Manufacturing Sentiment: Forecasting Industrial Production With Text Analysis

This study is theoretical on the sentiment analysis field of deep learning-based natural language processing, which is the world's advanced technology, namely data collection and preprocessing stage, tokenizing stage, Sentiment Dictionary construction stage, positive and negative word extraction stage through sentiment analysis, deep learning introduces major contents and related technologies such as model configuration, execution stage, and data visualization stage. In addition, speech processing technology performed in the data collection stage, STT (Speech to Text) and TTS (Text to Speech) technology will be introduced. In this study, a program was written using various open sources (libraries) including ’keras’ 2.0 version used in the deep learning natural language processing field of the python language base. This study is executed to help students who are studying deep learning natural language processing.

With advances in deep learning and natural language processing (NLP), the analysis of medical texts is becoming increasingly important. Nonetheless, despite the importance of processing medical texts, no research on Korean medical-specific language models has been conducted. The Korean medical text is highly difficult to analyze because of the agglutinative characteristics of the language, as well as the complex terminologies in the medical domain. To solve this problem, we collected a Korean medical corpus and used it to train the language models. In this paper, we present a Korean medical language model based on deep learning NLP. The model was trained using the pre-training framework of BERT for the medical context based on a state-of-the-art Korean language model. The pre-trained model showed increased accuracies of 0.147 and 0.148 for the masked language model with next sentence prediction. In the intrinsic evaluation, the next sentence prediction accuracy improved by 0.258, which is a remarkable enhancement. In addition, the extrinsic evaluation of Korean medical semantic textual similarity data showed a 0.046 increase in the Pearson correlation, and the evaluation for the Korean medical named entity recognition showed a 0.053 increase in the F1-score.

Validation of deep learning models should separately consider bedside chest radiographs (CXRs) as they are the most challenging to interpret, while at the same time the resulting diagnoses are important for managing critically ill patients. Therefore, we aimed to develop and evaluate deep learning models for the identification of clinically relevant abnormalities in bedside CXRs, using reference standards established by computed tomography (CT) and multiple radiologists. In this retrospective study, a dataset consisting of 18,361 bedside CXRs of patients treated at a level 1 medical center between January 2009 and March 2019 was used. All included CXRs occurred within 24 hours before or after a chest CT. A deep learning algorithm was developed to identify 8 findings on bedside CXRs (cardiac congestion, pleural effusion, air-space opacification, pneumothorax, central venous catheter, thoracic drain, gastric tube, and tracheal tube/cannula). For the training dataset, 17,275 combined labels were extracted from the CXR and CT reports by a deep learning natural language processing (NLP) tool. In case of a disagreement between CXR and CT, human-in-the-loop annotations were used. The test dataset consisted of 583 images, evaluated by 4 radiologists. Performance was assessed by area under the receiver operating characteristic curve analysis, sensitivity, specificity, and positive predictive value. Areas under the receiver operating characteristic curve for cardiac congestion, pleural effusion, air-space opacification, pneumothorax, central venous catheter, thoracic drain, gastric tube, and tracheal tube/cannula were 0.90 (95% confidence interval [CI], 0.87-0.93; 3 radiologists on the receiver operating characteristic [ROC] curve), 0.95 (95% CI, 0.93-0.96; 3 radiologists on the ROC curve), 0.85 (95% CI, 0.82-0.89; 1 radiologist on the ROC curve), 0.92 (95% CI, 0.89-0.95; 1 radiologist on the ROC curve), 0.99 (95% CI, 0.98-0.99), 0.99 (95% CI, 0.98-0.99), 0.98 (95% CI, 0.97-0.99), and 0.99 (95% CI, 0.98-1.00), respectively. A deep learning model used specifically for bedside CXRs showed similar performance to expert radiologists. It could therefore be used to detect clinically relevant findings during after-hours and help emergency and intensive care physicians to focus on patient care.

Developing a deep learning natural language processing algorithm for automated reporting of adverse drug reactions

