Natural Language Processing Algorithms Research Articles

Readability and Writing Quality in Radiation Oncology Journal Articles from 2004 to 2024

PurposeScientific literature is a vital tool which we rely upon to communicate the findings of our studies; however, we rarely direct our study to the writing itself. Methods and MaterialsHere, we make use of modern natural language processing algorithms coupled with the large, open access PubMed Central corpus to analyze trends in writing complexity within the field of radiation oncology from 2004–2024. Changes in 1) required grade-level to comprehend, 2) lexical complexity, and 3) information content were assessed. Articles were also classified—and then analyzed—by disease subsite. ResultsWe found significant increases in the three domains over the twenty-year collection period. Genitourinary literature had the greatest readability while gastrointestinal literature was the most complex. ConclusionsThis analysis reveals broad increases in the complexity of our writing. This study demonstrates metrics to use, and benchmark values to refer to, to evaluate the complexity of radiation oncology journal articles.

Development of a natural language processing algorithm for the detection of spinal metastasis based on magnetic resonance imaging reports

BackgroundMetastasis to the spinal column is a common complication of malignancy, potentially causing pain and neurologic injury. An automated system to identify and refer patients with spinal metastases can help overcome barriers to timely treatment. We describe the training, optimization and validation of a natural language processing algorithm to identify the presence of vertebral metastasis and metastatic epidural cord compression (MECC) from radiology reports of spinal MRIs. MethodsReports from patients with spine MRI studies performed between January 1, 2008 and April 14, 2019 were reviewed by a team of radiologists to assess for the presence of cancer and generate a labeled dataset for model training. Using regular expression, impression sections were extracted from the reports and converted to all lower-case letters with all nonalphabetic characters removed. The reports were then tokenized and vectorized using the doc2vec algorithm. These were then used to train a neural network to predict the likelihood of spinal tumor or MECC. For each report, the model provided a number from 0 to 1 corresponding to its impression. We then obtained 111 MRI reports from outside the test set, 92 manually labeled negative and 19 with MECC to test the model's performance. ResultsAbout 37,579 radiology reports were reviewed. About 36,676 were labeled negative, and 903 with MECC. We chose a cutoff of 0.02 as a positive result to optimize for a low false negative rate. At this threshold we found a 100% sensitivity rate with a low false positive rate of 2.2%. ConclusionsThe NLP model described predicts the presence of spinal tumor and MECC in spine MRI reports with high accuracy. We plan to implement the algorithm into our EMR to allow for faster referral of these patients to appropriate specialists, allowing for reduced morbidity and increased survival.

Machine Learning and Natural Language Processing Algorithms in the Remote Mobile Medical Diagnosis System of Internet Hospitals

In order to alleviate the contradiction between supply and demand of professional pharmacists, integrate medical resources, and ensure the safety of patients’ medication, the telemedicine diagnosis system has played a great role. Today, in this “Internet +” era, all walks of life have begun to integrate with Internet technology. The purpose of this article was to discuss the practical utility of machine learning and natural language processing algorithms in the remote mobile medical diagnosis system of Internet hospitals, for which this article conducted in-depth discussion. This article first introduced the basic concepts, development, and characteristics of machine learning and natural language processing algorithms in detail, and carefully studied and analyzed the development and culture of traditional offline medical diagnosis models. Based on machine learning and natural language processing algorithms, a remote mobile medical diagnosis is designed. By combining with the medical diagnosis system of traditional hospitals, a new type of remote mobile medical diagnosis system for Internet hospitals was designed and developed, and the combination of traditional medical industry and Internet technology was deeply studied. According to each functional requirement, the image module, heart rate measurement module, and user setting module are designed, respectively. Compared to traditional medical diagnosis systems, the accuracy of the remote mobile medical diagnosis system based on machine learning applied in Internet hospital diagnosis in this article reached 80% or even higher. At the same time, it was found through experiments that when the evolution number was 3, the maximum fit value and average fit value were the same, both of which were 0.6. This indicates that the system can accommodate more than 10,000 people at the same time, and patients can receive good treatment plans, with a very broad application prospect

