Abstract: We reported a 59-year-old female who diagnosed with right breast invasive lobular carcinoma (pT2N0M0, stage IIA) and received modified radical mastectomy with adjuvant chemotherapy and radiotherapy (50 Gy) in 1999. But, she found T10-spine metastasis and received palliative radiotherapy (30 Gy in 10 fractions) 3 years later. In 2012, she had a left abdominal mass and received abdominal wall tumor resection and a metaplastic invasive lobular carcinoma [estrogen receptor (ER)(+), progesterone receptor (PR)(−), human epidermal growth factor receptor 2 (HER2)(−) with positive surgical margin] was noted by pathological reports. In spite of hormone therapy, she experienced a left abdominal painless mass at the same location underneath the previous surgical scar in 2016. After surgical excision, computed tomography showed a residual left external oblique muscle 4.8 cm × 5.0 cm mass. Under the impression of right breast cancer with left external oblique muscle metastasis [metastatic invasive lobular carcinoma, rcT0N0M1, rpT0N0M1, stage IV (AJCC 7th staging)], she received post-operative radiotherapy 60 Gy in 30 fractions. She continued to receive chemotherapy and no evidence of abdominal recurrence till now.
Early screening is crucial in reducing the mortality of colorectal cancer (CRC). Current screening methods, including fecal occult blood tests (FOBT) and colonoscopy, are primarily limited by low patient compliance and the invasive nature of the procedures. Several advanced imaging techniques such as computed tomography (CT) and histological imaging have been integrated with artificial intelligence (AI) to enhance the detection of CRC. There are still limitations because of the challenges associated with image acquisition and the cost. Kidney, ureter, and bladder (KUB) radiograph which is inexpensive and widely used for abdominal assessments in emergency settings and shows potential for detecting CRC when enhanced using advanced techniques. This study aimed to develop a deep learning model (DLM) to detect CRC using KUB radiographs. This retrospective study was conducted using data from the Tri-Service General Hospital (TSGH) between January 2011 and December 2020, including patients with at least one KUB radiograph. Patients were divided into development (n = 28,055), tuning (n = 11,234), and internal validation (n = 16,875) sets. An additional 15,876 patients were collected from a community hospital as the external validation set. A 121-layer DenseNet convolutional network was trained to classify KUB images for CRC detection. The model performance was evaluated using receiver operating characteristic curves, with sensitivity, specificity, and area under the curve (AUC) as metrics. The AUC, sensitivity, and specificity of the DLM in the internal and external validation sets achieved 0.738, 61.3%, and 74.4%, as well as 0.656, 47.7%, and 72.9%, respectively. The model performed better for high-grade CRC, with AUCs of 0.744 and 0.674 in the internal and external sets, respectively. Stratified analysis showed superior performance in females aged 55–64 with high-grade cancers. AI-positive predictions were associated with a higher long-term risk of all-cause mortality in both validation cohorts. AI-enhanced KUB X-ray analysis can enhance CRC screening coverage and effectiveness, providing a cost-effective alternative to traditional methods. Further prospective studies are necessary to validate these findings and fully integrate this technology into clinical practice.
We report here preparation of multi-composition Cu/ZnO/Al2O3 (CZA) catalyst by homogeneous precipitation (HP) method using urea treatment. Compared to the conventional co-precipitation (CP) method, the HP method used here improves the uniformity of metal mixing through homogeneous generation of hydroxide ions as a result of hydrolysis of urea in the solution. In this study, optimization of the conditions to prepare CZA catalyst was achieved by adjusting the urea concentration, amount of water, reaction temperature and reaction time; to control the pH value. The HP-derived CZA particles exhibited a characteristic flower-like morphology with a higher surface area, typically 78.5 m2/g as measured by the BET analysis, as compared to the CP-derived CZA catalysts. Induction coupled plasma and energy dispersive spectroscopy mapping results further confirmed the homogeneity of HP-CZA components and highly uniform dispersion of the active metal. Significantly lowering and a narrower range of the reduction temperature for HP-CZA is observed. An improved performance in methanol reforming reaction, in terms of methanol conversion, yield of hydrogen production, and higher carbon dioxide selectivity, has been achieved. Furthermore, the concentration of carbon monoxide can be further reduced by employing CeO2 and ZrO2 to modify the support, which also results in reduced reduction temperature and improved performance. Among the modified catalysts, HP-CZCZ catalyst showed the highest methanol conversion and rate of hydrogen production, simultaneously with reduced concentration of CO. Moreover, only 20 mg of catalyst loading yielded 98% methanol conversion rate under more than 8500 h−1 GHSV. In future, not only can this method be used to synthesize other multi-composition materials with high homogeneity, but also our approach presents opportunity for production of a highly active catalyst for efficient generation of hydrogen for fuel cell applications.
