RESUMO
BACKGROUND AND OBJECTIVE: Researchers commonly use automated solutions such as Natural Language Processing (NLP) systems to extract clinical information from large volumes of unstructured data. However, clinical text's poor semantic structure and domain-specific vocabulary can make it challenging to develop a one-size-fits-all solution. Large Language Models (LLMs), such as OpenAI's Generative Pre-Trained Transformer 3 (GPT-3), offer a promising solution for capturing and standardizing unstructured clinical information. This study evaluated the performance of InstructGPT, a family of models derived from LLM GPT-3, to extract relevant patient information from medical case reports and discussed the advantages and disadvantages of LLMs versus dedicated NLP methods. METHODS: In this paper, 208 articles related to case reports of foreign body injuries in children were identified by searching PubMed, Scopus, and Web of Science. A reviewer manually extracted information on sex, age, the object that caused the injury, and the injured body part for each patient to build a gold standard to compare the performance of InstructGPT. RESULTS: InstructGPT achieved high accuracy in classifying the sex, age, object and body part involved in the injury, with 94%, 82%, 94% and 89%, respectively. When excluding articles for which InstructGPT could not retrieve any information, the accuracy for determining the child's sex and age improved to 97%, and the accuracy for identifying the injured body part improved to 93%. InstructGPT was also able to extract information from non-English language articles. CONCLUSIONS: The study highlights that LLMs have the potential to eliminate the necessity for task-specific training (zero-shot extraction), allowing the retrieval of clinical information from unstructured natural language text, particularly from published scientific literature like case reports, by directly utilizing the PDF file of the article without any pre-processing and without requiring any technical expertise in NLP or Machine Learning. The diverse nature of the corpus, which includes articles written in languages other than English, some of which contain a wide range of clinical details while others lack information, adds to the strength of the study.
RESUMO
Background: The prognostic impact of catheter ablation (CA) of atrial fibrillation (AF) in hypertrophic cardiomyopathy (HCM) patients has not yet been satisfactorily elucidated. Objectives: The aim of the study was to assess the impact of CA of AF on clinical outcomes in a large cohort of HCM patients. Methods: In this retrospective multicenter study, 555 HCM patients with AF were enrolled, 140 undergoing CA and 415 receiving medical therapy. 1:1 propensity score matching led to the inclusion of 226 patients (113 medical group, 113 intervention group) in the final analysis. The primary outcome was a composite of all-cause mortality, heart transplant and acute heart failure exacerbations. Secondary outcomes included AF recurrence and transition to permanent AF. Additionally, an inverse probability weighted (IPW) model was examined. Results: At propensity score matching analysis, after a median follow-up of 58.1 months, the primary endpoint occurred in 29 (25.7%) patients in intervention group vs 42 (37.2%) in medical group (P = 0.9). Thromboembolic strokes and major arrhythmic events in intervention vs medical group were 9.7% vs 7.1% (P = 0.144) and 4.4 vs 8.0% (P = 0.779), respectively. Fewer patients in intervention vs medical group experienced AF recurrences (63.7% vs 84.1%, P = 0.001) and transition to permanent AF pattern (20.4% vs 33.6%, P = 0.026). IPW analysis showed consistent results. Severe complications related to CA were uncommon (0.7%). Conclusions: After 5 years of follow-up, CA did not improve major adverse cardiac outcomes in a large cohort of patients with HCM and AF. Nevertheless, CA seems to facilitate the maintenance of sinus rhythm and slow the progression to permanent AF, without significant safety concerns.
RESUMO
INTRODUCTION: Differentiated vulvar intraepithelial neoplasia (dVIN) is a high-risk preinvasive vulvar lesion and precursor of human papillomavirus-independent vulvar squamous cell carcinoma (VSCC). Due to its rarity, literature data on its malignant potential are scant. The aim of the study is to assess the risk of developing VSCC in patients surgically treated for dVIN not associated with VSCC (solitary dVIN) and the risk of VSCC recurrence in patients treated for dVIN associated with VSCC (dVIN-VSCC) at first diagnosis. MATERIAL AND METHODS: A historical cohort study was performed in a northern Italy referral center for vulvar neoplasms. All consecutive women surgically treated for histologically confirmed dVIN from 1994 to 2021 were collected. Primary outcome was cancer risk or recurrent cancer risk, secondary outcomes were risk factors associated with VSCC development or recurrence. Kaplan-Meier method and log-rank test were used to estimate cancer risk or recurrent cancer risk differences and uni- and multivariate Cox regression analyses to identify risk factors associated with VSCC development in solitary dVIN and recurrence of dVIN-VSCC. RESULTS: Seventy-six patients with dVIN at preoperative biopsy were included: at excisional specimens 44 were solitary dVIN and 32 were dVIN-VSCC. The absolute risk of VSCC development after solitary dVIN treatment was 43.2% with median time to to VSCC diagnosis of 25.4 months (range 3.5-128.0 months). VSCC recurrence absolute risk in treated dVIN-VSCC patients was 31.3% with median time to VSCC recurrence of 52.9 months (range 6.5-94.8 months). At uni- and multivariate regression analyses, only compliant topical ultrapotent corticosteroid treatment after solitary dVIN excision showed an ability to prevent VSCC development. No protective effect by corticosteroid treatment was shown for VSCC recurrence in dVIN-VSCC patients. Smoking was associated with higher cancer recurrence risk in dVIN-VSCC patients on both uni- and multivariate regression analyses. CONCLUSIONS: Patients with dVIN have a high risk of developing both primary and recurring VSCC. Early recognition, long-term follow up, and compliant ultrapotent topical corticosteroid treatment are recommended.
