Abstract: A body fluid volume estimation device includes a pre-training unit, a transfer learning unit, and an estimation unit. The pre-training unit performs pre-training by using, as supervised information, information indicating body fluid volumes of the multiple patients when face images of multiple patients are captured. The transfer learning unit further performs transfer learning on multiple face images of one specific patient after the pre-training, and constructs a trained model. The estimation unit estimates, by inputting a face image of the one specific patient to the trained model, a body fluid volume at a point in time at which the face image of the one specific patient is captured. By estimating a body fluid volume from a face image by machine learning, the body fluid volume can be used for assistance such as decision making of a user.

Abstract: A body fluid volume estimation device includes a pre-training unit, a transfer learning unit, and an estimation unit. The pre-training unit performs pre-training by using, as supervised information, information indicating body fluid volumes of the multiple patients when face images of multiple patients are captured. The transfer learning unit further performs transfer learning on multiple face images of one specific patient after the pre-training, and constructs a trained model. The estimation unit estimates, by inputting a face image of the one specific patient to the trained model, a body fluid volume at a point in time at which the face image of the one specific patient is captured. By estimating a body fluid volume from a face image by machine learning, the body fluid volume can be used for assistance such as decision making of a user.

Abstract: A body fluid volume estimation device includes a pre-training unit, a transfer learning unit, and an estimation unit. The pre-training unit performs pre-training by using, as supervised information, information indicating body fluid volumes of the multiple patients when face images of multiple patients are captured. The transfer learning unit further performs transfer learning on multiple face images of one specific patient after the pre-training, and constructs a trained model. The estimation unit estimates, by inputting a face image of the one specific patient to the trained model, a body fluid volume at a point in time at which the face image of the one specific patient is captured. By estimating a body fluid volume from a face image by machine learning, the body fluid volume can be used for assistance such as decision making of a user.

Abstract: A body fluid volume estimation device includes a pre-training unit, a transfer learning unit, and an estimation unit. The pre-training unit performs pre-training by using, as supervised information, information indicating body fluid volumes of the multiple patients when face images of multiple patients are captured. The transfer learning unit further performs transfer learning on multiple face images of one specific patient after the pre-training, and constructs a trained model. The estimation unit estimates, by inputting a face image of the one specific patient to the trained model, a body fluid volume at a point in time at which the face image of the one specific patient is captured. By estimating a body fluid volume from a face image by machine learning, the body fluid volume can be used for assistance such as decision making of a user.

Abstract: Provided are a disease-condition assessment device for being capable of assessing an epileptic condition of a subject, a disease-condition assessment method, a program for disease-condition assessment device, and a disease-condition assessment system. The gaze data indicating a subject's gazing point measured when the subject is driving a vehicle is acquired, the driving-characteristic data indicating driving characteristics of the subject for the vehicle is acquired), and the epileptic condition of the subject is assessed depending on the relationship between the gaze data and the driving-characteristic data.

Abstract: Provided are a disease-condition assessment device for assessing a disease condition of a subject, a disease-condition assessment method, a program for disease-condition assessment device, and a disease-condition assessment system. The operation-quantity data that the subject operates the vehicle is acquired, the operation-related data in the components of a predetermined frequency range is calculated from the operation-quantity data, the operation value that quantifies the operation-related data is calculated from the operation-related data, and the disease condition of the subject is assessed depending on the operation value.

Abstract: Provided are a disease-condition assessment device for assessing a disease condition of a subject, a disease-condition assessment method, a program for disease-condition assessment device, and a disease-condition assessment system. The disease condition assessment device acquires a data of a seat pressure distribution on a seating surface where a subject operating a vehicle is seated, calculates a center position depending on the seat pressure distribution, calculates a degree of laterality in the seat pressure distribution based on the center position, and assesses a disease condition of the subject depending on the degree of laterality.

Abstract: A method of covalently bonding a cyclic nitroxide radical compound to a hydrophobic block of a specific hydrophylic-phobic block copolymer, and polymerized cyclic nitroxide radical compound copolymerized in this manner, as well as use of such a compound, for instance, in the medical field are provided. The compound demonstrates long term stability in vivo under reductive environment.

Abstract: A method of covalently bonding a cyclic nitroxide radical compound to a hydrophobic block of a specific hydrophylic-phobic block copolymer, and polymerized cyclic nitroxide radical compound copolymerized in this manner, as well as use of such a compound, for instance, in the medical field are provided. The compound demonstrates long term stability in vivo under reductive environment.

Abstract: There is provided targeting drug delivery system (DDS) nanoparticles that can be accumulated in target tissues such as inflammatory sites of inflammatory diseases and can thus be utilized in a therapeutic or diagnostic DDS for locally delivering drugs or genes to the affected parts. The present invention provides a pharmaceutical composition for the medical treatment or diagnosis of an inflammatory disease comprising a sugar-modified liposome having a sugar chain bound to the membrane of the liposome.

Abstract: An object of the present invention is to provide a liposome having a sugar chain bonded thereto, the sugar chain having an activity of specifically binding to various lectins (sugar chain recognizing proteins) present on the cell surfaces of various tissues and thus being capable of actually distinguishing a cell and a tissue in vivo, thereby efficiently delivering a medicinal drug or a gene.