Article
Anesthesiology
Stephen L. Luther, Dezon K. Finch, Lina Bouayad, James McCart, Ling Han, Steven K. Dobscha, Melissa Skanderson, Samah J. Fodeh, Bridget Hahm, Allison Lee, Joseph L. Goulet, Cynthia A. Brandt, Robert D. Kerns
Summary: This study used rule-based natural language processing algorithms to extract pain care quality indicators from documents of Veterans Health Administration primary care providers. The patterns and frequency of these indicators were described. The study found that the most commonly documented indicators were pain presence, etiology or source, and pain site, while the least commonly documented were sensation, pain's impact, and pain relief factors. The study also calculated a PCQ indicator score for each visit and found the scores to be highly stable across patient characteristics and healthcare facilities.
Article
Mathematics
Lingzi Jin, Zuohua Ding, Huihui Zhou
Summary: This article uses metamorphic testing technology to evaluate the quality of natural language processing systems and assess their robustness through various tasks, revealing the strengths and weaknesses of each system.
Article
Psychology, Multidisciplinary
Oscar Kjell, Daiva Daukantaite, Sverker Sikstrom
Summary: This study found correlations between overall harmony in life and cooperation, particularly among prosocial participants, when assessed through computational language assessments (CLA), while traditional rating scales showed no correlation. Satisfaction with life was not significantly correlated with cooperation in either CLA or traditional rating scales.
FRONTIERS IN PSYCHOLOGY
(2021)
Article
Computer Science, Information Systems
Paula Alexandra Silva, Renato Santos
Summary: Despite the positive impact of games for health on players' health, users tend to stop playing them after a short period of time, leading benefits to fade. To sustain interest and preserve the health benefits of games for health, this paper introduces a methodology that analyzes user comments posted on YouTube about the Just Dance game. By automatically extracting information about usability, user experience, and perceived health impacts related to quality of life, this methodology provides insights for better understanding user opinions and informing the (re)design of games for health.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Review
Pharmacology & Pharmacy
Enzo Tagliazucchi
Summary: This review focuses on the interaction between serotonergic psychedelics and language production. It examines the acute effects of psychedelic drugs on speech organization and the subjective effects by analyzing the semantic content of written retrospective reports. The computational characterization of language production can partially predict the therapeutic outcome of individual experiences, draw comparisons between psychedelics and other altered states of consciousness, and investigate the neurochemical profile and mechanism of action of different psychedelic drugs.
FRONTIERS IN PHARMACOLOGY
(2022)
Article
Psychology, Multidisciplinary
Tianyi Han, Dechao Li, Xingcheng Ma, Nan Hu
Summary: This study proposes evaluation frameworks for translation and paraphrasing and examines the correlation and differences in product quality between the two activities. The findings reveal a closely related performance between translation and paraphrasing, with shared predictive indices in lexical sophistication. However, there are also differences in the most salient textual features between translations and paraphrases.
FRONTIERS IN PSYCHOLOGY
(2022)
Article
Chemistry, Multidisciplinary
Zaira Hassan Amur, Yew Kwang Hooi, Gul Muhammad Soomro, Hina Bhanbhro, Said Karyem, Najamudin Sohu
Summary: Keyword extraction is a critical task for various applications, but the lack of a suitable dataset for semantic analysis remains a problem. To address this, a study was conducted to identify a dataset based on structure, complexity, and quality factors.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Keno K. Bressem, Jens-Michalis Papaioannou, Paul Grundmann, Florian Borchert, Lisa C. Adams, Leonhard Liu, Felix Busch, Lina Xu, Jan P. Loyen, Stefan M. Niehues, Moritz Augustin, Lennart Grosser, Marcus R. Makowski, Hugo J. W. L. Aerts, Alexander Loeser
Summary: This paper presents medBERT.de, a pre-trained German BERT model designed specifically for the German medical domain. The model achieves state-of-the-art performance on various medical benchmarks and the analysis investigates the impact of data deduplication and tokenization methods on the model's performance.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
John Pavlopoulos, Aristidis Likas
Summary: Commonsense knowledge is often approximated by the fraction of annotators who classified an item as positive, which overlooks the polarization of opinions. We propose a novel measure, DFU, that estimates the extent of polarization and correlates well with human judgment. Applying DFU to pandemic-related tweets and toxic posts, we find that polarization occurs on different days for different states and is more likely among annotators from different countries. Furthermore, DFU can be used as an objective function to predict the potential for polarized opinions.