Assuntos
Carcinoma in Situ , Carcinoma de Células Escamosas , Recidiva Local de Neoplasia , Neoplasias Vulvares , Humanos , Feminino , Neoplasias Vulvares/patologia , Carcinoma in Situ/patologia , Carcinoma in Situ/terapia , Pessoa de Meia-Idade , Recidiva Local de Neoplasia/epidemiologia , Carcinoma de Células Escamosas/patologia , Prognóstico , Seguimentos , Estudos de Coortes , Adulto , Fatores de Risco , Idoso , Itália/epidemiologiaRESUMO
R-CHOP standard chemotherapy is successful in about 60% of diffuse large B-cell lymphoma (DLBCL) patients. Unresponsive patients have a poor prognosis, and predictive biomarkers of response to R-CHOP are lacking. We conducted the first prospective GWAS study aimed at exploring constitutional biomarkers predictive of R-CHOP efficacy and toxicity. Overall, 216 any-stage chemonaïve DLBCL patients candidate to R-CHOP were enrolled. The median age of the 185 eligible patients was 59.2 years, 49.7% were women and 45.4% were stage I-II patients. According to the Revised International Prognostic Index (R-IPI), 14.1%, 56.8% and 29.2% were in the very good, good and poor prognosis groups, respectively. Of the patients, 85.9% produced a complete response. Highly significant associations (i.e., p < 5 × 10-8) were found between progression-free survival (PFS) and six SNPs (i.e., rs116665727, rs1607795, rs75614943, rs77241831, rs117500207, rs78466241). Additionally, five SNPs (i.e., rs74832512, rs117500207, rs35789195, rs11721010, rs12356569) were highly associated with overall survival (OS). Wild-type patients showed a prolonged PFS or OS compared with patients carrying deleterious alleles (p < 0.001). No association with the adequate significant threshold was observed between SNPs and the objective response or toxicity. In the future, these SNPs, alone or in combination, after a proper validation in an independent cohort, could contribute to improving the prediction of R-CHOP response.
RESUMO
CONTEXT: Because of the rarity of adrenocortical cancer (ACC), only a few population-based studies are available, and they reported limited details in the characterization of patients and their treatment. OBJECTIVE: To describe in a nationwide cohort the presentation of patients with ACC, treatment strategies, and potential prognostic factors. METHODS: Retrospective analysis of 512 patients with ACC, diagnosed in 12 referral centers in Italy from January 1990 to June 2018. RESULTS: ACC diagnosed as incidentalomas accounted for overall 38.1% of cases, with a frequency that increases with age and with less aggressive pathological features than symptomatic tumors. Women (60.2%) were younger than men and had smaller tumors, which more frequently secreted hormones. Surgery was mainly done with an open approach (72%), and after surgical resection, 62.7% of patients started adjuvant mitotane therapy. Recurrence after tumor resection occurred in 56.2% of patients. In patients with localized disease, cortisol secretion, ENSAT stage III, Ki67%, and Weiss score were associated with an increased risk of recurrence, whereas margin-free resection, open surgery, and adjuvant mitotane treatment were associated with reduced risk. Death occurred in 38.1% of patients and recurrence-free survival (RFS) predicted overall survival (OS). In localized disease, age, cortisol secretion, Ki67%, ENSAT stage III, and recurrence were associated with increased risk of mortality. ACCs presenting as adrenal incidentalomas showed prolonged RFS and OS. CONCLUSION: Our study shows that ACC is a sex-related disease and demonstrates that an incidental presentation is associated with a better outcome. Given the correlation between RFS and OS, RFS may be used as a surrogate endpoint in clinical studies.
