Kingsley, Thomas C.

Abstract Hospital census prediction has well-described implications for efficient hospital resource utilization, and recent issues with hospital crowding due to CoVID-19 have emphasized the importance of this task. Our team has been leading an institutional effort to develop machine-learning models that can predict hospital census 12 hours into the future. We describe our efforts at developing accurate empirical models for this task. Ultimately, with limited resources and time, we were able to develop simple yet useful models for 12-hour census prediction and design a dashboard application to display this output to our hospital’s decision-makers. Specifically, we found that linear models with ElasticNet regularization performed well for this task with relative 95% error of +/− 3.4% and that this work could be completed in approximately 7 months.

A 38‐year‐old woman, status‐post renal transplant on immunosuppressive therapy, presented with fever, hypotension, and painful erythematous nodules on her chest, abdomen, and back. Skin biopsy revealed panniculitis with fat necrosis, and corresponding cultures showed no growth. Over the next 5 days, she became obtunded and developed a left hemiparesis. MRI showed non‐enhancing bilateral lesions in the cerebral cortex. She deteriorated and died. At autopsy, the 954 gram brain demonstrated flattened gyri and multiple disseminated necrotic foci. Microscopically, numerous cysts and trophozoites were identified within necrotic foci, consistent with Acanthamoeba spp. Review of the skin biopsy revealed similar organisms. Unlike primary amebic meningoencephalitis in healthy children and young adults caused by Naglearia fowlerii, encephalitis due to Acanthamoeba spp. is a subacute, progressive disease of immunocompromised patients. The double‐walled, cysts of Acanthamoeba spp. stain with H&E and Gomori Methenamine Silver, and may be mistaken for a fungus. Knowledge of the epidemiology and microscopic appearance of Acanthamoeba spp. is essential for accurate and timely diagnosis of this serious and potentially treatable infection.