Background: Automated disease code classification using free-text medical information is important for public health surveillance. However, traditional natural language processing (NLP) pipelines are limited, so we propose a method combining word embedding with a convolutional neural network (CNN). Objective: Our objective was to compare the performance of traditional pipelines (NLP plus supervised machine learning models) with that of word embedding combined with a CNN in conducting a classification task identifying International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) diagnosis codes in discharge notes. Methods: We used 2 classification methods: (1) extracting from discharge notes some features (terms, n-gram phrases, and SNOMED CT categories) that we used to train a set of supervised machine learning models (support vector machine, random forests, and gradient boosting machine), and (2) building a feature matrix, by a pretrained word embedding model, that we used to train a CNN. We used these methods to identify the chapter-level ICD-10-CM diagnosis codes in a set of discharge notes. We conducted the evaluation using 103,390 discharge notes covering patients hospitalized from June 1, 2015 to January 31, 2017 in the Tri-Service General Hospital in Taipei, Taiwan. We used the receiver operating characteristic curve as an evaluation measure, and calculated the area under the curve (AUC) and F-measure as the global measure of effectiveness. Results: In 5-fold cross-validation tests, our method had a higher testing accuracy (mean AUC 0.9696; mean F-measure 0.9086) than traditional NLP-based approaches (mean AUC range 0.8183-0.9571; mean F-measure range 0.5050-0.8739). A real-world simulation that split the training sample and the testing sample by date verified this result (mean AUC 0.9645; mean F-measure 0.9003 using the proposed method). Further analysis showed that the convolutional layers of the CNN effectively identified a large number of keywords and automatically extracted enough concepts to predict the diagnosis codes. Conclusions: Word embedding combined with a CNN showed outstanding performance compared with traditional methods, needing very little data preprocessing. This shows that future studies will not be limited by incomplete dictionaries. A large amount of unstructured information from free-text medical writing will be extracted by automated approaches in the future, and we believe that the health care field is about to enter the age of big data.
In this study, the website information in the SARS period was taken as the example. By setting attributes of information of each article, the relations between articles are established. The relation,presented by an interacted graphic interface based on SVG language, could very with users query. The results show that the new approach could help users to find and understand the contents and relationship among different information source more efficiently.
Most current state-of-the-art models for searching the International Classification of Diseases, Tenth Revision Clinical Modification (ICD-10-CM) codes use word embedding technology to capture useful semantic properties. However, they are limited by the quality of initial word embeddings. Word embedding trained by electronic health records (EHRs) is considered the best, but the vocabulary diversity is limited by previous medical records. Thus, we require a word embedding model that maintains the vocabulary diversity of open internet databases and the medical terminology understanding of EHRs. Moreover, we need to consider the particularity of the disease classification, wherein discharge notes present only positive disease descriptions.We aimed to propose a projection word2vec model and a hybrid sampling method. In addition, we aimed to conduct a series of experiments to validate the effectiveness of these methods.We compared the projection word2vec model and traditional word2vec model using two corpora sources: English Wikipedia and PubMed journal abstracts. We used seven published datasets to measure the medical semantic understanding of the word2vec models and used these embeddings to identify the three-character-level ICD-10-CM diagnostic codes in a set of discharge notes. On the basis of embedding technology improvement, we also tried to apply the hybrid sampling method to improve accuracy. The 94,483 labeled discharge notes from the Tri-Service General Hospital of Taipei, Taiwan, from June 1, 2015, to June 30, 2017, were used. To evaluate the model performance, 24,762 discharge notes from July 1, 2017, to December 31, 2017, from the same hospital were used. Moreover, 74,324 additional discharge notes collected from seven other hospitals were tested. The F-measure, which is the major global measure of effectiveness, was adopted.In medical semantic understanding, the original EHR embeddings and PubMed embeddings exhibited superior performance to the original Wikipedia embeddings. After projection training technology was applied, the projection Wikipedia embeddings exhibited an obvious improvement but did not reach the level of original EHR embeddings or PubMed embeddings. In the subsequent ICD-10-CM coding experiment, the model that used both projection PubMed and Wikipedia embeddings had the highest testing mean F-measure (0.7362 and 0.6693 in Tri-Service General Hospital and the seven other hospitals, respectively). Moreover, the hybrid sampling method was found to improve the model performance (F-measure=0.7371/0.6698).The word embeddings trained using EHR and PubMed could understand medical semantics better, and the proposed projection word2vec model improved the ability of medical semantics extraction in Wikipedia embeddings. Although the improvement from the projection word2vec model in the real ICD-10-CM coding task was not substantial, the models could effectively handle emerging diseases. The proposed hybrid sampling method enables the model to behave like a human expert.
