Machine and deep learning in inflammatory bowel disease.

PURPOSE OF REVIEW: The Management of inflammatory bowel disease (IBD) has evolved with the introduction and widespread adoption of biologic agents; however, the advent of artificial intelligence technologies like machine learning and deep learning presents another watershed moment in IBD treatment. Interest in these methods in IBD research has increased over the past 10 years, and they offer a promising path to better clinical outcomes for IBD patients. RECENT FINDINGS: Developing new tools to evaluate IBD and inform clinical management is challenging because of the expansive volume of data and requisite manual interpretation of data. Recently, machine and deep learning models have been used to streamline diagnosis and evaluation of IBD by automating review of data from several diagnostic modalities with high accuracy. These methods decrease the amount of time that clinicians spend manually reviewing data to formulate an assessment. SUMMARY: Interest in machine and deep learning is increasing in medicine, and these methods are poised to revolutionize the way that we treat IBD. Here, we highlight the recent advances in using these technologies to evaluate IBD and discuss the ways that they can be leveraged to improve clinical outcomes.

Genetic loss of diazepam binding inhibitor in mice impairs social interest.

Neuropsychiatric disorders in which reduced social interest is a common symptom, such as autism, depression, and anxiety, are frequently associated with genetic mutations affecting γ-aminobutyric acid (GABA)ergic transmission. Benzodiazepine treatment, acting via GABA type-A receptors, improves social interaction in male mouse models with autism-like features. The protein diazepam binding inhibitor (DBI) can act as an endogenous benzodiazepine, but a role for DBI in social behavior has not been described. Here, we investigated the role of DBI in the social interest and recognition behavior of mice. The responses of DBI wild-type and knockout male and female mice to ovariectomized female wild-type mice (a neutral social stimulus) were evaluated in a habituation/dishabituation task. Both male and female knockout mice exhibited reduced social interest, and DBI knockout mice lacked the sex difference in social interest levels observed in wild-type mice, in which males showed higher social interest levels than females. The ability to discriminate between familiar and novel stimulus mice (social recognition) was not impaired in DBI-deficient mice of either sex. DBI knockouts could learn a rotarod motor task, and could discriminate between social and nonsocial odors. Both sexes of DBI knockout mice showed increased repetitive grooming behavior, but not in a manner that would account for the decrease in social investigation time. Genetic loss of DBI did not alter seminal vesicle weight, indicating that the social interest phenotype of males lacking DBI is not due to reduced circulating testosterone. Together, these studies show a novel role of DBI in driving social interest and motivation.

Temporal association between serum gelsolin levels and clinical events in a patient with severe falciparum malaria.

Actin is present in high concentrations in most eukaryotic cells and can polymerize into filaments under physiological buffer conditions. As a result of tissue injury and cell lysis, large quantities of actin are released locally and may obstruct the downstream microvasculature, causing further damage to already injured organs. It has been postulated that this mechanism contributes to the development of the adult respiratory distress syndrome and to the diverse complications of falciparum malaria. Actin scavenging proteins--e.g., gelsolin--counteract the effects of extracellular actin, but the capacity of these plasma proteins can be overwhelmed by massive tissue injury. We examined the temporal relationship between serum levels of gelsolin (and tumor necrosis factor-alpha) and the clinical findings for a patient with severe falciparum malaria. The level of gelsolin decreased and then increased as the patient's status first worsened and then improved. We could not determine whether gelsolin served a biologically important function in this patient's recovery or was simply an epiphenomenon of disease activity. Gelsolin levels may be an early prognostic indicator in patients with a systemic inflammatory response syndrome. Moreover, the potential therapeutic role of recombinant human plasma gelsolin in patients with delayed organ dysfunction that commonly follows a self-limited initial insult merits investigation.

Comparison of MicroScan WalkAway system and Vitek system for identification of gram-negative bacteria.

In a prospective side-by-side comparison conducted from September through November 1994, we compared the MicroScan WalkAway system, a conventional biochemical identification system (Dade MicroScan, Inc., Sacramento, Calif.), with the Vitek system (bioMerieux Vitek, Hazelwood, Mo. [analysis software version AMS-RO8.2] for the identification of gram-negative bacteria. Three-hundred thirty-one nonurine isolates and 493 urine isolates were tested. For nonurinary isolates, there was 91.5% agreement between the two methods. For urinary isolates, there was 97.4% agreement between the two methods. Overall, there was 95% agreement between the two systems. The results suggest that the current version of the MicroScan WalkAway system with conventional panels is essentially comparable to the current Vitek system.