Entertainment robots based on smartphone terminals for mobile network music E-learning mode

This study adopted the method of system requirements analysis to design the functions and structure of the network music E-learning mode system on smartphone terminals. Through research and user requirement analysis, the core functions and requirements of the system were determined, and the system was designed in terms of functionality and structure. The system’s functional design adopts speech recognition technology, enabling entertainment robots to accurately understand user voice commands and questions. Through natural language processing and machine learning algorithms, entertainment robots can analyze user needs and recommend suitable music teaching resources based on their interests and learning goals. Divide the system into two parts: front-end and back-end. The front-end is the user interface, and through a user-friendly graphical interface and interactive design, users can easily operate the system and interact with entertainment robots. The backend is the core processing part of the system, which achieves the application of entertainment robots in the network music E-learning mode on smartphone terminals through the collaboration of the front-end and back-end. The entertainment robot based on smartphone terminals has high effectiveness and feasibility in the application of mobile network music E-learning mode. The performance test results of the system indicate that it can run stably and meet the concurrent needs of a large number of users.

USING NATURAL LANGUAGE PROCESSING (NLP) FOR CATEGORIZING PAPER TITLES FROM GOOGLE FORMS

<p>Modern data collection, storage, and processing rely on diverse techniques to handle various types of information, ranging from structured tables to free-form text. This paper explores the captivating application of Natural Language Processing (NLP) for categorizing titles from Google Forms or any other textual data. The process of training an NLP model will be demonstrated through a specific example. Just as we learn from our past experiences, NLP models need to be fed with relevant data and labels. This ensures accurate and efficient processing even when new titles are introduced. We will conclude with a fascinating demonstration of how NLP algorithms analyze the structure and meaning of titles. By identifying keywords and understanding the context, they can automatically classify titles into relevant categories. This dramatically simplifies data organization and analysis, empowering us to extract valuable insights faster.</p>

AI-Enhanced Fintech communication: Leveraging Chatbots and NLP for efficient banking support

The convergence of artificial intelligence (AI) and financial technology (fintech) has revolutionized the way banks and financial institutions communicate with customers. This paper explores the use of AI-enhanced fintech communication, focusing on the utilization of chatbots and natural language processing (NLP) to provide efficient banking support. AI-powered chatbots have become indispensable tools for banks seeking to enhance customer service and streamline communication channels. By leveraging NLP algorithms, these chatbots can understand and respond to customer queries in real-time, providing personalized assistance round-the-clock. The integration of AI into fintech communication enables banks to offer seamless and efficient support, improving customer satisfaction and loyalty. The key to the effectiveness of AI-enhanced fintech communication lies in the ability of chatbots to interpret and respond to natural language input accurately. NLP algorithms enable chatbots to analyze and understand the intent behind customer queries, allowing them to provide relevant and contextually appropriate responses. This capability enhances the overall customer experience by reducing response times and ensuring that customers receive accurate and helpful information. Furthermore, AI-powered chatbots can handle a wide range of inquiries, from basic account inquiries to complex financial transactions. By automating routine tasks and inquiries, banks can free up human agents to focus on more complex and value-added activities. This not only improves operational efficiency but also allows banks to deliver faster and more responsive customer service. In addition to providing support to customers, AI-enhanced fintech communication can also help banks gather valuable insights into customer preferences and behavior. By analyzing interactions between customers and chatbots, banks can identify trends, anticipate customer needs, and tailor their products and services accordingly. This data-driven approach enables banks to offer more personalized and targeted offerings, leading to increased customer satisfaction and loyalty. In conclusion, AI-enhanced fintech communication, powered by chatbots and NLP, offers significant benefits for banks and financial institutions. By leveraging AI technology, banks can provide efficient and personalized support to customers, improve operational efficiency, and gain valuable insights into customer behavior. As AI continues to advance, the future of fintech communication promises even greater efficiency, personalization, and innovation in banking support. Keywords: Al- Enhanced, Fintech Communication, Leveraging, Chatbots, NLP.

Identifying X (Formerly Twitter) Posts Relevant to Dementia and COVID-19: Machine Learning Approach.

