1.Analysis of Adverse Drug Reactions Identified in Nursing Notes Using Reinforcement Learning
Eunjoo JEON ; Youngsam KIM ; Hojun PARK ; Rae Woong PARK ; Hyopil SHIN ; Hyeoun-Ae PARK
Healthcare Informatics Research 2020;26(2):104-111
Electronic Health Records (EHRs)-based surveillance systems are being actively developed for detecting adverse drug reactions (ADRs), but this is being hindered by the difficulty of extracting data from unstructured records. This study performed the analysis of ADRs from nursing notes for drug safety surveillance using the temporal difference method in reinforcement learning (TD learning). Nursing notes of 8,316 patients (4,158 ADR and 4,158 non-ADR cases) admitted to Ajou University Hospital were used for the ADR classification task. A TD(λ) model was used to estimate state values for indicating the ADR risk. For the TD learning, each nursing phrase was encoded into one of seven states, and the state values estimated during training were employed for the subsequent testing phase. We applied logistic regression to the state values from the TD(λ) model for the classification task. The overall accuracy of TD-based logistic regression of 0.63 was comparable to that of two machine-learning methods (0.64 for a naïve Bayes classifier and 0.63 for a support vector machine), while it outperformed two deep learning-based methods (0.58 for a text convolutional neural network and 0.61 for a long short-term memory neural network). Most importantly, it was found that the TD-based method can estimate state values according to the context of nursing phrases. TD learning is a promising approach because it can exploit contextual, time-dependent aspects of the available data and provide an analysis of the severity of ADRs in a fully incremental manner.
2.Effects of the Female Estrous Cycle on the Sexual Behaviors and Ultrasonic Vocalizations of Male C57BL/6 and Autistic BTBR T+ tf/J Mice.
Hyopil KIM ; Junehee SON ; Hyoungseob YOO ; Hakyoo KIM ; Jihae OH ; Daehee HAN ; Yoon HWANG ; Bong Kiun KAANG
Experimental Neurobiology 2016;25(4):156-162
A primary characteristic of autism, which is a neurodevelopmental disorder, is impaired social interaction and communication. Furthermore, patients with autism frequently show abnormal social recognition. In mouse models of autism, social recognition is usually assessed by examining same-sex social behavior using various tests, such as the three-chamber test. However, no studies have examined the ability of male mice with autism to recognize the estrous cycle of female partners. In this study, we investigated the sexual behaviors, especially mounting and ultrasonic vocal communication (USV), of BTBR T+ tf/J (BTBR) mice, which are used as a well-known mouse model of autism, when they encountered estrus or diestrus female mice. As expected, C57BL/6 mice mounted more female mice in the estrus stage compared with the diestrus stage. We found that BTBR mice also mounted more female mice in the estrus stage than female mice in the diestrus stage. Although the USV emission of male mice was not different between estrus and diestrus female mice in both strains, the mounting result implies that BTBR mice distinguish sexual receptivity of females.
Animals
;
Autistic Disorder
;
Diestrus
;
Estrous Cycle*
;
Estrus
;
Female*
;
Humans
;
Interpersonal Relations
;
Male*
;
Mice*
;
Neurodevelopmental Disorders
;
Sexual Behavior*
;
Social Behavior
;
Ultrasonics*
3.Spatial Learning and Motor Deficits in Vacuolar Protein Sorting-associated Protein 13b (Vps13b) Mutant Mouse
Min Jung KIM ; Ro Un LEE ; Jihae OH ; Ja Eun CHOI ; Hyopil KIM ; Kyungmin LEE ; Su Kyeong HWANG ; Jae Hyung LEE ; Jin A LEE ; Bong Kiun KAANG ; Chae Seok LIM ; Yong Seok LEE
Experimental Neurobiology 2019;28(4):485-494
Vacuolar protein sorting-associated protein 13B (VPS13B), also known as COH1, is one of the VPS13 family members which is involved in transmembrane transport, Golgi integrity, and neuritogenesis. Mutations in the VPS13B gene are associated with Cohen syndrome and other cognitive disorders such as intellectual disabilities and autism spectrum disorder (ASD). However, the patho-physiology of VPS13B-associated cognitive deficits is unclear, in part, due to the lack of animal models. Here, we generated a Vps13b exon 2 deletion mutant mouse and analyzed the behavioral phenotypes. We found that Vps13b mutant mice showed reduced activity in open field test and significantly shorter latency to fall in the rotarod test, suggesting that the mutants have motor deficits. In addition, we found that Vps13b mutant mice showed deficits in spatial learning in the hidden platform version of the Morris water maze. The Vps13b mutant mice were normal in other behaviors such as anxiety-like behaviors, working memory and social behaviors. Our results suggest that Vps13b mutant mice may recapitulate key clinical symptoms in Cohen syndrome such as intellectual disability and hypotonia. Vps13b mutant mice may serve as a useful model to investigate the pathophysiology of VPS13B-associated disorders.
Animals
;
Autism Spectrum Disorder
;
Cognition Disorders
;
Exons
;
Humans
;
Intellectual Disability
;
Learning Disorders
;
Memory, Short-Term
;
Mice
;
Models, Animal
;
Muscle Hypotonia
;
Phenotype
;
Rotarod Performance Test
;
Social Behavior
;
Spatial Learning
;
Water