COGNITIVE COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Meng Xiao, Ziyue Qiao, Yanjie Fu, Hao Dong, Yi Du, Pengyang Wang, Hui Xiong, Yuanchun Zhou
Summary: The increasing interdisciplinary nature of research proposals poses a challenge in assigning appropriate reviewers. This study aims to develop a fair and precise proposal reviewer assignment system by leveraging AI. A deep hierarchical interdisciplinary research proposal classification network (HIRPCN) is proposed, which extracts textual semantic information, learns interdisciplinary knowledge, and detects interdisciplinary topic paths for each proposal. Extensive experiments and expert evaluations demonstrate the effectiveness of the proposed model.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Review
Computer Science, Artificial Intelligence
Silvia Casola, Alberto Lavelli
Summary: This paper surveys Natural Language Processing (NLP) approaches in summarizing, simplifying, and generating patent text. It highlights the challenges posed by the unique characteristics of patents to the current state of NLP research, presents previous work and its evolution critically, and draws attention to areas where further research is needed. To the best of the authors' knowledge, this is the first survey of generative approaches in the patent domain.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Psychiatry
Justyna Sarzynska-Wawer, Aleksander Wawer, Aleksandra Pawlak, Julia Szymanowska, Izabela Stefaniak, Michal Jarkiewicz, Lukasz Okruszek
Summary: The study used ELMo to represent interviews with schizophrenia patients and healthy individuals, finding that ELMo was more accurate in detecting FTD compared to coherence models, and had a similar accuracy rate to TLC evaluations.
PSYCHIATRY RESEARCH
(2021)
Article
Computer Science, Information Systems
Mamoru Mimura
Summary: This study evaluated a method for detecting malicious PE files using printable characters and conducted experiments using the latest dataset. The results showed that specific tokens were effective in detecting the latest malicious PE files, and the optimal combination was Doc2vec and multilayer perceptron.
INTERNET OF THINGS
(2022)
Review
Computer Science, Information Systems
Miguel A. Alvarez-Carmona, Ramon Aranda, Ansel Y. Rodriguez-Gonzalez, Daniel Fajardo-Delgado, Maria Guadalupe Sanchez, Humberto Perez-Espinosa, Juan Martinez-Miranda, Rafael Guerrero-Rodriguez, Lazaro Bustio-Martinez, Angel Diaz-Pacheco
Summary: The social networks and advancements in technology have greatly impacted the tourism industry. Natural language processing (NLP) in artificial intelligence is particularly beneficial for gathering information on user-generated content related to tourism services and products. This study conducts a systematic review of the use of NLP in the tourism industry, analyzing methodologies, tools, data sources, and other relevant features. It also introduces a taxonomy for using NLP in tourism and identifies six major topics in applying NLP to tourism issues. The analysis of metadata reveals similarities in tourism issues or approaches among China, the United States, Thailand, and Spain.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Richard K. G. Do, Kaelan Lupton, Pamela I. Causa Andrieu, Anisha Luthra, Michio Taya, Karen Batch, Huy Nguyen, Prachi Rahurkar, Lior Gazit, Kevin Nicholas, Christopher J. Fong, Natalie Gangai, Nikolaus Schultz, Farhana Zulkernine, Varadan Sevilimedu, Krishna Juluru, Amber Simpson, Hedvig Hricak
Summary: This study demonstrated the feasibility of using natural language processing to gather accurate data from radiology reports for assessing metastatic spread patterns in a large patient cohort. Metastatic disease tropism was found to be distinct among common cancers, with variations in the most common first site of metastases.
