RESUMEN
Thyroid cancer (TC) is a common endocrine malignancy with an increasing incidence worldwide. Early diagnosis is particularly important for TC patients, because it allows patients to receive treatment as early as possible. Artificial intelligence (AI) provides great advantages for complex healthcare systems by analyzing big data based on machine learning. Nowadays, AI is widely used in the early diagnosis of cancer such as TC. Ultrasound detection and fine needle aspiration biopsy are the main methods for early diagnosis of TC. AI has been widely used in the detection of malignancy in thyroid nodules by ultrasound images, cytopathology images and molecular markers. It shows great potential in auxiliary medical diagnosis. The latest clinical trial has shown that the performance of AI models matches with the diagnostic efficiency of experienced clinicians, and more efficient AI tools will be developed in the future. Therefore, in this review, we summarized the recent advances in the application of AI algorithms in assessing the risk of malignancy in thyroid nodules. The objective of this review was to provide a data base for the clinical use of AI-assisted diagnosis in TC, as well as to provide new ideas for the next generation of AI-assisted diagnosis in TC.
RESUMEN
PURPOSE: Thyroid nodules are a kind of common endocrine system disease, with approximately 5% of them developing into malignant lesions, the most common of which belong to differentiated thyroid carcinoma (DTC). Accurate differential diagnosis using reliable methods and targeted treatment of benign and malignant thyroid nodules are of great significance to improve patient outcomes. This study mainly investigates the diagnostic value of thyroglobulin (Tg) and anti-thyroglobulin antibody (anti-TgAb) combined with emission computed tomography (ECT) in the adjuvant diagnosis DTC. METHODS: All the data of 387 histopathologically diagnosed DTC patients (observation group) and 151 patients with nodular goiter (control group) admitted between June 2019 and June 2021 were collected and retrospectively analyzed. Serum Tg and anti-TgAb levels were detected in all subjects. In addition, all patients in the observation group underwent thyroid ECT, and the results were compared with the pathological findings. The receiver operating characteristic (ROC) curve was drawn to analyze the diagnostic performance of Tg, TgAb and thyroid ECT, either alone or in combination, in patients with thyroid cancer (TC). RESULTS: The consistency test showed that Tg (Kappa-value = 0.370) and anti-TgAb (Kappa-value = 0.393) had generally consistent efficiency with pathological findings in the diagnosis of DTC; ECT (Kappa-value = 0.625) and the combined diagnosis of the three (Kappa-value = 0.757) showed higher consistency than the pathological diagnosis, of which the combined diagnosis contributed to an even higher consistency. The combined diagnosis of Tg, anti-TgAb, and thyroid ECT outperformed either of these alone in DTC diagnosis, with a sensitivity of 91.5%, a specificity of 86.1%, and an accuracy of 90%. CONCLUSIONS: The combination of Tg. anti-TgAb, and RNI can effectively improve the diagnostic accuracy of DTC and reduce the missed diagnosis rate, which has important reference significance for clinical diagnosis and treatment of TC.
Asunto(s)
Adenocarcinoma , Neoplasias de la Tiroides , Nódulo Tiroideo , Humanos , Adenocarcinoma/diagnóstico por imagen , Estudios Retrospectivos , Neoplasias de la Tiroides/diagnóstico por imagen , Tomografía Computarizada por Rayos X , Tiroglobulina , Diagnóstico DiferencialRESUMEN
Trust is considered a critical factor in the physician-patient relationship. However, little is known about the development and impact of physicians trusting their patients. A model that is premised on the integrated model of organizational trust was proposed in this article to reveal the cognitive processes involved in physicians' trust, with perceived integrity and the ability of the patient as antecedents and the physicians' communication efficacy as the outcome. A cross-sectional survey of 348 physicians in Zhejiang province, China, revealed that a physician's trust in a patient mediated the relationship between the physicians' perception of the integrity and ability of the patient, and the physician's communication efficacy. The physicians' educational backgrounds and work experience were also found to moderate an indirect effect: a lower level of education and longer work experience intensified the impact of the perceived integrity and ability of the patient on the physician's trust, while shorter work experience made the association between the physician's trust and communication efficacy more salient. This paper provided implications for both physician and patient sides.
