Systems, methods, and media for indicating the likelihood of an adverse outcome based on medical data

Abstract

Mechanisms, including systems, methods, and media, for indicating an expected outcome of a procedure are provided, the mechanisms including: receiving medical data; processing the medical data to provide processed data; evaluating the processed data using a first machine learning algorithm using a hardware processor; generating the expected outcome of the procedure based on the evaluating the processed data; and causing the expected outcome to be presented to a user. In some embodiments, the medical data is 3D matrix image data from a computed tomography (CT) scan. In some embodiments, processing the medical data includes at least one of decompressing, intensity scaling, and resizing the medical data. In some embodiments, the first machine learning algorithm is a deep convolutional neural network. In some embodiments, the method further comprises: evaluating procedure data using a second machine learning algorithm, wherein expected outcome generated also based on the evaluating of the procedure data.

Description

SYSTEMS, METHODS, AND MEDIA FOR INDICATING THE LIKELIHOOD OF AN ADVERSE OUTCOME BASED ON MEDICAL DATACross-Reference to Related Application

[0001] This application claims the benefit of United States Provisional Patent Application No. 63 / 654,633, filed May 31, 2024 and to United States Provisional Patent Application No.63 / 511,862, filed August 31, 2023, each of which is hereby incorporated by reference herein in its entirety.Background

[0002] Adverse outcomes (e.g., strokes, heart attacks, etc.) resulting from medical procedures are naturally of great concern to medical professionals, hospitals, insurance companies, and, of course, patients and their families.

[0003] Accordingly, mechanisms, including systems, methods, and media for indicating the likelihood of adverse outcomes based on medical data are desirable.Summary

[0004] In accordance with some embodiments, mechanisms, which can include systems, methods, and media for indicating the likelihood of an adverse outcome based on medical data are provided.

[0005] In some embodiments, systems for indicating an expected outcome of a procedure are provided, the systems comprising: memory; and at least one hardware processor coupled to the memory and collectively configured to at least: receive medical data; process the medical data to provide processed data; evaluate the processed data using a first machine learning algorithm using a hardware processor; generate the expected outcome of the procedure based on theevaluating the processed data; and cause the expected outcome to be presented to a user. In some of these embodiments, the medical data is 3D matrix image data from a computed tomography (CT) scan. In some of these embodiments, processing the medical data includes at least one of decompressing, intensity scaling, and resizing the medical data. In some of these embodiments, the first machine learning algorithm is a deep convolutional neural network. In some of these embodiments, the at least one hardware processor is further configured to: evaluate procedure data using a second machine learning algorithm, wherein expected outcome generated also based on the evaluating of the procedure data. In some of these embodiments, the second machine learning algorithm is a deep neural network. In some of these embodiments, the expected outcome includes a prediction of a risk associated with an outcome and an indication of a risk threshold for the outcome.

[0006] In some embodiments, methods for indicating an expected outcome of a procedure are provided, the methods comprising: receiving medical data; processing the medical data to provide processed data; evaluating the processed data using a first machine learning algorithm using a hardware processor; generating the expected outcome of the procedure based on the evaluating the processed data; and causing the expected outcome to be presented to a user. In some of these embodiments, the medical data is 3D matrix image data from a computed tomography (CT) scan. In some of these embodiments, processing the medical data includes at least one of decompressing, intensity scaling, and resizing the medical data. In some of these embodiments, the first machine learning algorithm is a deep convolutional neural network. In some of these embodiments, the method further comprises: evaluating procedure data using a second machine learning algorithm, wherein expected outcome generated also based on the evaluating of the procedure data. In some of these embodiments, the second machine learningalgorithm is a deep neural network. In some of these embodiments, the expected outcome includes a prediction of a risk associated with an outcome and an indication of a risk threshold for the outcome.

[0007] In some embodiments, non-transitory computer-readable media containing computer executable instructions that, when executed by a processor, cause the processor to perform a method for indicating an expected outcome of a procedure are provided, the method comprising: receiving medical data; processing the medical data to provide processed data; evaluating the processed data using a first machine learning algorithm; generating the expected outcome of the procedure based on the evaluating the processed data; and causing the expected outcome to be presented to a user. In some of these embodiments, the medical data is 3D matrix image data from a computed tomography (CT) scan. In some of these embodiments, processing the medical data includes at least one of decompressing, intensity scaling, and resizing the medical data. In some of these embodiments, the first machine learning algorithm is a deep convolutional neural network. In some of these embodiments, the method further comprises: evaluating procedure data using a second machine learning algorithm, wherein expected outcome generated also based on the evaluating of the procedure data. In some of these embodiments, the second machine learning algorithm is a deep neural network. In some of these embodiments, the expected outcome includes a prediction of a risk associated with an outcome and an indication of a risk threshold for the outcome.Brief Description of the Drawings

[0008] FIG. 1 is an example of a block diagram of a system architecture in accordance with some embodiments.