During the pandemic, patients with dementia were identified as a vulnerable population. X (formerly Twitter) became an important source of information for people seeking updates on COVID-19, and, therefore, identifying posts (formerly tweets) relevant to dementia can be an important support for patients with dementia and their caregivers. However, mining and coding relevant posts can be daunting due to the sheer volume and high percentage of irrelevant posts. The objective of this study was to automate the identification of posts relevant to dementia and COVID-19 using natural language processing and machine learning (ML) algorithms. We used a combination of natural language processing and ML algorithms with manually annotated posts to identify posts relevant to dementia and COVID-19. We used 3 data sets containing more than 100,000 posts and assessed the capability of various algorithms in correctly identifying relevant posts. Our results showed that (pretrained) transfer learning algorithms outperformed traditional ML algorithms in identifying posts relevant to dementia and COVID-19. Among the algorithms tested, the transfer learning algorithm A Lite Bidirectional Encoder Representations from Transformers (ALBERT) achieved an accuracy of 82.92% and an area under the curve of 83.53%. ALBERT substantially outperformed the other algorithms tested, further emphasizing the superior performance of transfer learning algorithms in the classification of posts. Transfer learning algorithms such as ALBERT are highly effective in identifying topic-specific posts, even when trained with limited or adjacent data, highlighting their superiority over other ML algorithms and applicability to other studies involving analysis of social media posts. Such an automated approach reduces the workload of manual coding of posts and facilitates their analysis for researchers and policy makers to support patients with dementia and their caregivers and other vulnerable populations.

PARIBHAASHA

As in world increasingly reliant on digital communication, effective writing skills are paramount. However, for “Hindi” language users, finding tools that take their unique linguistic needs presents a challenge. This abstract will come with a novel solution: a Grammarly-like platform precisely designed to empower Hindi writers by offering advanced language correction and enhancement features tailored specifically for the nuances of the Hindi language. At the core of our platform lies a sophisticated text analysis engine, powered by state-of-the-art natural language processing algorithms meticulously trained on vast corpora of Hindi text. Our platform offers a seamless user experience, with a user-friendly interface designed to facilitate effortless interaction in single time of corrections. Users can simply input their “Hindi” text into the platform, and within moments, receive comprehensive feedback and suggestions aimed at refining their writing to perfection. In addition to its high dynamic language correction capabilities, our platform also features advanced plagiarism detection functionality. Leveraging cutting-edge algorithms that is particular focusing on platform thoroughly scans user-submitted text against an extensive database of online sources, academic papers, and published works to ensure originality and integrity, vulnerable and fully secured. Furthermore, our platform goes beyond mere error correction to offer personalized writing insights and guidance. Users can set custom writing goals based on their intended audience, style preferences, and communication objectives. Our platform then provides tailored suggestions and recommendations aimed at helping users achieve their desired writing outcomes, whether it be crafting formal business documents, creative literature, or casual social media posts. This engine enables our platform to accurately identify and rectify a myriad of grammatical errors, spelling mistakes, and stylistic inconsistencies commonly encountered in Hindi writing.

Comparison of Diagnosis Codes to Clinical Notes in Classifying Patients with Diabetic Retinopathy

