Predicting surgical case lengths using machine learning
The prediction system accesses a flowchart of questions relating to surgical cases and receives, for each of set of surgical case identifiers, surgical case information and an actual surgical case length. The prediction system trains a machine learning model to predict surgical case lengths using the surgical case information and prunes the flowchart by removing questions associated with a uniform set of answers. The prediction system receives, from a client device, a request to reserve an operating room for a surgical case, and transmits, for display via a user interface of the client device, questions from the flowchart. The prediction system receives a feature vector of answers to the transmitted questions from the client device and inputs a type surgical case and the feature vector to the machine learning model, which outputs a predicted surgical case length. The prediction system reserves an operating room for the predicted surgical case length.
1. A computer-implemented method for predicting surgical case length, the method comprising:
accessing a flowchart of questions relating to surgical cases;
receiving, for each of a set of surgical case identifiers, surgical case information and an actual surgical case length, the surgical case information including a surgical case type and one or more feature vectors of answers to questions from the flowchart;
training a machine learning model on the surgical case information and on the actual surgical case lengths for the set of surgical case identifiers, the machine learning model trained to predict a future surgical case length for a future surgical case based on a future surgical case type;
pruning the flowchart by removing questions associated with a uniform set of answers;
receiving, via a user interface of a client device, a request to reserve an operating room for a particular future surgical case, the request including a particular future surgical case type;
transmitting, for display via the user interface of the client device, questions from the flowchart, wherein each question is transmitted based on a previous answer input for a previous question;
receiving, from the client device, one or more feature vectors of answers to the questions entered via the user interface;
inputting the particular future surgical case type and the received one or more feature vectors of answers to the questions to the machine learning model;
determining, for each feature vector, an estimated time, the estimated time representing an amount of time surgical cases associated with the feature vector took to perform;
pruning the flowchart based on the estimated times;
receiving, from the machine learning model, a predicted surgical case length for the particular future surgical case; and
reserving the operating room for the predicted surgical case length.
2. The computer-implemented method of claim 1 , wherein the flowchart is associated with the particular future surgical case type.
3. The computer-implemented method of claim 1 , further comprising:
pruning the flowchart by removing questions with a selection percentage below a lower threshold percentage.
4. The computer-implemented method of claim 1 , wherein the machine learning model is trained for a medical professional who will perform the particular future surgical case.
5. The computer-implemented method of claim 1 , wherein the machine learning model is trained for the particular future surgical case.
6. The computer-implemented method of claim 1 , wherein the machine learning model is trained for a medical facility.
7. The computer-implemented method of claim 1 , further comprising:
transmitting, for display via the user interface, a confirmation of the reservation of the operating room, the confirmation including the predicted surgical case length.
8. A non-transitory computer-readable storage medium comprising instructions executable by a processor, the instructions comprising:
instructions for accessing a flowchart of questions relating to surgical cases;
instructions for receiving, for each of a set of surgical case identifiers, surgical case information and an actual surgical case length, the surgical case information including a surgical case type and one or more feature vectors of answers to questions from the flowchart;
instructions for training a machine learning model on the surgical case information and on the actual surgical case lengths for the set of surgical case identifiers, the machine learning model trained to predict a future surgical case length for a future surgical case based on a future surgical case type;
instructions for pruning the flowchart by removing questions associated with a uniform set of answers;
instructions for receiving, via a user interface of a client device, a request to reserve an operating room for a particular future surgical case, the request including a type-f particular future surgical case type;
instructions for transmitting, for display via the user interface of the client device, questions from the flowchart, wherein each question is transmitted based on a previous answer input for a previous question;
instructions for receiving, from the client device, one or more feature vectors of answers to the questions entered via the user interface;
instructions for inputting the type-f particular future surgical case type and the received one or more feature vectors of answers to the questions to the machine learning model;
instructions for determining, for each feature vector, an estimated time, the estimated time representing an amount of time surgical cases associated with the feature vector took to perform;
instructions for pruning the flowchart based on the estimated times;
instructions for receiving, from the machine learning model, a predicted surgical case length for the particular future surgical case; and
instructions for reserving the operating room for the predicted surgical case length.
9. The non-transitory computer-readable storage medium of claim 8 , wherein the flowchart is associated with the particular future surgical case type.
10. The non-transitory computer-readable storage medium of claim 8 , the instructions further comprising:
instructions for pruning the flowchart by removing questions with a selection percentage below a lower threshold percentage.
11. The non-transitory computer-readable storage medium of claim 8 , wherein the machine learning model is trained for a medical professional who will perform the particular future surgical case.
12. The non-transitory computer-readable storage medium of claim 8 , wherein the machine learning model is trained for the particular future surgical case.
13. The non-transitory computer-readable storage medium of claim 8 , wherein the machine learning model is trained for a medical facility.
14. The non-transitory computer-readable storage medium of claim 8 , the instructions further comprising:
instructions for transmitting, for display via the user interface, a confirmation of the reservation of the operating room, the confirmation including the predicted surgical case length.
15. A computer system comprising:
a computer processor; and
a non-transitory computer-readable storage medium storage instructions that when executed by the computer processor perform actions comprising:
accessing a flowchart of questions relating to surgical cases;
receiving, for each of a set of surgical case identifiers, surgical case information and an actual surgical case length, the surgical case information including a surgical case type and one or more feature vectors of answers to questions from the flowchart;
training a machine learning model on the surgical case information and on the actual surgical case lengths for the set of surgical case identifiers, the machine learning model trained to predict a future surgical case length for a future surgical case based on a future surgical case type;
pruning the flowchart by removing questions associated with a uniform set of answers;
receiving, via a user interface of a client device, a request to reserve an operating room for a particular future surgical case, the request including a particular future surgical case type;
transmitting, for display via the user interface of the client device, questions from the flowchart, wherein each question is transmitted based on a previous answer input for a previous question;
receiving, from the client device, one or more feature vectors of answers to the questions entered via the user interface;
inputting the particular future surgical case type and the received one or more feature vectors of answers to the questions to the machine learning model;
determining, for each feature vector, an estimated time, the estimated time representing an amount of time surgical cases associated with the feature vector took to perform;
pruning the flowchart based on the estimated times;
receiving, from the machine learning model, a predicted surgical case length for the particular future surgical case; and
reserving the operating room for the predicted surgical case length.
16. The computer system of claim 15 , wherein the flowchart is associated with the particular future surgical case type.
17. The computer system of claim 15 , the actions further comprising:
instructions for pruning the flowchart by removing questions with a selection percentage below a lower threshold percentage.