Current Applications of Artificial Intelligence in Sarcoidosis.

PURPOSE: Sarcoidosis is a complex disease which can affect nearly every organ system with manifestations ranging from asymptomatic imaging findings to sudden cardiac death. As such, diagnosis and prognostication are topics of continued investigation. Recent technological advancements have introduced multiple modalities of artificial intelligence (AI) to the study of sarcoidosis. Machine learning, deep learning, and radiomics have predominantly been used to study sarcoidosis. METHODS: Articles were collected by searching online databases using keywords such as sarcoid, machine learning, artificial intelligence, radiomics, and deep learning. Article titles and abstracts were reviewed for relevance by a single reviewer. Articles written in languages other than English were excluded. CONCLUSIONS: Machine learning may be used to help diagnose pulmonary sarcoidosis and prognosticate in cardiac sarcoidosis. Deep learning is most comprehensively studied for diagnosis of pulmonary sarcoidosis and has less frequently been applied to prognostication in cardiac sarcoidosis. Radiomics has primarily been used to differentiate sarcoidosis from malignancy. To date, the use of AI in sarcoidosis is limited by the rarity of this disease, leading to small, suboptimal training sets. Nevertheless, there are applications of AI that have been used to study other systemic diseases, which may be adapted for use in sarcoidosis. These applications include discovery of new disease phenotypes, discovery of biomarkers of disease onset and activity, and treatment optimization.

Medical marijuana certification for patients with sickle cell disease: a report of a single center experience.

More than one-third of adults with sickle cell disease (SCD) report using cannabis-based products. Many states list SCD or pain as qualifying conditions for medical marijuana, but there are few data to guide practitioners whether or whom should be certified. We postulated that certifying SCD patients may lead to a reduction in opioid use and/or health care utilization. Furthermore, we sought to identify clinical characteristics of patients who would request this intervention. Retrospective data obtained over the study period included rates of health care and opioid utilization for 6 months before certification and after certification. Patients who were certified but failed to obtain medical marijuana were compared with those who obtained it. Patients who were certified were invited to participate in a survey regarding their reasons for and thoughts on certification. Patients who were certified for medical marijuana were compared with 25 random patients who did not request certification. Fifty adults with SCD were certified for medical marijuana and 29 obtained it. Patients who obtained medical marijuana experienced a decrease in admission rates compared with those who did not and increased use of edible cannabis products. Neither group had changes in opioid use. Patients who were certified for medical marijuana had higher rates of baseline opioid use and illicit cannabis use compared with those who did not request certification. Most patients with SCD who requested medical marijuana were already using cannabis illicitly. Obtaining medical marijuana decreased inpatient hospitalizations.

Interdependence between dorsal and ventral hippocampus during spatial navigation.

INTRODUCTION: The hippocampus is linked to the formation and retrieval of episodic memories and spatial navigation. In rats, it is an elongated structure divided into dorsal (septal) and ventral (temporal) regions paralleling the respective division in the posterior and anterior hippocampus in humans. The dorsal hippocampus has been suggested to be more important for spatial processing and the ventral to processing anxiety-based behaviors. Far less is known regarding the degree to which these different regions interact during information processing. The anatomical connectivity suggests a flow of information between the dorsal and ventral regions; conversely, there are also commissural connections to the contralateral hippocampus. The current study examined the extent to which information from the dorsal hippocampus interacts with processing in the ipsilateral and contralateral ventral hippocampus following the acquisition of a spatial task. METHODS: Rats were well-trained on a spatial reference version of the water maze, followed by muscimol inactivation of different hippocampal subregions in a within-animal repeated design. Various combinations of bilateral, ipsilateral, and contralateral infusions were used. RESULTS: Combined dorsal and ventral inactivation produced a severe impairment in spatial performance. Inactivation of only the dorsal or ventral regions resulted in intermediate impairment with performance levels falling between controls and combined inactivation. Performance was impaired during contralateral inactivation and was almost equivalent to bilateral dorsal and ventral hippocampus inactivation, while ipsilateral inactivation resulted in little impairment. CONCLUSIONS: Taken together, results indicate that for spatial processing, the hippocampus functions as a single integrated structure along the longitudinal axis.