PurposeElectronic health records (EHR) contain a vast amount of clinical data. Improved, automated classification approaches have the potential to accurately and efficiently identify patient cohorts for research. We evaluated if a rule-based natural language processing (NLP) algorithm using clinical notes performed better for classifying proliferative diabetic retinopathy (PDR) and non-proliferative diabetic retinopathy (NPDR) severity compared to International Classification of Diseases 9th or 10th edition (ICD) codes. DesignCross-sectional study SubjectsDe-identified EHR data from an academic medical center identified 2366 patients aged ≥18 years, with diabetes mellitus, diabetic retinopathy, and available clinical notes. MethodsFrom these 2366 patients, 306 random patients (100 training set, 206 test set) underwent chart review by ophthalmologists to establish the gold standard. ICD codes were extracted from the EHR. The notes algorithm identified positive mention of PDR and NPDR severity from clinical notes. PDR and NPDR severity classification by ICD codes and the notes algorithm were compared to the gold standard. The entire diabetic retinopathy cohort (N=2366) was then classified as having presence (or absence) of PDR using ICD codes and the notes algorithm. Main Outcome MeasuresSensitivity, specificity, positive predictive value (PPV), negative predictive value, F1 score for the notes algorithm compared to ICD codes using a gold standard of chart review. ResultsFor PDR classification of the test set patients, the notes algorithm performed better than ICD codes for all metrics. Specifically, the notes algorithm had significantly higher sensitivity (90.5% [95% CI 85.7, 94.9] vs 68.4% [60.4, 75.3]), but similar PPV (98.0% [95.4-100] vs 94.7% [90.3, 98.3]) respectively. The F1 score was 0.941 [0.910, 0.966] for the notes algorithm compared to 0.794 [0.734, 0.842] for ICD codes. For PDR classification, ICD-10 codes performed better than ICD-9 codes (F1 score 0.836 [0.771, 0.878] vs 0.596 [0.222, 0.692]). For NPDR severity classification, the notes algorithm performed similarly to ICD codes, but performance was limited by small sample size. ConclusionsThe notes algorithm outperformed ICD codes for PDR classification. The findings demonstrate the significant potential of applying a rule-based NLP algorithm to clinical notes to increase the efficiency and accuracy of cohort selection for research.

Artificial Intelligence in Central Banking

Abstract The paper uses qualitative research to investigate the potential uses of artificial intelligence in the field of central banking. The analysis shows that monetary policy, prudential supervision and the oversight of payments are the areas where the use artificial intelligence is most likely to bring benefits. Monetary policy calibration involves working with long time series of data for various parameters and making the necessary analysis and forecasts, an activity in which artificial neural networks may prove useful. Bank supervision can benefit from the use natural language processing algorithms that can read documents and extract the relevant information. Such algorithms can read all of the required documents (not just those that the supervisor selected) and return all of the sentences that contain a certain predefined expression. In the field of the oversight of payments, the capabilities of machine learning to identify new patterns or anomalies in the data that could indicate fraud or money laundering will boost the efforts to combat them. In terms of challenges associated with the use of artificial intelligence in central banking, perhaps the two biggest challenges are that some of the models do not allow for a reasonable level of explainability of the algorithm(s) through which they arrive at the result (especially relevant for bank supervision) and data availability. With respect to the latter, although the issue of quantity of data can be dismissed as a shortcoming given the huge amounts of data available, the issue of data quality seems to be more pronounced, as deficiencies such as data measured incompletely or incorrectly, scarcity and regulatory barriers that impede data sharing may be difficult to surpass.

Uncontrolled diabetes mellitus and the progression of monoclonal gammopathy of undetermined significance to multiple myeloma in US veterans.

7551 Background: Studies have shown that, independent of obesity, the metabolic effects of diabetes mellitus (DM) promote the progression of monoclonal gammopathy of undetermined significance (MGUS) to multiple myeloma (MM). However, it is unclear whether glycemic control is associated with MGUS progression in DM patients. We aimed to evaluate the association between poor glycemic control, measured by HbA1c >6.5%, and progression. Methods: Patients diagnosed with MGUS from 1999-2021 in the Veterans Health Administration (VHA) were identified using a published natural language processing (NLP)-based algorithm. We focused on patients whose MGUS subtype was IgG, IgA, or light chain. We excluded patients lacking body weight measurements from the time of MGUS diagnosis to the end of follow-up to ensure receiving care in the VHA. We further excluded patients with extended gaps >1 year between HbA1c measurements. Time-varying HbA1c measurements during the follow-up, evaluated at 1-day intervals and categorized into uncontrolled (HbA1c >6.5%) or controlled (≤6.5%) DM was the exposure variable. Progression of MGUS to MM was also confirmed by a published NLP algorithm. The association between the time-varying controlled/uncontrolled DM and progression was estimated by multivariable-adjusted hazard ratio (aHR) with death as a competing event. The covariates included sex, race, MGUS subtype as well as age, body mass index, monoclonal protein level, Charlson Comorbidity Index, DM medication, and DM type (type 1, type 2 with insulin-dependency status, type 2 without insulin-dependency status), all at MGUS diagnosis. Same analysis was conducted in a subgroup of patients with non-insulin dependent DM type 2 (NIDDMT2) without insulin use between MGUS diagnosis and the end of follow-up. Results: After applying inclusion and exclusion criteria, we identified 9,682 patients with both DM and MGUS. The multivariable analysis revealed a positive association between poor glycemic control and MM progression (see Table): (aHR 1.27, 95% CI 1.13-1.42). In NIDDMT2 without insulin use (n=3,498), poor glycemic control was associated with MM progression (aHR 1.81; 95% CI 1.57-2.10). Conclusions: For patients with DM and MGUS, the risk of MGUS progression to MM was 27% higher in uncontrolled DM and 81% higher in patients with NIDDMT2. This finding highlights a modifiable risk factor for MM progression in MGUS patients. Future studies should examine if interventions to enhance glycemic control could potentially reduce MGUS progression.