BackgroundTimely diagnosis of dementia is important to patients and their caregivers for advanced planning, yet dementia is under‐diagnosed by healthcare professionals and under‐coded in claims data. Sensitive and specific tools to detect cognitive concerns in diverse clinical settings could prompt referral for cognitive evaluation and specialist care.MethodWe developed a deep learning natural language processing (NLP) method to detect cognitive concerns in unstructured clinician notes from electronic health records (EHR). We leveraged a gold‐standard set of ∼1000 patients sampled randomly from three strata: patients with diagnosis codes, patients with specialist visits but no code, or patients with neither. The physician performed a detailed chart review and adjudication of cognitive status, noting "cognitive concern" (i.e., any evidence of cognitive difficulties) and rating patients on a 5‐point scale: normal, normal vs. MCI, MCI, MCI vs. dementia, and dementia. We used 10% of the labeled data as a test set and the remaining 90% for training and validation of the model to classify patients with any cognitive concerns (normal vs. other). We also built a web‐based chart review annotation tool that facilitates labeling and enables an active learning loop to scale up labeling to thousands of charts.ResultIn a random sample from the gold‐standard dataset, 30 out of 80 patients with cognitive concerns had no diagnosis code or medication related to dementia; we hypothesized that our deep learning tool could leverage clinical text to improve detection of cognitive concerns. Indeed, a model with codes and medications had an area under the receiver operating characteristic (AUROC) curve of 0.79, sensitivity of 0.59, and specificity of 1.00 for the binary classification task. The deep learning model improved the AUROC to 0.90, increased sensitivity to 0.79, and maintained specificity of 0.98. Notes from primary care, specialties such as neurology and psychiatry, and social workers had the highest likelihood of containing information.ConclusionThe deep learning model was successful in detecting cases without a dementia‐related diagnosis code or medication. Automatic processing of electronic medical records with a deep learning tool can be used for early detection of cognitive concern to optimize patient care and predict hospital readmission.

Patient-reported outcomes (PROs) are essential in evaluating aesthetic procedures. RealSelf is an online platform for cosmetic and reconstructive feedback. Currently, no validated PRO tools exist to compare Kybella (synthetic deoxycholic acid; AbbVie Pharmaceuticals, North Chicago, IL) with submental liposuction. Robust optimizing Bidirectional Encoder Representation from Transformers, a deep learning natural language processing (NLP) model, can analyze emotions and sentiment in text and was used compare patient-reported experiences for Kybella and submental liposuction on RealSelf. RealSelf was queried for English reviews of Kybella and submental liposuction from 2014 to 2024. Reviews were excluded if they lacked procedural details, focused on the provider, or included adjunct procedures such as a necklift or Botox. Two NLP models analyzed posts: 1 characterized posts as positive or negative (scored 0-1); The latter scored each post from 0 to 1 ∼7 emotions-fear, sadness, anger, disgust, neutral, surprise, and joy. Overall, 1338 posts met the inclusion criteria: 753 for submental liposuction and 585 for Kybella. A greater proportion of liposuction reviews were positive compared with Kybella (83.4% vs 55.2%, P < .00001). Liposuction also had significantly higher mean positive scores (0.73 vs 0.41, P < .0001). Joy was the most common emotion for liposuction reviews (51.3%), whereas Kybella reviews more often reflected sadness (17.9%) and fear (12%), with fewer expressing joy (22.7%). The authors of this study applied NLP to extract structured sentiment from unstructured reviews RealSelf. Our findings suggest that submental liposuction patients report greater satisfaction and more positive emotional experiences than those who receive Kybella.

This study delves into the undergraduate Chinese-Foreign Cooperative Education programs to explore the trends in the internationalization of higher education in China. Utilizing two datasets, we first evaluate the program listings from the Ministry of Education from 2018 to 2024, focusing on collaborative patterns between regions and institutions. Secondly, this research independently extracts data from Weibo to perform sentiment analysis on discussions related to top-ranked education programs, particularly around the period six months before and after the Gaokao from 2020 to 2024. Our methodologies include data cleaning, categorization, statistical analysis, and the application of advanced Deep Learning Natural Language Processing (NLP) techniques, notably the BERT [1] model. The study reveals temporal fluctuations in program development, regional disparities, and trends in student sentiment, providing valuable insights for policy making and educational reform. This comprehensive analysis aids in deepening our understanding of the evolution of educational programs and student engagement within the context of global education trends.

