluated. The sensitivity and specificity of Amplicor was compared with that of an in-house PCR test used for detecting the IS6110 sequence of Mycobacterium tuberculosis(M.tbc) in the bronchial washing fluid. METHODS: 66 patients whose sputum smear for M.tbc were negative or who could not produce any sputum were recruited from January 1999 to July 1999. They all had a bronchoscopy performed to determine if there were signs of hemoptysis, patients who could not cough up sputum, lung lesion that exclude pulmonary tuberculosis. Pulmonary tuberculosis was diagnosed on the basis of a positive culture or a response to anti-tuberculosis therapy. RESULTS: 19 patients with tuberculosis were identified and samples from 16 patients were later confirmed by culture. Bronchial washing for Amplicor PCR revealed a sensitivity, specificity, positive and negative predictive values of 94.7%, 97.9%, 94.7%, 97.9%, respectively. Using IS6110 based PCR, the sensitivity, specificity, positive and negative predictive values were of 73.7%, 87.2%, 70%, 89.1% respectively. CONCLUSION: Bronchial washing for Amplicor PCR proved to be more useful than IS6110 based PCR in rapidly diagnosing smear negative pulmonary pulmoary tuberculosis in patients where tuberculosis was likely to be differential and rapid diagnosis was essential for optimal treatment.
Bronchoscopy
;
Cough
;
Diagnosis*
;
Hemoptysis
;
Humans
;
Lung
;
Mycobacterium
;
Polymerase Chain Reaction*
;
Sensitivity and Specificity
;
Sputum
;
Tuberculosis
;
Tuberculosis, Pulmonary*
3.Influence of lifestyle, depression, and marital intimacy on quality of life in breast cancer survivors
Su-Jin SEO ; Ju-Hee NHO ; Myoungha LEE ; Youngsam PARK
Korean Journal of Women Health Nursing 2020;26(1):28-36
Purpose:
This study investigated lifestyle, depression, marital intimacy, and quality of life (QoL) in breast cancer survivors, with the goal of identifying the impacts of these factors on QoL.
Methods:
A sample of 146 breast cancer survivors was surveyed in this cross-sectional study. Data were collected from March 20 to May 30, 2019, using self-report structured questionnaires at a hospital located in Jeonju, Korea. Data were analyzed using the independent t-test, analysis of variance, Pearson correlation coefficients, and hierarchical regression analysis. Participants agreed to complete a face-to-face interview, including administration of the Health Promoting Lifestyle Profile II, Depression Anxiety Stress Scale 21-Depression Scale, Marital Intimacy Scale, and Functional Assessment Cancer Therapy-Breast Cancer tool.
Results:
QoL was positively correlated with lifestyle (r=.49, p<.001) and marital intimacy (r=.45, p<.001) and negatively correlated with depression (r=–.72, p<.001). Hierarchical multiple regression analysis showed that depression (β=–0.63, p<.001), marital intimacy (β=0.19, p=.001), and lifestyle (β=0.13, p=.031) had significant effects on the QoL of breast cancer survivors, accounting for 63.3% of variance in related QoL.
Conclusion
This study provides insights into how breast cancer survivors’ QoL was influenced by depression, marital intimacy, and lifestyle. To improve the QoL of breast cancer survivors, healthcare providers should consider developing strategies to decrease depression, to increase marital intimacy, and to improve lifestyle.
4.Roles of Inflammatory Biomarkers in Exhaled Breath Condensates in Respiratory Clinical Fields
Yong Jun CHOI ; Min Jae LEE ; Min Kwang BYUN ; Sangho PARK ; Jimyung PARK ; Dongil PARK ; Sang-Hoon KIM ; Youngsam KIM ; Seong Yong LIM ; Kwang Ha YOO ; Ki Suck JUNG ; Hye Jung PARK
Tuberculosis and Respiratory Diseases 2024;87(1):65-79
Background:
Exhaled condensates contain inflammatory biomarkers; however, their roles in the clinical field have been under-investigated.
Methods:
We prospectively enrolled subjects admitted to pulmonology clinics. We collected exhaled breath condensates (EBC) and analysed the levels of six and 12 biomarkers using conventional and multiplex enzyme-linked immunosorbent assay, respectively.
Results:
Among the 123 subjects, healthy controls constituted the largest group (81 participants; 65.9%), followed by the preserved ratio impaired spirometry group (21 patients; 17.1%) and the chronic obstructive pulmonary disease (COPD) group (21 patients; 17.1%). In COPD patients, platelet derived growth factor-AA exhibited strong positive correlations with COPD assessment test (ρ=0.5926, p=0.0423) and COPD-specific version of St. George’s Respiratory Questionnaire (SGRQ-C) score (total, ρ=0.6725, p=0.0166; activity, ρ=0.7176, p=0.0086; and impacts, ρ=0.6151, p=0.0333). Granzyme B showed strong positive correlations with SGRQ-C score (symptoms, ρ=0.6078, p=0.0360; and impacts, ρ=0.6007, p=0.0389). Interleukin 6 exhibited a strong positive correlation with SGRQ-C score (activity, ρ=0.4671, p=0.0378). The absolute serum eosinophil and basophil counts showed positive correlations with pro-collagen I alpha 1 (ρ=0.6735, p=0.0164 and ρ=0.6295, p=0.0283, respectively). In healthy subjects, forced expiratory volume in 1 second (FEV1)/forced vital capacity demonstrated significant correlation with CC chemokine ligand 3 (CCL3)/macrophage inflammatory protein 1 alpha (ρ=0.3897 and p=0.0068). FEV1 exhibited significant correlation with CCL11/eotaxin (ρ=0.4445 and p=0.0017).
Conclusion
Inflammatory biomarkers in EBC might be useful to predict quality of life concerning respiratory symptoms and serologic markers. Further studies are needed.