A deep learning–enabled workflow to estimate real world progression-free survival in patients with metastatic breast cancer.

11176 Background: Progression-free survival (PFS) is frequently measured in oncology clinical trials. In analyses outside of the trial setting, various strategies have been utilized to assess real-world PFS (rwPFS), including manual abstraction of clinical records, natural language processing (NLP) of oncology notes and radiology reports, and longitudinal analyses of radiologic images. Here we develop and validate a new semi-automated workflow that combines NLP of clinical notes with structured electronic health record data to facilitate the evaluation of rwPFS in patients with metastatic breast cancer (mBC). Methods: This study analyzes de-identified EHR data using nference nSights. The data is extracted following privacy-preserving protocols and is HIPAA compliant. The overall cohort included 316 patients with HR-positive, HER2-negative mBC who initiated Palbociclib and Letrozole combination therapy between January 1, 2015 and December 31, 2021. We developed and implemented an ensemble of deep-learning NLP frameworks to capture progression events from unstructured clinical notes and radiology reports. A change in the line of therapy, as determined by structured drug order/administration records, was also considered a progression event. We used manually curated “ground-truth” datasets to evaluate the performance of the progression-event capture workflow at the levels of both sentences (N = 1000) and patients (N = 100) by calculating sensitivity, specificity, precision, accuracy, and F1 scores. Progression events and censoring events (death, loss to follow-up, end of study period) were considered to compute rwPFS. Results: At the sentence level, progression events were captured from clinical notes and radiology reports with a sensitivity of 99.8%, specificity of 96.7%, and accuracy of 98.2% (Table). At the patient level, initial progression was correctly captured within a window of +/-30 days with a sensitivity of 92.5%, specificity of 83.0%, and accuracy of 88.0% (Table). In a sample of 100 patients, the median rwPFS was determined to be 25 months (95% CI; 15-35 months) by manual curation and 22 months (95% CI; 15-35 months) by the semi-automated workflow. In the overall cohort, median rwPFS was 20 months (95% CI; 18-25 months). Conclusions: An ensemble of NLP algorithms extracted progression events from clinical notes and radiology reports with high accuracy. A semi-automated workflow enabled rapid and accurate determination of rwPFS in mBC patients receiving a combination chemotherapy regimen. Further evaluation of this workflow to estimate rwPFS in other cancers and therapeutic settings is warranted. [Table: see text]

Human-AI teams to improve accuracy and timeliness of oncology trial prescreening: Preplanned interim analysis of a randomized trial.