[0009] FIG. 2 is an example of a block diagram of hardware that can be used to implement certain components of FIG. 1 in accordance with some embodiments.

[0010] FIG. 3 is an example of a high-flow diagram in accordance with some embodiments.

[0011] FIG. 4 is an example of another high-level flow diagram in accordance with some embodiments.

[0012] FIG. 5 is an example of a flow diagram of a process for training a machine learning algorithm in accordance with some embodiments.

[0013] FIG. 6 is an example of a flow diagram of a process for determining and presenting possible outcome data in accordance with some embodiments.

[0014] FIG. 7 is an example of a user interface in accordance with some embodiments.Detailed Description

[0015] Mechanisms, which can include systems, methods, and media for indicating the likelihood of an adverse outcome based on medical data are provided.

[0016] In some embodiments, the mechanisms described herein can predict the likelihood of an adverse outcome based on medical data, such as computed tomography (CT) scan data. In some embodiments, the mechanisms described herein can predict the likelihood of a patient having a stroke. In some embodiments, the mechanisms described herein can predict the likelihood of a patient having a stroke based on CT scan data. In some embodiments, the mechanisms described herein can predict the likelihood of a patient having a stroke based on CT scan data as well as data regarding a procedure that the patient is undergoing. For example, data regarding a procedure that the patient is undergoing can include data indicating whether cerebral protection was / is to be used, data indicating a prosthesis valve type that was / is to be used, and / or any other data regarding a patient's procedure.

[0017] In some embodiments, the likelihood of an adverse outcome can be determined using one or more machine learning algorithms. Any suitable number and type of machine learning algorithms can be used, in some embodiments. For example, in some embodiments, a convolutional neural network (CNN), which can be a deep CNN in some such embodiments, can be used as a machine learning algorithm that is used in the mechanisms described herein. As another example, in some embodiments, a residual network with aggregated transformations leveraging cardinality can be used as a machine learning algorithm that is used in the mechanisms described herein. As still another example, in some embodiments, a logistic regression algorithm can be used as a machine learning algorithm that is used in the mechanisms described herein. As yet another example, in some embodiments, a SEResNextlOl machine learning algorithm available from The Py Torch Foundation can be used as a machine learning algorithm that is used in the mechanisms described herein. In some such, embodiments, the machine learning algorithm can use Squeeze-and-Excitation (SE) blocks as described in Hu et al., Squeeze-and-Excitation Networks, https: / / arxiv.org / pdf / 1709.01507.pdf, which is hereby incorporated by reference here in in its entirety.

[0018] Turning to FIG. 1, an example block diagram 100 of a system architecture in accordance with some embodiments is shown. As illustrated, the system includes medical data source(s) 102 (which can include medical image data source(s) (which can provide medical image data (e.g., CT image data)) 104, outcome data source(s) (which can indicate any suitable outcome data) 106, and procedure data source(s) (which can indicate any suitable procedure data) 108. Although three medical data sources are shown in FIG. 1, any suitable number of medical data sources can be provided, and they can be provided in any suitable one or more devices, in some embodiments. Each medical data source can provide any suitable data in anysuitable format, in some embodiments. For example, in some embodiments, each medical data source can be implemented using specialty equipment, such as a CT imager, or general-purpose equipment, such as a computer, a database, a server, etc.

[0019] The system can also include one or more machine learning servers 110 that can each implement any suitable one or more machine learning algorithms. The machine learning server(s) can be administered by an administrator using a machine leaning admin device 112.

[0020] The system can further include one or more web interface servers 120 that can each provide one or more web interfaces that can be accessed by a user for interacting with the system. The web interface server(s) can be administered by an administrator using a web interface admin device 122.

[0021] The system can still further include one of more user devices 116 and 118 that can be used by a user to access interfaces provided by the web interface server(s).

