RESUMEN
Stenotrophomonas maltophilia (SM) is a multidrug-resistant, Gram-negative (GN) bacillus that is an increasingly recognized nosocomial and environment pathogen. It is intrinsically resistant to carbapenems, a drug commonly utilized in the management of necrotizing pancreatitis (NP). We report a 21-year-old immunocompetent female with NP complicated by pancreatic fluid collection (PFC) infected with SM. One-third of patients with NP will develop infections by GN bacteria, while broad-spectrum antibiotics, including carbapenems, cover most infections, trimethoprim-sulfamethoxazole (TMP-SMX) is the first-line treatment antibiotic for SM. This case is critical because it highlights a rare pathogen that should be considered a causal pathogen in patients who do not respond to their care plan.
RESUMEN
Background: Numerous deep learning-based survival models are being developed for various diseases, but those that incorporate both deep learning and transfer learning are scarce. Deep learning-based models may not perform optimally in real-world populations due to variations in variables and characteristics. Transfer learning, on the other hand, enables a model developed for one domain to be adapted for a related domain. Our objective was to integrate deep learning and transfer learning to create a multivariable survival model for lung cancer. Methods: We collected data from 601,480 lung cancer patients in the Surveillance, Epidemiology, and End Results (SEER) database and 4,512 lung cancer patients in the First Affiliated Hospital of Guangzhou Medical University (GYFY) database. The primary model was trained with the SEER database, internally validated with a dataset from SEER, and externally validated through transfer learning with the GYFY database. The performance of the model was compared with a traditional Cox model by C-indexes. We also explored the model's performance in the setting of missing data and generated the artificial intelligence (AI) certainty of the prediction. Results: The C-indexes in the training dataset (SEER full sample) with DeepSurv and Cox model were 0.792 (0.791-0.792) and 0.714 (0.713-0.715), respectively. The values were 0.727 (0.704-0.750) and 0.692 (0.666-0.718) after applying the trained model in the test dataset (GYFY). The AI certainty of the DeepSurv model output was from 0.98 to 1. For transfer learning through fine-tuning, the results showed that the test set could achieve a higher C-index (20% vs. 30% fine-tuning data) with more fine-tuning dataset. Besides, the DeepSurv model was more accurate than the traditional Cox model in predicting with missing data, after random data loss of 5%, 10%, 15%, 20%, and median fill-in missing values. Conclusions: The model outperformed the traditional Cox model, was robust with missing data and provided the AI certainty of prediction. It can be used for patient self-evaluation and risk stratification in clinical trials. Researchers can fine-tune the pre-trained model and integrate their own database to explore other prognostic factors.
RESUMEN
Anti-N-methyl-D-aspartate (anti-NMDA) receptor encephalitis is an autoimmune disorder affecting the N-methyl-D-aspartate receptors in the central and peripheral nervous systems. Gastrointestinal (GI) complications are rarely manifested in this disease. Autoimmune dysregulation of the GI tract is considered a potential cause. We present a challenging case of a 38-year-old male with a history of newly diagnosed epilepsy. He was admitted for three weeks of confusion, hallucinations, and bizarre behavior, and was later diagnosed with anti-NMDA encephalitis from a cerebrospinal fluid (CSF) immunological study. He was treated with a five days course of intravenous immunoglobulin (IVIG) and high-dose steroids. His course was further complicated with GI obstruction and upper GI bleed. His laboratory workup showed lactic acidosis and there was a concern for ischemic bowel injury. Computed tomography (CT) of the abdomen with contrast showed diffuse moderate to pronounced dilated small intestine swirling the mesenteric vessels, concerning for intestinal vascular compromise. The patient also became tachypneic and hypoxic, requiring 6 L of oxygen with a venti-mask. CT of the chest, abdomen, and pelvis with contrast revealed saddle pulmonary embolism (PE) extending to the right and left pulmonary arteries with right heart strain. He underwent emergent explorative laparotomy and emergent catheter-directed thrombectomy. Neither necrotic bowel nor any evidence of perforation or volvulus was noted during the laparotomy; however, the small bowel and the colon were reported to be significantly dilated, hyperemic, and engorged with blood without any evidence of ischemic bowel. He had a complicated 29-day admission course and recovered functional capacity to be safely discharged to a skilled nursing facility for further care. Physicians should keep in mind the gut-brain axis and autonomic effects on gut receptors of any patient presenting with psychosis and seizure disorder to provide timely care and improve morbidity and mortality in this patient population.
