公开(公告)号：US20210183484A1

公开(公告)日：2021-06-17

申请号：US17114184

申请日：2020-12-07

Applicant: SURGICAL SAFETY TECHNOLOGIES INC.

Inventor： Chantal SHAIB ,  Jinyue FENG ,  Frank RUDZICZ

IPC: G16H10/60 ,  G06N20/00 ,  G06F17/16

Abstract: Clinical prediction models often use structured variables and provide outcomes that are not readily interpretable by clinicians. Further, text medical notes may contain information not immediately available in structured variables. Applicants propose a hierarchical CNN-Transformer model with an explicit attention mechanism as an interpretable, multi-task clinical language model.

公开(公告)号：US20200265273A1

公开(公告)日：2020-08-20

申请号：US16791919

申请日：2020-02-14

Applicant: SURGICAL SAFETY TECHNOLOGIES INC.

Inventor： Haiqi WEI ,  Teodor Pantchev GRANTCHAROV ,  Babak TAATI ,  Yichen ZHANG ,  Frank RUDZICZ ,  Kevin Lee YANG

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06N20/10 ,  G06T7/00 ,  G06T3/00

Abstract: Embodiments described herein may provide devices, systems, methods, and/or computer readable medium for adverse event detection and severity estimation in surgical videos. The system can train multiple models for adverse detection and severity estimation. The system can load selected models for real-time adverse event detection and severity estimation.

公开(公告)号：US20240028762A1

公开(公告)日：2024-01-25

申请号：US18026641

申请日：2021-09-15

Applicant: SURGICAL SAFETY TECHNOLOGIES INC.

Inventor： Amar S. CHAUDHRY ,  Frank RUDZICZ ,  Tianbao LI ,  Shuja KHALID ,  Kevin YANG ,  Teodor Pantchev GRANTCHAROV

IPC: G06F21/62 ,  G16H10/60 ,  G06F3/0482

CPC classification number: G06F21/6254 ,  G16H10/60 ,  G06F3/0482

Abstract: Systems, devices, and methods of configuring and operating a de-identification system are provided. At least one electronic data model is maintained, which includes a plurality of de-identification requirements for removing personal information from clinical data obtained in a clinical environment, the plurality of de-identification requirements including requirements applicable to at least one jurisdiction of a plurality of jurisdictions. An identifier identifying one of the jurisdictions is received. The data model is traversed to determine a subset of the de-identification requirements applicable to the identified jurisdiction. Data defining a user selection of operating parameters of the de-identification system are received. The user selection is analyzed for conformity with the subset of de-identification requirements. In response to determining the user selection conforms with the subset of de-identification requirements, a signal is generated indicating the conformity. A configuration data structure is generated including data reflective of the user selection of operating parameters.

公开(公告)号：US20200367974A1

公开(公告)日：2020-11-26

申请号：US16881906

申请日：2020-05-22

Applicant: SURGICAL SAFETY TECHNOLOGIES INC.

Inventor： Shuja KHALID ,  Mitchell Geoffrey GOLDENBERG ,  Teodor Pantchev GRANTCHAROV ,  Babak TAATI ,  Frank RUDZICZ

IPC: A61B34/20 ,  G06N20/00 ,  G06N3/063 ,  G06K9/62 ,  G06K9/00 ,  H04N19/54 ,  A61B34/00

Abstract: Computer implemented methods and systems are provided for training a machine learning architecture for surgical performance tracking and measurement based on surgical procedure video data set. The methods and systems include, in a first aspect, a sequential relation architecture and a dimensionality reduction architecture. In a second aspect, the methods and systems include a surgical instrument instance segmentation architecture, a decomposition model, and a sequential relation architecture. The video data is processed on a frame level to generate compressed or reduced representations of the video data.

公开(公告)号：US20230419503A1

公开(公告)日：2023-12-28

申请号：US18037987

申请日：2021-11-19

Applicant: SURGICAL SAFETY TECHNOLOGIES INC.

Inventor： Frank RUDZICZ ,  Amar S. CHAUDHRY ,  Shuja KHALID ,  Teodor Pantchev GRANTCHAROV ,  Tianbao LI

IPC: G06T7/20

CPC classification number: G06T7/20 ,  G06T2207/10016 ,  G06T2207/20084 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/30196 ,  G06T2207/30242

Abstract: Systems and methods for traffic monitoring in an operating room are disclosed herein. Video data of an operating room is received, the video data captured by a camera having a field of view for viewing movement of a plurality of individuals in the operating room during a medical procedure. An event data model is stored, the model including data defining a plurality of possible events within the operating room is stored. The video data is processed to track movement of objects within the operating room, the objects including at least one body part, and the processing using at least one detector trained to detect a given type of the objects. A likely occurrence of one of the possible events is determined based on the tracked movement.