[0022] The system can further include a communication network 122 for connecting the above-described components. The communication network can be any suitable combination of one or more wired and / or wireless networks in some embodiments. For example, in some embodiments, the communication network can include any one or more of the Internet, a mobile data network, a satellite network, a local area network, a wide area network, a telephone network, a cable television network, a WiFi network, a WiMax network, and / or any other suitable communication network.

[0023] In some embodiments, the medical data source(s), the machine learning server(s), the machine learning admin device, the web interface server(s), the web interface admin device, and / or the user device(s) can be implemented in or utilize any suitable computing device(s). For example, in some embodiments, these components can be implemented using any suitablegeneral -purpose computer or sped al -purpose computer(s). Any such general-purpose computer or special-purpose computer can include any suitable hardware. For example, as illustrated in example hardware 200 of FIG. 2, such hardware can include a hardware processor 202, memory and / or storage 204, an input device controller 206, an input device 208, display / audio drivers 210, display and audio output circuitry 212, communication interface(s) 214, an antenna 216, and a bus 218.

[0024] Hardware processor 202 can include any suitable hardware processor, such as a graphical processing unit (GPU), tensor processing unit (TPU) and quantum processing unit (QPU), a microprocessor, a micro-controller, digital signal processor(s), dedicated logic, and / or any other suitable circuitry for controlling the functioning of a general-purpose computer or a special purpose computer in some embodiments. For example, when used to implement a machine learning server the hardware processor can be implemented using eight NVIDIA Al 0G Tensor Core GPUs and 192 vCPUs.

[0025] Memory and / or storage 204 can be any suitable memory and / or storage for storing programs, data, and / or any other suitable information in some embodiments. For example, memory and / or storage 204 can include: hard disk storage; optical media; Random Access Memory (RAM) (such as dynamic RAM, static RAM, etc.); NAND flash memory; NOR flash memory; any other suitable flash technology; phase change memory technology; and / or other any other suitable volatile and / or non-volatile memory storage technology. For example, when used to implement a machine learning server the memory can include 192 GiB GPU memory and 768 GiB Random Access Memory (RAM).

[0026] Input device controller 206 can be any suitable circuitry for controlling and receiving input from input device(s) 208, in some embodiments. For example, input device controller 206can be circuitry for receiving input from an input device 208 such as a touch screen, from one or more buttons (such as on a keyboard), from a voice recognition circuit, from a microphone, from a camera, from an optical sensor, from an accelerometer, from a temperature sensor, from a near field sensor, and / or any other type of input device.

[0027] Display / audio drivers 210 can be any suitable circuitry for controlling and driving output to one or more display / audio output circuitries 212 in some embodiments. For example, display / audio drivers 210 can be circuitry for driving one or more display / audio output circuitries 212, such as an LCD display, a speaker, an LED, or any other type of output device.

[0028] Communication interface(s) 214 can be any suitable circuitry for interfacing with one or more communication networks (such as the communication network shown in FIG. 1). For example, interface(s) 214 can include network interface card circuitry, wireless communication circuitry, and / or any other suitable type of communication network circuitry.

[0029] Antenna 216 can be any suitable one or more antennas for wirelessly communicating with a communication network in some embodiments. In some embodiments, antenna 216 can be omitted when not needed.

[0030] Bus 218 can be any suitable mechanism for communicating between two or more components 202, 204, 206, 210, and 214 in some embodiments.

[0031] Any other suitable components can additionally or alternatively be included in hardware 200 in accordance with some embodiments.

[0032] In some embodiments, two or more of devices 104, 106, 108, 110, 112, 116, 118, 120, and 122 can be combined. For example, devices 104, 110, 116, and 120 can be implemented in a single device, such as a CT imager, in some embodiments.

[0033] As noted above and as illustrated in FIG. 3, in some embodiments, the mechanisms described herein can predict the likelihood of an adverse outcome 306 based on medical data 302, such as computed tomography (CT) scan data, using one or more machine learning algorithms 304. For example, in some embodiments, the mechanisms described herein can predict the likelihood of a patient having a stroke using suitable input data and a suitable trained machine learning algorithm.

[0034] As shown in FIG. 4, in some embodiments, the mechanisms described herein can predict the likelihood of an adverse outcome 412 based on medical data 402, such as computed tomography (CT) scan data, as well as data regarding a procedure that the patient is undergoing 404, using one or more machine learning algorithms 406, 408, and 410.

[0035] Training for a machine learning algorithm can be performed in any suitable manner, in some embodiments.