BackgroundElectronic Health Records (EHR) with large sample sizes and rich information offer great potential for dementia research, but current methods of phenotyping cognitive status are either not scalable or suffer from inaccuracies. Our objective is to evaluate whether deep learning Natural Language Processing (NLP)‐powered semi‐automated annotation can improve the speed and reliability of chart reviews for phenotyping cognitive status.MethodIn this study we developed and evaluated a semi‐automated NLP‐powered annotation tool (NAT) to facilitate phenotyping of cognitive status. Clinical experts adjudicated the cognitive status of 627 patients at Mass General Brigham (MGB) Healthcare using NAT or traditional chart reviews. Patient charts contained EHR data from two datasets: (1) Records from January 1, 2017 to December 31, 2018 for 100 Medicare beneficiaries from the MGB Accountable Care Organization (ACO), and (2) Records from 2‐years pre‐COVID diagnosis to the date of COVID diagnosis for 527 MGB patients. All EHR data from the relevant period were extracted; diagnosis codes, medications, and laboratory test values were processed and summarized. Clinical notes were processed through a deep learning NLP algorithm and a web tool was developed to present an integrated view of all data. Cognitive status was rated as cognitively normal, cognitively impaired, or undetermined. Assessment time and interrater agreement of NAT compared to manual chart reviews for cognitive status phenotyping was evaluated.ResultNAT adjudication provided higher interrater agreement (Cohen k = 0.89 vs. k = 0.80) and significant speed up (time difference mean [SD]: 1.4 [1.3] minutes, P &lt; 0.001; ratio median [min, max]: 2.2 [0.4, 20]) over manual chart reviews. There was moderate agreement with manual chart reviews (Cohen k = 0.67). In the cases that exhibited disagreement with manual chart review, NAT adjudication was able to produce assessments that had broader clinical consensus due to its integrated view of highlighted relevant information and semi‐automated NLP features.ConclusionNAT adjudication improves the speed and reliability for phenotyping cognitive status compared to manual chart reviews. This study underscores the potential of an NLP‐based clinically adjudicated method to build large‐scale dementia research cohorts from EHR.

Due to the influence of psychological factors during sports, basketball players often change the shooting rhythm in sports, which will reduce the shooting rate and directly affect the training effect. Therefore, we need to analyze the basketball shooting process of some athletes, which is not a complete negation of traditional training methods, but a psychological analysis of some athletes’ shooting in the course of competition, so as to complement the feedback and training information after the game. With the great improvement of computer computing power, deep learning natural language processing can help people analyze and solve previously unsolvable problems in production and life. The psychological emotion of adolescence has a great influence on the study and life of middle school students. At present, the unified monitoring and analysis of the daily life of middle school students need not only a lot of manpower, but also slow speed. If the psychological problems are not found in time and feedback is given, it will cause a series of adverse effects on individual athletes. The neural network model based on deep learning can process students' daily mass text information quickly and accurately, and then give comprehensive judgment, which is a good solution. This paper applies the neural network algorithm of the Bi-LSTM model and CNN model to study the text data, and finally has 95.55% and 90.03% accuracy in the psychological analysis experiment, which provides a feasible solution to solve the batch rapid analysis of psychological changes reflected in the daily text of athletes during basketball. Some suggestions are put forward on how to strengthen and improve the psychological quality of college basketball players and their ability to bear pressure and difficulties.

Introduction: Statins are guideline-recommended and potentially life-saving for individuals with diabetes. Yet, statin use is concerningly low in this group. Identifying reasons for statin nonuse can inform targeted interventions. We hypothesize that clinical reasoning around reasons for statin nonuse may be buried in unstructured, narrative portions of the electronic health record (EHR). We aimed to identify reasons for statin nonuse in patients with diabetes from unstructured EHRs using deep learning. Methods: Adults diagnosed with diabetes from 2014 to 2020 with no statin prescriptions were identified from a multisite EHR health system in Northern California. We used a benchmark deep learning natural language processing (NLP) approach, Clinical Bidirectional Encoder Representations from Transformers (BERT), to identify statin nonuse and reasons for statin nonuse from unstructured EHRs. Clinical BERT was evaluated against expert clinician review in 20% test sets. Results: Of 33,461 patients with diabetes (mean age 59+15y, 49% women, 36% White, 24% Asian, 15% Hispanic), nearly half (47%) lacked statin prescriptions. By leveraging unstructured data containing any mention of statin-related terms, Clinical BERT accurately identified statin nonuse (area under the receiver operating characteristic curve (AUC 0.99 [0.98-1.0]) and identified key patient, clinician, and system reasons for statin nonuse, including statin-associated side effects, guideline-discordant clinician practice, and patient hesitancy (AUC 0.90 [0.86-0.93]; Figure). Conclusions: In a multiethnic diabetes cohort, we identified actionable reasons for statin nonuse using a deep learning approach to mine unstructured EHRs. Findings may enable targeted interventions to improve guideline-directed statin use and be readily scaled to other evidence-based therapies.