The detection of dyskalemias-hypokalemia and hyperkalemia-currently depends on laboratory tests. Since cardiac tissue is very sensitive to dyskalemia, electrocardiography (ECG) may be able to uncover clinically important dyskalemias before laboratory results.Our study aimed to develop a deep-learning model, ECG12Net, to detect dyskalemias based on ECG presentations and to evaluate the logic and performance of this model.Spanning from May 2011 to December 2016, 66,321 ECG records with corresponding serum potassium (K+) concentrations were obtained from 40,180 patients admitted to the emergency department. ECG12Net is an 82-layer convolutional neural network that estimates serum K+ concentration. Six clinicians-three emergency physicians and three cardiologists-participated in human-machine competition. Sensitivity, specificity, and balance accuracy were used to evaluate the performance of ECG12Net with that of these physicians.In a human-machine competition including 300 ECGs of different serum K+ concentrations, the area under the curve for detecting hypokalemia and hyperkalemia with ECG12Net was 0.926 and 0.958, respectively, which was significantly better than that of our best clinicians. Moreover, in detecting hypokalemia and hyperkalemia, the sensitivities were 96.7% and 83.3%, respectively, and the specificities were 93.3% and 97.8%, respectively. In a test set including 13,222 ECGs, ECG12Net had a similar performance in terms of sensitivity for severe hypokalemia (95.6%) and severe hyperkalemia (84.5%), with a mean absolute error of 0.531. The specificities for detecting hypokalemia and hyperkalemia were 81.6% and 96.0%, respectively.A deep-learning model based on a 12-lead ECG may help physicians promptly recognize severe dyskalemias and thereby potentially reduce cardiac events.
// Chun-Yu Liu 1,2 , Ming-Hung Hu 3,4 , Chia-Jung Hsu 1 , Chun-Teng Huang 2,5 , Duen-Shian Wang 1 , Wen-Chun Tsai 1 , Yi-Ting Chen 1 , Chia-Han Lee 1 , Pei-Yi Chu 10 , Chia-Chi Hsu 11 , Ming-Huang Chen 1,2 , Chung-Wai Shiau 6 , Ling-Ming Tseng 2,7 and Kuen-Feng Chen 8,9 1 Division of Medical Oncology, Department of Oncology, Taipei Veterans General Hospital, Taipei, Taiwan 2 School of Medicine, National Yang-Ming University, Taipei, Taiwan 3 Division of Hematology and Oncology, Department of Medicine, Cardinal Tien Hospital, New Taipei City, Taiwan 4 School of Medicine, Fu Jen Catholic University, New Taipei City, Taiwan 5 Division of Hematology & Oncology, Department of Medicine, Yang-Ming Branch of Taipei City Hospital, Taipei, Taiwan 6 Institute of Biopharmaceutical Sciences, National Yang-Ming University, Taipei, Taiwan 7 Department of Surgery, Taipei Veterans General Hospital, Taipei, Taiwan 8 Department of Medical Research, National Taiwan University Hospital, Taipei, Taiwan 9 National Taiwan University College of Medicine, Taipei, Taiwan 10 Department of Pathology, Show Chwan Memorial Hospital, Changhua City, Taiwan 11 Institute of Pharmacology, National Yang-Ming University, Taipei, Taiwan Correspondence to: Kuen-Feng Chen, email: // Ling-Ming Tseng, email: // Keywords : lapatinib, triple-negative breast cancer, PP2A, CIP2A, apoptosis Received : July 07, 2015 Accepted : January 19, 2016 Published : January 27, 2016 Abstract We tested the efficacy of lapatinib, a dual tyrosine kinase inhibitor which interrupts the HER2 and epidermal growth factor receptor (EGFR) pathways, in a panel of triple-negative breast cancer (TNBC) cells, and examined the drug mechanism. Lapatinib showed an anti-proliferative effect in HCC 1937, MDA-MB-468, and MDA-MB-231 cell lines. Lapatinib induced significant apoptosis and inhibited CIP2A and p-Akt in a dose and time-dependent manner in the three TNBC cell lines. Overexpression of CIP2A reduced lapatinib-induced apoptosis in MDA-MB-468 cells. In addition, lapatinib increased PP2A activity (in relation to CIP2A inhibition). Moreover, lapatinib-induced apoptosis and p-Akt downregulation was attenuated by PP2A antagonist okadaic acid. Furthermore, lapatinib indirectly decreased CIP2A transcription by disturbing the binding of Elk1 to the CIP2A promoter. Importantly, lapatinib showed anti-tumor activity in mice bearing MDA-MB-468 xenograft tumors, and suppressed CIP2A as well as p-Akt in these xenografted tumors. In summary, inhibition of CIP2A determines the effects of lapatinib-induced apoptosis in TNBC cells. In addition to being a dual tyrosine kinase inhibitor of HER2 and EGFR, lapatinib also inhibits CIP2A/PP2A/p-Akt signaling in TNBC cells.
'/%3e%3cuse xlink:href='%23a' transform='rotate(60)'/%3e%3ccircle r='17' fill='%23000095'/%3e%3ccircle r='15' fill='%23fff'/%3e%3c/svg%3e)