Assuntos
Neoplasias do Córtex Suprarrenal , Neoplasias das Glândulas Suprarrenais , Carcinoma Adrenocortical , Masculino , Humanos , Feminino , Mitotano/uso terapêutico , Carcinoma Adrenocortical/diagnóstico , Carcinoma Adrenocortical/epidemiologia , Carcinoma Adrenocortical/terapia , Estudos de Coortes , Neoplasias das Glândulas Suprarrenais/tratamento farmacológico , Estudos Retrospectivos , Hidrocortisona/uso terapêutico , Antígeno Ki-67 , Neoplasias do Córtex Suprarrenal/diagnóstico , Neoplasias do Córtex Suprarrenal/epidemiologia , Neoplasias do Córtex Suprarrenal/cirurgiaRESUMO
Objective: In the past 2 years, the number of scientific publications has grown exponentially. The COVID-19 outbreak hugely contributed to this dramatic increase in the volume of published research. Currently, text mining of the volume of SARS-CoV-2 and COVID-19 publications is limited to the first months of the outbreak. We aim to identify the major topics in COVID-19 literature collected from several citational sources and analyze the temporal trend from November 2019 to December 2021. Methods: We performed an extensive literature search on SARS-Cov-2 and COVID-19 publications on PubMed, Scopus, and Web of Science (WoS) and a structural topic modelling on the retrieved abstracts. The temporal trend of the recognized topics was analyzed. Furthermore, a comparison between our corpus and the COVID-19 Open Research Dataset (CORD-19) repository was performed. Results: We collected 269,186 publications and identified 10 topics. The most popular topic was related to the clinical pictures of the COVID-19 outbreak, which has a constant trend, and the least popular includes studies on COVID-19 literature and databases. "Telemedicine", "Vaccine development", and "Epidemiology" were popular topics in the early phase of the pandemic; increasing topics in the last period are "COVID-19 impact on mental health", "Forecasting", and "Molecular Biology". "Education" was the second most popular topic, which emerged in September 2020. Conclusions: We identified 10 topics for classifying COVID-19 research publications and estimated a nonlinear temporal trend that gives an overview of their unfolding over time. Several citational databases must be searched to retrieve a complete set of studies despite the efforts to build repositories for COVID-19 literature. Our collected data can help build a more focused literature search between November 2019 and December 2021 when carrying out systematic and rapid reviews and our findings can give a complete picture on the topic.
RESUMO
BACKGROUND: Breast cancer (BC) is the most frequently diagnosed cancer among women. Numerous studies explored cell-free circulating microRNAs as diagnostic biomarkers of BC. As inconsistent and rarely intersecting microRNA panels have been reported thus far, we aim to evaluate the overall diagnostic performance as well as the sources of heterogeneity between studies. METHODS: Based on the search of three online search engines performed up to March 21st 2022, 56 eligible publications that investigated diagnostic circulating microRNAs by utilizing Real-Time Quantitative Reverse Transcription PCR (qRT-PCR) were obtained. Primary studies' potential for bias was evaluated with the revised tool for the quality assessment of diagnostic accuracy studies (QUADAS-2). A bivariate generalized linear mixed-effects model was applied to obtain pooled sensitivity and specificity. A novel methodology was utilized in which the sample and study models' characteristics were analysed to determine the potential preference of studies for sensitivity or specificity. RESULTS: Pooled sensitivity and specificity of 0.85 [0.81-0.88] and 0.83 [0.79-0.87] were obtained, respectively. Subgroup analysis showed a significantly better performance of multiple (sensitivity: 0.90 [0.86-0.93]; specificity: 0.86 [0.80-0.90]) vs single (sensitivity: 0.82 [0.77-0.86], specificity: 0.83 [0.78-0.87]) microRNA panels and a comparable pooled diagnostic performance between studies using serum (sensitivity: 0.87 [0.81-0.91]; specificity: 0.83 [0.78-0.87]) and plasma (sensitivity: 0.83 [0.77-0.87]; specificity: 0.85 [0.78-0.91]) as specimen type. In addition, based on bivariate and univariate analyses, miRNA(s) based on endogenous normalizers tend to have a higher diagnostic performance than miRNA(s) based on exogenous ones. Moreover, a slight tendency of studies to prefer specificity over sensitivity was observed. CONCLUSIONS: In this study the diagnostic ability of circulating microRNAs to diagnose BC was reaffirmed. Nonetheless, some subgroup analyses showed between-study heterogeneity. Finally, lack of standardization and of result reproducibility remain the biggest issues regarding the diagnostic application of circulating cell-free microRNAs.
Assuntos
Neoplasias da Mama , MicroRNA Circulante , MicroRNAs , Biomarcadores Tumorais/genética , Neoplasias da Mama/diagnóstico , Neoplasias da Mama/genética , Feminino , Humanos , MicroRNAs/genética , Reprodutibilidade dos Testes , Sensibilidade e EspecificidadeRESUMO
BACKGROUND: In a randomized controlled trial (RCT) with binary outcome the estimate of the marginal treatment effect can be biased by prognostic baseline covariates adjustment. Methods that target the marginal odds ratio, allowing for improved precision and power, have been developed. METHODS: The performance of different estimators for the treatment effect in the frequentist (targeted maximum likelihood estimator, inverse-probability-of-treatment weighting, parametric G-computation, and the semiparametric locally efficient estimator) and Bayesian (model averaging), adjustment for confounding, and generalized Bayesian causal effect estimation frameworks are assessed and compared in a simulation study under different scenarios. The use of these estimators is illustrated on an RCT in type II diabetes. RESULTS: Model mis-specification does not increase the bias. The approaches that are not doubly robust have increased standard error (SE) under the scenario of mis-specification of the treatment model. The Bayesian estimators showed a higher type II error than frequentist estimators if noisy covariates are included in the treatment model. CONCLUSIONS: Adjusting for prognostic baseline covariates in the analysis of RCTs can have more power than intention-to-treat based tests. However, for some classes of model, when the regression model is mis-specified, inflated type I error and potential bias on treatment effect estimate may arise.