Background Statins are guideline-recommended medications that reduce cardiovascular events in patients with diabetes. Yet, statin use is concerningly low in this high-risk population. Identifying reasons for statin nonuse, which are typically described in unstructured electronic health record data, can inform targeted system interventions to improve statin use. We aimed to leverage a deep learning approach to identify reasons for statin nonuse in patients with diabetes. Methods and Results Adults with diabetes and no statin prescriptions were identified from a multiethnic, multisite Northern California electronic health record cohort from 2014 to 2020. We used a benchmark deep learning natural language processing approach (Clinical Bidirectional Encoder Representations from Transformers) to identify statin nonuse and reasons for statin nonuse from unstructured electronic health record data. Performance was evaluated against expert clinician review from manual annotation of clinical notes and compared with other natural language processing approaches. Of 33 461 patients with diabetes (mean age 59±15 years, 49% women, 36% White patients, 24% Asian patients, and 15% Hispanic patients), 47% (15 580) had no statin prescriptions. From unstructured data, Clinical Bidirectional Encoder Representations from Transformers accurately identified statin nonuse (area under receiver operating characteristic curve [AUC] 0.99 [0.98-1.0]) and key patient (eg, side effects/contraindications), clinician (eg, guideline-discordant practice), and system reasons (eg, clinical inertia) for statin nonuse (AUC 0.90 [0.86-0.93]) and outperformed other natural language processing approaches. Reasons for nonuse varied by clinical and demographic characteristics, including race and ethnicity. Conclusions A deep learning algorithm identified statin nonuse and actionable reasons for statin nonuse in patients with diabetes. Findings may enable targeted interventions to improve guideline-directed statin use and be scaled to other evidence-based therapies.

Based on this method, this paper deeply researches natural language processing,based on deep learning, and applies deep learning to natural language processing in order to obtain more accurate results in analyzing the similarity of words in natural language, and combines this method to develop Deep learning natural language processing system for network public opinion analysis. This paper needs to constantly update the existing corpus in the process of processing data, so it is necessary to build a corresponding corpus data server to store real-time corpus data and complete the preliminary processing of corpus data in the database. Segmentation to get data that can be used for deep learning.

Pathology reports contain the essential data for both clinical and research purposes. However, the extraction of meaningful, qualitative data from the original document is difficult due to the narrative and complex nature of such reports. Keyword extraction for pathology reports is necessary to summarize the informative text and reduce intensive time consumption. In this study, we employed a deep learning model for the natural language process to extract keywords from pathology reports and presented the supervised keyword extraction algorithm. We considered three types of pathological keywords, namely specimen, procedure, and pathology types. We compared the performance of the present algorithm with the conventional keyword extraction methods on the 3115 pathology reports that were manually labeled by professional pathologists. Additionally, we applied the present algorithm to 36,014 unlabeled pathology reports and analysed the extracted keywords with biomedical vocabulary sets. The results demonstrated the suitability of our model for practical application in extracting important data from pathology reports.

PURPOSECollecting information on clinical outcomes (recurrence/progression) from complex treatment courses in non–muscle invasive bladder cancer (NMIBC) is challenging and time-consuming. We developed a deep learning natural language processing model to assess outcomes in patients with NMIBC using vast data from electronic health records (EHRs).METHODSThis retrospective study analyzed data from Japanese adults with NMIBC who started Bacillus Calmette-Guérin (BCG) induction therapy between April 2016 and June 2022. A Bidirectional Encoder Representations from Transformers (BERT) model was trained to classify outcomes, supported by human review for past history records. The model's performance was assessed by precision, recall, and F1 scores. We compared the effectiveness of BCG therapy between completion (patients who completed therapy) and non-completion groups. RESULTSOf 372 patients studied, 79.3% and 20.7% were in the completion group and the non-completion group, respectively. The final BERT model achieved average F1 scores of 0.91 and 0.98 for time to recurrence (TTR), and 0.74 and 0.94 for time to progression (TTP) before and after human support, respectively. The hazard ratio for TTR in BCG completion versus non-completion groups was 0.40 (95% CI, 0.26 to 0.62) by a multivariate Cox proportional hazard model and 0.41 (95% CI, 0.26 to 0.63) by inverse probability of treatment weighting.CONCLUSIONThe developed model could compare the clinical outcomes between treatments in patients with NMIBC using EHRs. Human support, although required, was needed in only 10% documents and was deemed feasible. The model was able to demonstrate the difference in TTR and TTP between BCG completion and non-completion groups.

Through conversation, humans relay complex information through the alternation of speech production and comprehension. The neural mechanisms that underlie these complementary processes or through which information is precisely conveyed by language, however, remain poorly understood. Here, we used pretrained deep learning natural language processing models in combination with intracranial neuronal recordings to discover neural signals that reliably reflect speech production, comprehension, and their transitions during natural conversation between individuals. Our findings indicate that neural activities that encoded linguistic information were broadly distributed throughout frontotemporal areas across multiple frequency bands. We also find that these activities were specific to the words and sentences being conveyed and that they were dependent on the word's specific context and order. Finally, we demonstrate that these neural patterns partially overlapped during language production and comprehension and that listener-speaker transitions were associated with specific, time-aligned changes in neural activity. Collectively, our findings reveal a dynamical organization of neural activities that subserve language production and comprehension during natural conversation and harness the use of deep learning models in understanding the neural mechanisms underlying human language.