Article
Surgery
Thomas Hank, Marta Sandini, Cristina R. Ferrone, David P. Ryan, Mari Mino-Kenudson, Motaz Qadan, Jennifer Y. Wo, Ulla Klaiber, Colin D. Weekes, Maximilian Weniger, Ulf Hinz, Jon M. Harrison, Max Heckler, Andrew L. Warshaw, Theodore S. Hong, Thilo Hackert, Jeffrey W. Clark, Markus W. Buechler, Keith D. Lillemoe, Oliver Strobel, Carlos Fernandez-del Castillo
Summary: This study developed a prognostic score for patients with primary chemotherapy undergoing surgery for pancreatic cancer based on pathological parameters and preoperative CA19-9 levels. The PANAMA-score showed better discrimination compared to the AJCC staging system and identified patients at high-risk for early death.
Article
Surgery
Brooks Udelsman, David C. Chang, Michael Lanuti, Douglas J. Mathisen, Ashok Muniappan
Summary: This study examined the rate and risk factors of recurrent spontaneous pneumothorax in different populations. It found that the risk of recurrence is higher in patients under the age of 35, Asians, and those requiring a tube thoracostomy. Mechanical pleurodesis was more effective in reducing recurrence risk compared to chemical pleurodesis.
AMERICAN JOURNAL OF SURGERY
(2022)
Editorial Material
Oncology
Zhi Ven Fong, Motaz Qadan
ANNALS OF SURGICAL ONCOLOGY
(2022)
Article
Cardiac & Cardiovascular Systems
Brooks Udelsman, David C. Chang, Daniel J. Boffa, Henning A. Gaissert
Summary: This study investigated adherence to guidelines regarding lymph node sampling during lobectomy for non-small cell lung cancer (NSCLC), and its association with hospital lobectomy volume. The results showed that the average rate of >= 10 lymph nodes harvested per lobectomy was higher in medium- to high-volume hospitals. However, 25% of high-volume hospitals still had a lymph node yield of <10 nodes, which may lead to inaccurate staging and have implications for adjuvant therapy and long-term survival.
ANNALS OF THORACIC SURGERY
(2023)
Article
Medicine, General & Internal
Matthew D. Pichert, Maureen E. Canavan, Richard C. Maduka, Andrew X. Li, Theresa Ermer, Peter L. Zhan, Michael Kaminski, Brooks Udelsman, Justin D. Blasberg, Henry S. Park, Sarah B. Goldberg, Daniel J. Boffa
Summary: In the general US population, immunotherapy after chemotherapy and radiation for stage III NSCLC showed a survival advantage, despite most patients being treated differently than the PACIFIC protocol. Further study is needed to clarify the clinical benefits of immunotherapy.
Review
Oncology
Brooks V. Udelsman, Justin D. Blasberg
Summary: Ground glass opacities that meet certain criteria, such as size, solid component development, or growth rate, may require operative resection. Minimally invasive robotic-assisted thoracoscopic surgery can be used with localization techniques and is compatible with developing intraoperative molecular targeting techniques.
JOURNAL OF SURGICAL ONCOLOGY
(2023)
Article
Surgery
Alan Z. Yang, Sasiprang Kongboonvijit, Carlos F. Fernandez F. del Castillo, Zhi Ven Fong, Piotr J. Zelga, Cristina R. Ferrone, Keith D. Lillemoe, Avinash Kambadakone, Motaz Qadan
Summary: This study aimed to investigate whether UDD increases the risk of HGD/IC in Fukuoka-positive IPMNs. The results showed that UDD indeed increases the odds of developing HGD/IC, which is not accounted for by the current Fukuoka risk criteria. This finding may have important implications for clinical assessment and treatment decisions in this field.