[0036] Turning to FIG. 5, an example 500 of a process for training a machine learning algorithm in accordance with some embodiments is shown. In some embodiments, this process can begin by receiving CT scan data (for example) and corresponding stroke outcome data (for example) at 502. Any suitable type of CT scan data and corresponding stroke outcome data, any suitable format of same, and any suitable amount of same, can be received, in some embodiments. For example, in some embodiments, the CT scan data can represent CT scans of chests with contrast injection or non-injected chest scans. As another example, in some embodiments, CT scans can be received in DICOM or NIFTY format. In some embodiments, the CT scan data can be received in a compressed format. In some embodiments, the CT scan data and the corresponding stroke outcome data can be received from any suitable source in anysuitable manner. For example, in some embodiments, the CT scan data can be received as 3D image data in a 3D matrix format that is fed into an image dataset loader.

[0037] Next, as shown in FIG. 5, in some embodiment, the CT scan data can be processed at 504 prior to being used for training. Any suitable processing can be performed in some embodiments. For example, in some embodiments, the CT scan data can be processed to perform intensity scaling, to perform image resizing (e.g., to a 96*96*96-pixel format), to perform random rotation (e.g., 90°), to add random gaussian noise, to perform random affine transformations, and / or to perform any other suitable functions. While these functions may be random, these functions may similarly be pseudorandom, or non-random, in some embodiments.

[0038] Then, as shown in FIG. 5, the machine learning algorithm can be trained at 506. In some embodiments, any suitable portion of the training dataset can be used to train the machine learning algorithm (e.g., such as 80%) and another portion of the training dataset can be used to test or validate the training of the machine learning algorithm (e.g., such as 20%).

[0039] Training of the machine learning algorithm can be performed in any suitable manner, in some embodiments. In some embodiments, an Adaptive Moment Estimation (Adam) optimizer can be used while training the machine learning algorithm. In some embodiments, a cross-entropy loss function can be used in the machine learning algorithm. In some embodiments, during training, the machine learning algorithm can implement input data shuffling between epochs.

[0040] Any suitable parameters can be used in the machine learning algorithm, in some embodiments. For example, in some embodiments, the machine learning algorithm can use any suitable number of epochs, such as 300 epochs. As another example, in some embodiments, the machine learning algorithm can use any suitable number of batches, such as 36 batches. As yetanother example, in some embodiments, the machine learning algorithm can implement any suitable number of parallel workers, such as 22 parallel workers. As still another example, in some embodiments, the machine learning algorithm can implement any suitable dropout rate, such as a 20% dropout rate. As yet another example, in some embodiments, the machine learning algorithm can implement any suitable number of channels, such as one channel. As still another example, in some embodiments, the machine learning algorithm can implement any suitable number of output classes, such as two output classes (e.g., whether the patient is at high risk of a stroke or not). As yet another example, in some embodiments, the machine learning algorithm can implement any suitable learning rate, such as a learning rate of 0.0001.

[0041] Next, at 508, the process can validate the training of the machine learning algorithm. In some embodiments, any suitable parameters can be used to determine whether a machine learning algorithm has been sufficiently trained, such as, area under the curve (AUC) applied on the sigmoid transformed model output, accuracy, precision, recall, AUC precision-recall, and / or any other suitable parameter.

[0042] In some embodiments, as shown in FIG. 5, after training, model weights of the machine learning algorithm can be checked for compatibility with a GPU and / or a CPU to be used in production at 510. Model weights of the machine learning algorithm can be checked for compatibility with a GPU and / or a CPU to be used in production in any suitable manner, in some embodiments.

[0043] In some embodiment, as also shown in FIG. 5, after training, the performance of the machine learning algorithm can be checked with fixed weights on the entire dataset to confirm that the algorithm has adequate performance at 512. The performance of the machinelearning algorithm can be checked with fixed weights on the entire dataset to confirm that the algorithm has adequate performance in any suitable manner, in some embodiments.

[0044] Turning to FIG. 6, an example 600 of a production (i.e., not training or validation)) process using the machine learning algorithm to determine the likelihood of a future adverse outcome in accordance with some embodiments is shown.

[0045] As illustrated, at 602, this process can receive CT scan data (e.g., a CT scan's 3D matrix image data) having the same or similar characteristics as the CT scan data received for training, as described above, in some embodiments. This data can be received from any suitable source and in any suitable manner, in some embodiments.

[0046] Next, as shown, at 604, the received data can be processed in any suitable manner. For example, in some embodiments, in production, the received CT scan data can be processed in the same or similar manner to that in which the training data was processed. More particularly, for example, the data can be decompressed, intensity scaled, and resized to have any suitable image such (e.g., such as 96*96*96 pixels).

