Prediction of Hemorrhagic Transformation after Ischemic Stroke Using Machine Learning.

Hemorrhagic transformation (HT) is one of the leading causes of a poor prognostic marker after acute ischemic stroke (AIS). We compared the performances of the several machine learning (ML) algorithms to predict HT after AIS using only structured data. A total of 2028 patients with AIS, who were admitted within seven days of symptoms onset, were included in this analysis. HT was defined based on the criteria of the European Co-operative Acute Stroke Study-II trial. The whole dataset was randomly divided into a training and a test dataset with a 7:3 ratio. Binary logistic regression, support vector machine, extreme gradient boosting, and artificial neural network (ANN) algorithms were used to assess the performance of predicting the HT occurrence after AIS. Five-fold cross validation and a grid search technique were used to optimize the hyperparameters of each ML model, which had its performance measured by the area under the receiver operating characteristic (AUROC) curve. Among the included AIS patients, the mean age and number of male subjects were 69.6 years and 1183 (58.3%), respectively. HT was observed in 318 subjects (15.7%). There were no significant differences in corresponding variables between the training and test dataset. Among all the ML algorithms, the ANN algorithm showed the best performance in terms of predicting the occurrence of HT in our dataset (0.844). Feature scaling including standardization and normalization, and the resampling strategy showed no additional improvement of the ANN's performance. The ANN-based prediction of HT after AIS showed better performance than the conventional ML algorithms. Deep learning may be used to predict important outcomes for structured data-based prediction.

Prediction of Stroke Outcome Using Natural Language Processing-Based Machine Learning of Radiology Report of Brain MRI.

Brain magnetic resonance imaging (MRI) is useful for predicting the outcome of patients with acute ischemic stroke (AIS). Although deep learning (DL) using brain MRI with certain image biomarkers has shown satisfactory results in predicting poor outcomes, no study has assessed the usefulness of natural language processing (NLP)-based machine learning (ML) algorithms using brain MRI free-text reports of AIS patients. Therefore, we aimed to assess whether NLP-based ML algorithms using brain MRI text reports could predict poor outcomes in AIS patients. This study included only English text reports of brain MRIs examined during admission of AIS patients. Poor outcome was defined as a modified Rankin Scale score of 3-6, and the data were captured by trained nurses and physicians. We only included MRI text report of the first MRI scan during the admission. The text dataset was randomly divided into a training and test dataset with a 7:3 ratio. Text was vectorized to word, sentence, and document levels. In the word level approach, which did not consider the sequence of words, and the "bag-of-words" model was used to reflect the number of repetitions of text token. The "sent2vec" method was used in the sensation-level approach considering the sequence of words, and the word embedding was used in the document level approach. In addition to conventional ML algorithms, DL algorithms such as the convolutional neural network (CNN), long short-term memory, and multilayer perceptron were used to predict poor outcomes using 5-fold cross-validation and grid search techniques. The performance of each ML classifier was compared with the area under the receiver operating characteristic (AUROC) curve. Among 1840 subjects with AIS, 645 patients (35.1%) had a poor outcome 3 months after the stroke onset. Random forest was the best classifier (0.782 of AUROC) using a word-level approach. Overall, the document-level approach exhibited better performance than did the word- or sentence-level approaches. Among all the ML classifiers, the multi-CNN algorithm demonstrated the best classification performance (0.805), followed by the CNN (0.799) algorithm. When predicting future clinical outcomes using NLP-based ML of radiology free-text reports of brain MRI, DL algorithms showed superior performance over the other ML algorithms. In particular, the prediction of poor outcomes in document-level NLP DL was improved more by multi-CNN and CNN than by recurrent neural network-based algorithms. NLP-based DL algorithms can be used as an important digital marker for unstructured electronic health record data DL prediction.

Physicochemical, molecular, emulsifying and rheological characterizations of sage (Salvia splendens) seed gum.

The objective was to investigate the physicochemical, molecular, rheological, and emulsifying properties of water soluble-sage seed gum (WSG). WSG mainly comprised galacturonic acid and xylose. FTIR and NMR analyses confirmed the presence of pectic polysaccharides in WSG. Additionally, the molecular weight of WSG was higher than that of pectin standard. Compared to pectin standard solutions, WSG solutions exhibited higher shear thinning behavior and higher values of apparent viscosity (ηa,100) and consistency index (K) in steady shear measurements. According to the results of frequency sweep test, the dynamic moduli (G' and G″) for WSG solutions were increased with increasing frequency and concentration. The changes in dynamic moduli of WSG solutions as a function of aging time at 4 °C indicated that WSG could form a more rigid network than pectin standard. According to the results of temperature sweep test, the dynamic moduli of WSG solutions were higher than those of pectin standard solutions. Emulsion capacity and stability analyses indicated that WSG (58 and 56%, respectively) had better emulsifying properties than pectin standard (46 and 37%). In conclusion, compared to pectin standard, superior rheological and emulsifying properties observed in WSG might be related to higher molecular weight and protein content, respectively.

Evaluation of changes in random blood glucose and body mass index during and after completion of chemotherapy in children with acute lymphoblastic leukemia.

PURPOSE: Improved survival of patients with childhood acute lymphoblastic leukemia (ALL) has drawn attention to the potential for late consequences of previous treatments among survivors, including metabolic syndrome. In this study, we evaluated changes in 3 parameters, namely, random blood glucose, body mass index (BMI), and Z score for BMI (Z-BMI), in children with ALL during chemotherapy and after completion of treatment. METHODS: Patients newly diagnosed with ALL from January, 2005 to December, 2008 at Saint Mary's Hospital, The Catholic University of Korea, who completed treatment with chemotherapy only were included (n=107). Random glucose, BMI, and Z-BMI were recorded at 5 intervals: at diagnosis, before maintenance treatment, at completion of maintenance treatment, and 6 and 12 months after completion of maintenance treatment. Similar analyses were conducted on 2 subcohorts based on ALL risk groups. RESULTS: For random glucose, a paired comparison showed significantly lower levels at 12 months post-treatment compared to those at initial diagnosis (P<0.001) and before maintenance (P<0.001). The Z-BMI score was significantly higher before maintenance than at diagnosis (P<0.001), but decreased significantly at the end of treatment (P<0.001) and remained low at 6 months (P<0.001) and 12 months (P<0.001) post-treatment. Similar results were obtained upon analysis of risk group-based subcohorts. CONCLUSION: For a cohort of ALL patients treated without allogeneic transplantation or cranial irradiation, decrease in random glucose and Z-BMI after completion of chemotherapy does not indicate future glucose intolerance or obesity.

Microstructural properties at the interfaces of ZnO nanorods and ZnO homo-buffer layers.

Uniformly and vertically well-aligned ZnO nanorods were fabricated in-situ and ex-situ on ZnO films using a catalyst-free metal-organic chemical vapor process. Microstructural properties of the initial growth of ZnO nanorods on ZnO films with different surface roughnesses were investigated. We observed that the ZnO nanorods grown on ZnO films with surface roughness of less than 1.0 nm were well-aligned along the c-axis and in the ab-plane. When the nanorods grew on ZnO films with a large surface roughness, they had three different growth directions of 28 degrees, 62 degrees, and 90 degrees to the film surface. The slant angle of 62 degrees corresponds to the angle between the ZnO(001) and (101) planes. The initial growth direction difference caused structural disorder at the interface of the ZnO nanorod and film, and prevented epitaxial growth and the alignment of the nanorods.