Systems and methods for prevention of surgical mistakes
An apparatus, system and process for guiding a surgeon during a medical procedure to prevent surgical mistakes are described. The system may include a machine learning medical procedure server that generates one or more machine learning medical procedure models using, at least, medical procedure data captured during medical procedures performed at a plurality of different medical procedure systems. The system may also include a medical procedure system communicably coupled with the machine learning medical procedure server that receives a selected machine learning medical procedure model from the machine learning medical procedure server, and utilizes the selected machine learning medical procedure model during a corresponding medical procedure to control one or more operations of the medical procedure system.
1 . A method for preventing surgical mistakes, the method comprising:
controlling one or more operations of a medical procedure system during a medical procedure;
wherein controlling the one or more operations of the medical procedure system comprises:
determining at least one expected object expected to be visible during a current step of the corresponding medical procedure;
providing an image of a field of view during the current step as input to a machine learning medical procedure model trained to identify objects; and
in response to determining that the at least one expected object was not identified by the machine learning medical procedure model in the image of the field of view during the current step, preventing a movement of a medical tool coupled with the medical procedure system based on the current step and the determination that the at least one expected object is not visible.
2 . The method of claim 1 , wherein the at least one expected object includes at least one of an anatomical structure and a medical tool.
3 . The method of claim 1 , further comprising identifying the current step of the medical procedure.
4 . The method of claim 3 , wherein identifying the current step of the medical procedure includes identifying the current step of the medical procedure using one or more sensors of a medical tool.
5 . The method of claim 1 , wherein the machine learning medical procedure model is trained to identify at least one of anatomical structures and medical tools visible during the current step of the medical procedure.
6 . The method of claim 1 , wherein the medical procedure system analyzes the medical procedure using the machine learning medical procedure model in real time during the medical procedure.
7 . The method of claim 1 , wherein controlling the one or more operations of the medical procedure system comprises controlling motion of a medical tool coupled with the medical procedure system during the medical procedure.
8 . The method of claim 7 , wherein the medical tool comprises a robotically assisted medical device controlled by a medical professional performing the medical procedure.
9 . The method of claim 1 , wherein controlling the one or more operations of the medical procedure system comprises:
preventing a requested motion of a medical tool based on one or more characteristics of the requested motion;
generating a graphical user interface that requests an acknowledgement of a medical professional to allow the requested motion; and
enabling the medical tool to move in accordance with the requested motion.
10 . The method of claim 1 , further comprising:
tracking, by the medical procedure system, sensor data generated during the corresponding medical procedure from medical tool sensors coupled with the medical procedure system; and
providing the tracked sensor data for generating or refining a machine learning medical procedure model.
11 . A non-transitory computer-readable medium having computer-executable instructions stored thereon that, in response to execution by one or more processors of a medical procedure system, cause the medical procedure system to perform actions for preventing surgical mistakes, the actions comprising:
controlling one or more operations of a medical procedure system during a medical procedure;
wherein controlling the one or more operations of the medical procedure system comprises:
determining at least one expected object expected to be visible during a current step of the corresponding medical procedure;
providing an image of a field of view during the current step as input to a machine learning medical procedure model trained to identify objects; and
in response to determining that the at least one expected object was not identified by the machine learning medical procedure model in the image of the field of view during the current step, preventing a movement of a medical tool coupled with the medical procedure system based on the current step and the determination that the at least one expected object is not visible.
12 . The non-transitory computer-readable medium of claim 11 , wherein the at least one expected object includes at least one of an anatomical structure and a medical tool.
13 . The non-transitory computer-readable medium of claim 11 , wherein the actions further comprise identifying the current step of the medical procedure.
14 . The non-transitory computer-readable medium of claim 13 , wherein identifying the current step of the medical procedure includes identifying the current step of the medical procedure using one or more sensors of a medical tool.
15 . The non-transitory computer-readable medium of claim 11 , wherein the machine learning medical procedure model is trained to identify at least one of anatomical structures and medical tools visible during the current step of the medical procedure.
16 . The non-transitory computer-readable medium of claim 11 , wherein the medical procedure system analyzes the medical procedure using the machine learning medical procedure model in real time during the medical procedure.
17 . The non-transitory computer-readable medium of claim 11 , wherein controlling the one or more operations of the medical procedure system comprises controlling motion of a medical tool coupled with the medical procedure system during the medical procedure.
18 . The non-transitory computer-readable medium of claim 17 , wherein the medical tool comprises a robotically assisted medical device controlled by a medical professional performing the medical procedure.
19 . The non-transitory computer-readable medium of claim 11 , wherein controlling the one or more operations of the medical procedure system comprises:
preventing a requested motion of a medical tool based on one or more characteristics of the requested motion;
generating a graphical user interface that requests an acknowledgement of a medical professional to allow the requested motion; and
enabling the medical tool to move in accordance with the requested motion.
20 . The non-transitory computer-readable medium of claim 11 , wherein the actions further comprise:
tracking, by the medical procedure system, sensor data generated during the corresponding medical procedure from medical tool sensors coupled with the medical procedure system; and
providing the tracked sensor data for generating or refining a machine learning medical procedure model.