[0047] Then, the received data can be evaluated at 606 to determine outcome data using the trained machine learning algorithm. Before doing so, in some embodiments, the machine learning algorithm can be loaded using its initial architecture (e.g., SEResNextlOl) and the trained parameters, weights, biases, and / or any other suitable parameters applied, in some embodiments. In some embodiments, the model can be loaded on a GPU or a CPU.

[0048] In some embodiments, an output vector of the machine learning algorithm can be processed by a sigmoid function and then divided by a clinical relevance correction factor. A clinical threshold value can then be used to interpret the output value as a low risk of stroke or a high risk of stroke, in some embodiments.

[0049] Finally, as shown in FIG. 6, outcome data can be presented at 608. The outcome data can be presented in any suitable manner, in some embodiments. For example, in some embodiments, a web application user interface as shown in FIG. 7 can be provided to present one or more of the output value and an interpretation to the clinician user for decision support. In some embodiments, a graphical histogram representation can be provided in the web application user interface as shown in FIG. 7. In some embodiments, the web application user interface can present likelihoods of stroke (or another adverse outcome) based on two or more possible treatment strategies. In some embodiments, slices of DICOM images used for prediction can be extracted and shown to a user in the web application. In some embodiments, any suitable number of ordered and evenly distributed slices can be selected regularly from the pool of slices to provide a sample representation from the pool. In some embodiment, the slices can be selected based on their relevance / importance to the algorithm by selecting the slices with the highest density of relevant pixels as provided by occlusion and heat maps as described below.

[0050] In some embodiments, anatomy areas that the machine learning algorithm has deemed important for prediction can be presented to the user. In some embodiments, heat maps and / or occlusions maps based on importance of anatomy areas in predicting outcomes can be presented to the user. In some embodiments, the most-relevant areas can be identified as an aggregation of pixels on a given slice or an aggregation of voxels on a given 3D volume, wherein important pixels and voxels can be identified through the relationship input-weights.

[0051] As described above in connection with FIG. 4, in some embodiments, the mechanisms described above can be augmented to account for changeable procedure-related factors such as the usage of cerebral protection and prosthesis valve design using any suitable procedure data. Any suitable changeable procedure-related factors can be considered, and dataregarding these changeable procedure-related factors can be received and represented in, any suitable manner, in some embodiments. For example, in some embodiments, such data when representing categorical data can be one-hot encoded.

[0052] As also shown in FIG. 4, in some embodiments, a predictive model that considers changeable procedure-related factors can be a combination of the previously described machine learning algorithm (e.g., a deep CNN) and a second machine learning algorithm (e.g., a deep neural network) attached in parallel with it, with their combined parameters resulting in the output prediction.

[0053] In some embodiments, such a combined model can be trained similarly to what is described in connection with FIG. 5 except that tabular data about procedure-related factors (such as cerebral protection (binary) and prosthesis valve type (e.g., 13 different valve types)) can also be fed alongside the patient CT scan data to the combined model. As mentioned above, this category data can be one-hot encoded.

[0054] In some embodiments, the output of the combined machine learning algorithms is adverse outcome (e.g., stroke) probability estimates by scenario. For example, in some embodiments, the scenarios can include procedure data indicating whether cerebral protection was / will be used, what type of valve design (e.g., number 1, number 2, etc.) was / will be used, and / or any other suitable data regarding the procedure. Based upon this estimate, a clinician user can choose to use the scenario that would result in the lowest stroke risk, in some embodiments.

[0055] As shown in FIG. 4, two machine learning algorithms can be used, in some embodiments. In some embodiments, SEResNextlOl can be used as machine learning algorithm 406 for receiving the CT scan data and a deep neural network can be used as machine learning algorithm 408 for receiving the procedure data. The outputs of these machine learningalgorithms can be concatenated or combined at 410 in any suitable manner, in some embodiments.