Asunto(s)
Médicos , Confianza , Humanos , Estudios Transversales , Relaciones Médico-Paciente , Médicos/psicología , CogniciónRESUMEN
This study explored the relationships between media exposure, cancer beliefs, and cancer information-seeking or information-avoidance behaviors. Based on the planned risk information-seeking model and its extended framework, two predictive models were constructed: one for cancer information seeking and the other for cancer information avoidance. A structural equation modeling strategy was applied to survey data from China HINTS 2017 (n = 3090) to compare the impact of traditional mass media and social media exposure to cancer-related information on cancer information-seeking and information-avoidance behaviors. The study findings suggest that health-related information exposure through different media channels may generate distinctive information-seeking or information-avoidance behaviors based on various cancer beliefs. Additionally, the findings indicate that social media exposure to health-related and cancer curability beliefs does not lead to cancer information avoidance; both mass media and social media exposure encourage people to seek cancer-related information. Cancer fatalism is positively associated with cancer information-seeking and avoiding intentions, suggesting that negative cancer beliefs predict seemingly contradictory yet psychologically coherent information intentions and behaviors.
Asunto(s)
Conducta en la Búsqueda de Información , Neoplasias , Reacción de Prevención , China/epidemiología , Humanos , Medios de Comunicación de Masas , Neoplasias/epidemiología , Encuestas y CuestionariosRESUMEN
The saying "mental illness is like any other illness" has increasingly become pervasive in promoting mental health literacy among the public in China. This discourse is based on the fact that mental illness is attributed to primarily biogenetic causes. This study comprises an investigation of the impact of causal attributions of mental illness on the social withdrawal inclination of people with chronic mental illnesses (PCMIs) in China. Drawing on attribution theory and a sample of PCMIs, the current authors further question the effectiveness of biogenetic discourse to combat social stigma and to integrate PCMIs into society. In addition, in response to the proliferation of discussion on the digital inclusion of those with mental disabilities, this study constructs a structural model in which the varied effects of supportive communication are used as bridging factors, including face-to-face, telephonic and social media communication. The results indicate a stronger social withdrawal inclination when the PCMIs attributed their illnesses to biogenetic causes. In addition, biogenetic attribution was also found to potentially hinder the PCMIs from using the telephone and social media to seek supportive communication, while psychosocial attribution was found to have potential to combat PCMIs' social withdrawal inclination. In this vein, this study calls for further investigation on the conditional factors upon which digital inclusion might work for PCMIs in China.
Asunto(s)
Trastornos Mentales , Aislamiento Social , Comunicación , Humanos , Salud Mental , Estigma SocialRESUMEN
OBJECTIVE: To determine the reproducibility of quantitative computed tomography perfusion (CTP) parameters generated using different post-processing methods and identify the relative impact of subjective factors on the robustness of CTP parameters in acute ischemic stroke (AIS). MATERIALS AND METHODS: A total of 80 CTP datasets from patients with AIS or transient ischemic attack (TIA) were retrospectively post-processed by two observers using different regions of interest (ROI) types, input models, and software. The CTP parameters were derived for 10 parenchymal ROIs. The intra-class correlation coefficients (ICCs) were used to assess the reproducibility of the CTP parameters for various post-processing methods. The Spearman correlation test was used to detect potential relationships between software and input models. RESULTS: The ICCs with 95% confidence intervals (CIs) were 0.94 (0.93-0.96), 0.94 (0.92-0.96), 0.82 (0.79-0.86), and 0.87 (0.85-0.90) for inter-reader agreement by using elliptic ROI, irregular ROI, single-input model, and dual-input model, respectively. The ICCs with 95% CI were 0.98 (0.98-0.98), 0.46 (0.43-0.50), and 0.25 (0.20-0.30) for inter-ROI type, inter-input model, and inter-software agreement, respectively. CONCLUSIONS: Although the CTP parameters were stable when measured using different readers with different ROI types, they varied for different input models and software. The standardization of CTP post-processing is essential to reduce variability of CTP values. KEY POINTS: ⢠The CTP parameters derived by different readers with different ROI types have agreements that range from good to excellent. ⢠The CTP parameters derived from different input models and software programs have poor agreement but significant correlations.