RESUMO
Objective: Surgical registries play a crucial role in clinical knowledge discovery, hospital quality assurance, and quality improvement. However, maintaining a surgical registry requires significant monetary and human resources given the wide gamut of information abstracted from medical records ranging from patient co-morbidities to procedural details to post-operative outcomes. Although natural language processing (NLP) methods such as pretrained language models (PLMs) have promised automation of this process, there are yet substantial barriers to implementation. In particular, constant shifts in both underlying data and required registry content are hurdles to the application of NLP technologies. Materials and Methods: In our work, we evaluate the application of PLMs for automating the population of the Society of Thoracic Surgeons (STSs) adult cardiac surgery registry (ACS) procedural elements, for which we term Cardiovascular Surgery Bidirectional Encoder Representations from Transformers (CS-BERT). CS-BERT was validated across multiple satellite sites and versions of the STS-ACS registry. Results: CS-BERT performed well (F1 score of 0.8417 ± 0.1838) in common cardiac surgery procedures compared to models based on diagnosis codes (F1 score of 0.6130 ± 0.0010). The model also generalized well to satellite sites and across different versions of the STS-ACS registry. Discussion and Conclusions: This study provides evidence that PLMs can be used to extract the more common cardiac surgery procedure variables in the STS-ACS registry, potentially reducing need for expensive human annotation and wide scale dissemination. Further research is needed for rare procedural variables which suffer from both lack of data and variable documentation quality.
RESUMO
Primary retroperitoneal teratomas are rare non-seminomatous germ cell tumors that arise from embryonal tissues. They form only 5%-10% of all retroperitoneal tumors. These are usually asymptomatic or present as lump or mass with compressive symptoms. Most of the patients are diagnosed by characteristic computed tomography findings. The chances of malignant transformation are rare. Complete surgical resection is the definitive treatment for most patients. We had a 19 years old young man, presented with pain abdomen and awareness of a lump in the right upper abdomen. Contrast-enhanced computed tomography (CECT) of the abdomen revealed a heterogeneous soft tissue mass in the retroperitoneum with calcification. He was successfully treated with en-bloc complete surgical resection. Histopathology confirmed benign mature teratoma including all three germ layers. The patient is doing fine at nine months of follow-up and planned for CECT abdomen. Primary mature teratomas arise in the retroperitoneum due to failure of germ cells migration to their normal location. Germ cells undergo differentiation into various germ layers. Teratomas can be classified as mature, immature, or non-dermal based on their histopathological characteristics. Although complete surgical excision is the mainstay of treatment, malignant teratomas frequently recur. So, annual follow-up is recommended with imaging. A classic mature teratoma requires careful examination and interpretation of the imaging. The amount of immature components determines outcome and recurrence in these patients so en-bloc surgical resection is the treatment of choice.
RESUMO
BACKGROUND: To prevent the rapid spread of infectious COVID-19 in India, many steps have been taken. Adherence to the control measures depends on the knowledge, attitude, and practices (KAPs) toward COVID-19 disease in health-care professionals. The present study was conducted among health-care professionals in Jaipur. The objective was to evaluate the KAPs about COVID-19 among health-care professionals. MATERIALS AND METHODS: A total of 385 participants took part in the study. A self-designed questionnaire was filled by the participants online (Google Form). The knowledge of the participants was assessed using 12 questions. Attitude and practices of the participants were assessed by two questions for each. RESULTS: Among the study completers, 52.20% were male, 71.42% of the participants were aged above 30 years, and 59.22% were nurse. The knowledge score was approximately 90%. The majority of the participants had a strong conviction that India can overcome this infectious disease in the near future. Multiple regression analysis found that good knowledge score of COVID-19 was associated with lower negative attitudes and less risky practices (P < 0.001). CONCLUSION: Participants of the study were knowledgeable, held positive attitudes, and had adequate practices for COVID-19.