1524 Background: Identifying eligible patients for oncology clinical trials (“prescreening”) relies on manual chart review by clinical research coordinators (CRCs), which is time-consuming and often inaccurate. Consequently, 70% of patients with cancer who meet trial eligibility criteria are not offered participation. Natural language processing (NLP) may improve the accuracy and timeliness of prescreening. Methods: This was a preplanned interim analysis of a paired-design noninferiority trial, powered to assess timeliness. We adapted NLP algorithms to identify 13 common eligibility criteria related to cancer type/stage, prior systemic therapy, actionable biomarkers, and response criteria. NLP systems performed optical character recognition, entity and relationship extraction, and natural language inference through deep learning and symbolic AI techniques. Deidentified unstructured electronic health records (EHRs) from real-world patients with non-small cell lung (NSCLC) or colorectal (CrCa) cancer were presented to CRCs via a secure platform. Two CRCs were randomized 1:1 to view blocks of 20 charts each with (Human+AI) or without (Human-alone) NLP annotations. In pre-trial assessment, the CRCs had 86% inter-rater agreement. The primary outcome was overall chart-level accuracy, defined as percent of the 13 CRC-coded eligibility items matching a gold standard set, determined by 2-3 clinicians blinded to experimental arms. Paired t-tests compared overall accuracy (noninferiority margin 5%) and criteria-specific accuracy. Significant differences were assessed for superiority using two-sided paired t-tests. Mann-Whitney tests compared the secondary outcome of timeliness (time per chart review). Results: Among 74 (40 NSCLC; 34 CrCa) of a planned 400 patients, overall accuracy for Human+AI was noninferior to Human-alone (78.7% vs. 76.7%, mean difference 2.0%, p<0.001 rejecting inferiority); both were greater than AI-alone (63.5%). Superiority for Human+AI was demonstrated for RECIST response, but not for overall nor other criteria-specific accuracy (Table). Median time per review was lower for Human+AI than Human-alone (34.1 vs 43.9 min, adjusted p=0.05). Conclusions: Human+AI teams can improve timeliness of trial prescreening with noninferior accuracy. This platform is being used for eligibility assessment in an ongoing clinical trial. [Table: see text]

Automating the detection of treatment progression in patients with lung cancer using large language models.

e13620 Background: Accurate assessment of treatment response is fundamental to advancing cancer patient care, particularly in lung cancer, where treatment modalities are diverse and complex. The extraction of treatment response, particularly disease progression information, from Electronic Health Records (EHRs) is essential for several reasons: It facilitates generation of real-world evidence from real-world data, enables personalized treatment planning, and contributes to a broader understanding of cancer therapeutics. However, much of treatment response information is documented in free-text EHR notes and traditional methods of extracting such information from notes are labor-intensive, error-prone, and inefficient, presenting significant barriers to timely and accurate real-world evidence studies. The advancement of Natural Language Processing (NLP) technologies, especially Large Language Models (LLMs), presents a transformative opportunity to automate the extraction of treatment responses. Methods: We used a cohort of 1,953 primary lung cancer patients identified from UPMC Hillman Cancer Center cancer registry and retrieved ~113,000 clinical notes from UPMC clinical data warehouse. We focused on extracting disease progression information, following the RECIST guidelines which define progression as an increase in tumor size or cancer markers after therapy. We selected ~50 notes to perform manual annotations by an experienced oncologist and created a gold standard dataset to validate the NLP models. We fine-tuned a state-of-the-art open-source LLM named LLAMA-2 and compared against a traditional rule-based NLP system for the automated extraction of disease progression from notes. The process of fine-tuning involved adjusting the model's parameters specifically to improve its ability to recognize and classify instances of disease progression. Results: Our analysis demonstrated a significant enhancement in performance with the LLM compared to the traditional rule-based NLP system. LLM exhibited a remarkable increase in sensitivity by ~37%, indicating its superior ability to accurately identify disease progression. Additionally, the model maintained high specificity and PPV, achieving scores nearly comparable to the rule-based system but with a notable improvement in the F1-score by ~14%. Conclusions: Our research highlights the transformative potential of LLM-based NLP algorithms in automating the extraction of treatment responses from free-text EHRs. This methodology not only provides a scalable and efficient mechanism for processing large volumes of clinical text but also significantly enhances the accuracy of lung cancer treatment response assessments. [Table: see text]

Unstructured EMR data hold the key to oncology studies: Methods for validating NLP-extracted phenotypes from EMR notes.