Editorial Material
Oncology
Peter L. L. Zhan, Maureen E. Canavan, Theresa Ermer, Matthew D. Pichert, Andrew X. X. Li, Richard C. Maduka, Brooks V. Udelsman, Attila Nemeth, Daniel J. Boffa
ANNALS OF SURGICAL ONCOLOGY
(2023)
Article
Oncology
Peter L. L. Zhan, Maureen E. E. Canavan, Theresa Ermer, Matthew D. D. Pichert, Andrew X. X. Li, Richard C. C. Maduka, Brooks V. V. Udelsman, Attila Nemeth, Daniel J. J. Boffa
Summary: The purpose of this study was to investigate the association between metastatic pattern and prognosis in stage IV gastric cancer, specifically focusing on patients with metastases limited to nonregional lymph nodes. The study utilized a retrospective cohort design and analyzed data from the National Cancer Database. The results demonstrated that patients with limited nonregional lymph node metastases had a better prognosis compared to patients with other metastatic patterns.
ANNALS OF SURGICAL ONCOLOGY
(2023)
Article
Oncology
Brooks V. Udelsman, Justin D. Blasberg
HEMATOLOGY-ONCOLOGY CLINICS OF NORTH AMERICA
(2023)
Editorial Material
Oncology
Brooks V. Udelsman, Justin Blasberg
JOURNAL OF SURGICAL ONCOLOGY
(2023)
Article
Surgery
Maximiliano Servin-Rojas, Zhi Ven Fong, Carlos Fernandez-Del Castillo, Cristina R. Ferrone, Dario M. Rocha-Castellanos, Jorge Roldan, Piotr J. Zelga, Andrew L. Warshaw, Keith D. Lillemoe, Motaz Qadan
Summary: Background: Mucinous cystic neoplasms of the pancreas are rare tumors that can potentially develop into cancer. This study aimed to identify preoperative factors that can predict high-grade dysplasia or invasive carcinoma in these tumors. Methods: The study analyzed the data of 157 patients who had undergone resection for mucinous cystic neoplasms of the pancreas. Results: Tumor size >= 4 cm, mural nodularity, and a serum CA 19-9 level >37 U/mL were associated with high-grade dysplasia or invasive carcinoma. Tumors with a size >= 4 cm and/or a high CA 19-9 level should be surgically resected promptly, while tumors <4 cm with no other high-risk features may benefit from nonoperative surveillance.
Article
Gastroenterology & Hepatology
Maximiliano Servin-Rojas, Neha Shafique, Naomi M. Sell, T. Clark Gamblin, Motaz Qadan
Summary: This study aimed to compare the outcomes of minimally invasive surgery (MIS) for pancreatic ductal adenocarcinoma (PDAC) between academic and community facilities. The results showed that patients treated at academic facilities experienced better perioperative and oncologic outcomes compared to those treated at community facilities.
Review
Respiratory System
Frank C. Detterbeck, Ulas Kumbasar, Andrew X. Li, Ami N. Rubinowitz, Leah Traube, Babina Gosangi, Brooks Udelsman, Brett C. Bade, Sora Ely, Gaspar Barreto, Lynn T. Tanoue, Edith M. Marom, M. Patricia Rivera
Summary: Based on a systematic review of 49 studies, it was found that lung cancers with air lucency may be distinct entities requiring different clinical management. Greater awareness and early detection of lung cancers with air lucency are needed, and aggressive treatment should be initiated once a solid component appears.
JOURNAL OF THORACIC DISEASE
(2023)
Article
Oncology
Zhi Ven Fong, Jonathan Teinor, Theresa P. Yeo, Dee Rinaldi, Jonathan B. Greer, Harish Lavu, Motaz Qadan, Fabian M. Johnston, Cristina R. Ferrone, David C. Chang, Charles J. Yeo, Christopher L. Wolfgang, Andrew L. Warshaw, Keith D. Lillemoe, Carlos Fernandez-del Castillo, Jennifer L. Wolff, Albert W. Wu, Matthew J. Weiss
Summary: People with pancreatic and periampullary cancers often rely on family and unpaid caregivers for assistance after surgery, but little is known about the nature and difficulty of the assistance they provide. This study aimed to assess the frequency and difficulty of specific assistance caregivers provide and identify potential interventions to alleviate their caregiving demands.
JCO ONCOLOGY PRACTICE
(2023)