公开(公告)号：US20230329723A1

公开(公告)日：2023-10-19

申请号：US18212790

申请日：2023-06-22

Applicant: Tel HaShomer Medical Research Infrastructure and Services Ltd. ,  The Trendlines Group Ltd.

Inventor： Abraham TSUR ,  Sharon FARBER ,  Roy MASHIACH ,  Yosef HAZAN ,  David SHASHAR ,  Avshalom SHENHAV

IPC: A61B17/122 ,  A61B17/42 ,  A61B5/00 ,  A61F6/08 ,  A61M31/00

CPC classification number: A61B17/122 ,  A61B17/42 ,  A61B17/1227 ,  A61B5/6846 ,  A61F6/08 ,  A61B5/6885 ,  A61B5/6882 ,  A61B5/4356 ,  A61B5/6847 ,  A61M31/00 ,  A61B2017/4225 ,  A61B2090/0811

Abstract: A device for retarding birth including an upper ring for surrounding a cervix, an anchoring component for anchoring the device, and an elastic component for attaching the upper ring to the anchoring component, wherein the elastic component pushes the upper ring and the anchoring component apart. A device for retarding birth including a sleeve for surrounding a cervix along a greater portion of a length of the cervix, a support strip on the sleeve directed along an axis of the sleeve, and a ring at least partially around the sleeve, in which when a top of the sleeve is pushed to expand radially, the support strip pivots on the ring, such that an end of the support strip near the top of the sleeve moves radially outward, and an end of the support strip near the bottom of the sleeve moves radially inward. Related apparatus and methods are also described.

公开(公告)号：US20240170147A1

公开(公告)日：2024-05-23

申请号：US18280254

申请日：2022-03-03

Applicant: Tel HaShomer Medical Research Infrastructure and Services Ltd.

Inventor： Abraham TSUR ,  Raanan MEYER ,  Roni EILENBERG

IPC: G16H50/20 ,  A61B5/00 ,  A61B8/08 ,  G16H50/30

CPC classification number: G16H50/20 ,  A61B5/435 ,  A61B8/0866 ,  G16H50/30

Abstract: There is provided a computer implemented method of training a machine learning model for prediction of unplanned Cesarean Delivery (uCD), comprising: creating or receiving a multi-record training dataset, wherein a record comprises: at least one fetal biometric parameter of a sample fetus obtained by an ultrasonography device, at least one personal parameter of a sample mother of the sample fetus, and a ground truth indicating whether a birth of the sample fetus by the sample mother was a uCD, and training the machine learning model on the multi-record training dataset for generating an outcome indicating likelihood of uCD for a target mother in response to an input of at least one fetal biometric parameter of a target fetus of the target mother and at least one personal parameter of the target mother.