11133 Background: Natural language processing (NLP) parsers are advanced algorithms designed to parse values of interest from free-text stored in Electronic Medical Records (EMR). Given the importance of information stored in free-text for use in oncology research, it is crucial to understand how accurately NLP algorithms are extracting oncology-specific measures of interest. We focus on validating NLP-parsers that identify three measures critical to oncology research by evaluating how closely the NLP-parser results match manual chart abstractor review: AJCC summary cancer stage group (cancer stage), AJCC TNM stage (TNM stage), and surgical treatment of cancer (surgery). Methods: Following deployment of the parsers on 8,000 non-identifiable free-text notes housed in an aggregated non-identifiable U.S. EMR database, manual chart abstraction was performed on a random selection of notes (n=300) dated between 2008 to 2023 to validate the parsers’ accurate capture of cancer stage, TNM stage, and surgical treatment of cancer. We report true positives (TP), false positives (FP) and positive percent value (PPV). Results: The PPV of AJCC Cancer Stage was 99.0% (n=297 TP, n=3 FP). The PPV of the TNM stage NLP-parser was 97.3% for tumor stage (n=292 TP, n=8 FP), 99.0% for nodal stage (n=297 TP, n=3 FP), and 96.7% for presence of metastases (n=290 TP, n=10 FP). The PPV of the surgery parser was 87.8% (n=468 TP, n=65 FP). Conclusions: These NLP-parsers performed very well identifying the measures of interest, providing confidence in use of these derived measures which are central to oncology research. Validation is a necessary initial step in processing real-world data for use in real-world evidence generation, with unique considerations needed in the oncology research space due to key information being documented in EMR free-text rather than structured data fields.

Let the algorithm speak: How to use neural networks for automatic item generation in psychological scale development.

Measurement is at the heart of scientific research. As many-perhaps most-psychological constructs cannot be directly observed, there is a steady demand for reliable self-report scales to assess latent constructs. However, scale development is a tedious process that requires researchers to produce good items in large quantities. In this tutorial, we introduce, explain, and apply the Psychometric Item Generator (PIG), an open-source, free-to-use, self-sufficient natural language processing algorithm that produces large-scale, human-like, customized text output within a few mouse clicks. The PIG is based on the GPT-2, a powerful generative language model, and runs on Google Colaboratory-an interactive virtual notebook environment that executes code on state-of-the-art virtual machines at no cost. Across two demonstrations and a preregistered five-pronged empirical validation with two Canadian samples (NSample 1 = 501, NSample 2 = 773), we show that the PIG is equally well-suited to generate large pools of face-valid items for novel constructs (i.e., wanderlust) and create parsimonious short scales of existing constructs (i.e., Big Five personality traits) that yield strong performances when tested in the wild and benchmarked against current gold standards for assessment. The PIG does not require any prior coding skills or access to computational resources and can easily be tailored to any desired context by simply switching out short linguistic prompts in a single line of code. In short, we present an effective, novel machine learning solution to an old psychological challenge. As such, the PIG will not require you to learn a new language-but instead, speak yours. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

SPPADE symptom prevalence and severity in a diverse sample of patients living with metastatic cancers.

11108 Background: Advances in cancer treatment have led to a growing population of patients living with metastatic cancer. Symptom burden for these patients is understudied. Our objective is to report the prevalence and severity of SPPADE symptoms (sleep disturbance, pain, physical function impairment, anxiety, depression, and low energy /fatigue) in a large cohort of patients with metastatic cancer. Methods: These data are drawn from the Enhanced, EHR-facilitated Cancer Symptom Control (E2C2) stepped wedge pragmatic trial evaluating a symptom management intervention for cancer patients (NCT03892967). This analysis was limited to those identified with metastatic disease using ICD- codes and a natural language processing algorithm prior to or within 30 days of their baseline symptom survey. Symptom severity was measured on a 0-10 scale with scores of 1-3 categorized as “mild”, 4-6 as “moderate”, and ≥7 as “severe.” A SPPADE composite score was calculated by summing six individual symptom scores and is an indicator of total symptom burden. We report descriptive statistics for each symptom by severity category. We also test for differences in SPPADE composite score by race, disability status, employment status, education and cancer type using Kruskal-Wallis tests. Results: 12,824 patients with metastatic disease completed a survey between March 2019 and January 2023. Discretized score distributions for the SPPADE symptoms are reported in the Table. The SPPADE composite mean score for the cohort was 17.6 (SD +/- 12.0). Significant differences were found in total symptom burden by sociodemographic and clinical characteristics ( p<0.01): Higher total symptom burden (Mean [SD])was experienced by individuals who were American Indian/Alaska Native (AI/AN) (23.8[13.5]) or African American (AA) (20.5[14.7]), disabled (24.0[12.8]) or unemployed (21.1[13.0]), and had a high school education (20.0[13.3]) or less than high school education (18.5[12.4]). There were also statistically significant differences ( p<0.01) in symptom burden across cancer types, with patients with metastatic lung cancer reporting the highest symptom burden (20.0[12.2]) and those with metastatic melanoma reporting the lowest (14.7[11.4]). Conclusions: SPPADE symptoms are common in patients with metastatic cancer, especially fatigue, sleep disturbance, and physical function impairment. Symptom burden is especially high in AI/AN, AA, disabled/unemployed, and less educated patients. Further research is needed to tailor symptom interventions among those living with metastatic disease. [Table: see text]

Multimodal Content Analysis Using Deep Learning

Abstract: The multimodal content analysis platform combines sentiment analysis and neural style transfertechniques to process and improve various types of digital content. The sentiment analysis module utilizes natural language processing (NLP) algorithms, such as recurrent neural networks (RNNs) or transformer models like BERT, to extract emotional signals from textual, visual, and auditory inputs. Signals are classified into predefined sentiment categories, providing granular insights into the emotional context of the content. The platform employs neural style transfer algorithms, such as style transfer networks (NSTNs) or generative adversarial networks (GANs), to transfer stylistic attributes between texts. By training on a diverse range of artistic styles, the system learns to apply these styles to input text while preserving semantic meaning. This process enhances the visual representation of textual content, making it more appealing and engaging to users.

Exploring Sentiment Analysis across Text, Audio, and Video: A Comprehensive Approach and Future Directions

Abstract: This study presents a comprehensive exploration of sentiment analysis techniques across text, audio, and video modalities. Leveraging natural language processing (NLP), speech recognition, and computer vision algorithms, the research demonstrates the versatility and adaptability of sentiment analysis across diverse data sources. The necessity of such an approach lies in its ability to provide deeper insights into user emotions and opinions expressed in various mediums, including written text, spoken language, and visual content. Moreover, the study highlights the importance of sentiment analysis in understanding customer feedback, market trends, social media sentiments, and sentiment-aware recommendation systems. Future directions include advancing algorithmic accuracy and efficiency, integrating multimodal fusion techniques, and exploring applications in diverse domains, thereby paving the way for enhanced sentiment analysis capabilities and broader realworld applications

An extended TF-IDF method for improving keyword extraction in traditional corpus-based research: An example of a climate change corpus

Keyword extraction involves the application of Natural Language Processing (NLP) algorithms or models developed in the realm of text mining. Keyword extraction is a common technique used to explore linguistic patterns in the corpus linguistic field, and Dunning’s Log-Likelihood Test (LLT) has long been integrated into corpus software as a statistic-based NLP model. While prior research has confirmed the widespread applicability of keyword extraction in corpus-based research, LLT has certain limitations that may impact the accuracy of keyword extraction in such research. This paper summarized the limitations of LLT, which include benchmark corpus interference, elimination of grammatical and generic words, consideration of sub-corpus relevance, flexibility in feature selection, and adaptability to different research goals. To address these limitations, this paper proposed an extended Term Frequency-Inverse Document Frequency (TF-IDF) method. To verify the applicability of the proposed method, 20 highly cited research articles on climate change from the Web of Science (WOS) database were used as the target corpus, and a comparison was conducted with the traditional method. The experimental results indicated that the proposed method could effectively overcome the limitations of the traditional method and demonstrated the feasibility and practicality of incorporating the TF-IDF algorithm into relevant corpus-based research.