[0056] Turning to FIG. 7, an example of a user interface that can be presented to a user in accordance with some embodiments is shown. As illustrated, predictions for multiple outcomes can be provided. For example, in some embodiments, predictions for stroke, pacemaker, mortality, and cardiac technical failure can be provided. In each case, indicators of the probability in the present case (i . e. , for the patient whose data was provided) for an adverse outcome and of the threshold for that probability being considered high risk can be shown. More particularly, for example, for stroke, in the present case, the risk can be shown as 5.37% and the threshold for high risk of stroke can be shown as 2%. As another example, for pacemaker, in the present case, the risk can be shown as 16.18% and the threshold for high risk of pacemaker can be shown as 2%. As still another example, for mortality, in the present case, the risk can be shown as 0.1% and the threshold for high risk of mortality can be shown as 1%. As yet another example, for cardiac technical failure, in the present case, the risk can be shown as 0.14% and the threshold for high risk of cardiac technical failure can be shown as 1%. As shown, in some embodiments, graphical histogram representations can be used for clarity.

[0057] It should be understood that at least some of the above-described blocks of the processes of FIGS. 5 and / or 6 can be executed or performed in any order or sequence not limited to the order and sequence shown in and described in the figures. Also, some of the above blocks of the processes of FIGS. 5 and / or 6 can be executed or performed substantially simultaneously where appropriate or in parallel to reduce latency and processing times. Additionally or alternatively, some of the above described blocks of the processes of FIGS. 5 and / or 6 can be omitted.

[0058] In some embodiments, any suitable computer readable media can be used for storing instructions for performing the functions and / or processes described herein. For example, in some embodiments, computer readable media can be transitory or non-transitory. For example, non-transitory computer readable media can include media such as non-transitory magnetic media (such as hard disks, floppy disks, and / or any other suitable magnetic media), non- transitory optical media (such as compact discs, digital video discs, Blu-ray discs, and / or any other suitable optical media), non-transitory semiconductor media (such as flash memory, electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), and / or any other suitable semiconductor media), any suitable media that is not fleeting or devoid of any semblance of permanence during transmission, and / or any suitable tangible media. As another example, transitory computer readable media can include signals on networks, in wires, conductors, optical fibers, circuits, any suitable media that is fleeting and devoid of any semblance of permanence during transmission, and / or any suitable intangible media.

[0059] Although the invention has been described and illustrated in the foregoing illustrative embodiments, it is understood that the present disclosure has been made only by way of example, and that numerous changes in the details of implementation of the invention can be made without departing from the spirit and scope of the invention. Features of the disclosed embodiments can be combined and rearranged in various ways.

Claims

What is claimed is:

1. A system for indicating an expected outcome of a procedure, comprising: memory; and at least one hardware processor coupled to the memory and collectively configured to at least: receive medical data; process the medical data to provide processed data; evaluate the processed data using a first machine learning algorithm using a hardware processor; generate the expected outcome of the procedure based on the evaluating the processed data; and cause the expected outcome to be presented to a user.

2. The system of claim 1, wherein the medical data is 3D matrix image data from a computed tomography (CT) scan.

3. The system of claim 1, wherein processing the medical data includes at least one of decompressing, intensity scaling, and resizing the medical data.

4. The system of claim 1, wherein the first machine learning algorithm is a deep convolutional neural network.

5. The system of claim 1, wherein the at least one hardware processor is further configured to: evaluate procedure data using a second machine learning algorithm,wherein expected outcome generated also based on the evaluating of the procedure data.

6. The system of claim 5, wherein the second machine learning algorithm is a deep neural network.

7. The system of claim 1, wherein the expected outcome includes a prediction of a risk associated with an outcome and an indication of a risk threshold for the outcome.

8. A method for indicating an expected outcome of a procedure, comprising: receiving medical data; processing the medical data to provide processed data; evaluating the processed data using a first machine learning algorithm using a hardware processor; generating the expected outcome of the procedure based on the evaluating the processed data; and causing the expected outcome to be presented to a user.

9. The method of claim 8, wherein the medical data is 3D matrix image data from a computed tomography (CT) scan.

10. The method of claim 8, wherein processing the medical data includes at least one of decompressing, intensity scaling, and resizing the medical data.11 . The method of claim 8, wherein the first machine learning algorithm is a deep convolutional neural network.

12. The method of claim 8, further comprising: evaluating procedure data using a second machine learning algorithm, wherein expected outcome generated also based on the evaluating of the procedure data.

13. The method of claim 12, wherein the second machine learning algorithm is a deep neural network.

14. The method of claim 8, wherein the expected outcome includes a prediction of a risk associated with an outcome and an indication of a risk threshold for the outcome.

15. Anon-transitory computer-readable medium containing computer executable instructions that, when executed by a processor, cause the processor to perform a method for indicating an expected outcome of a procedure, the method comprising: receiving medical data; processing the medical data to provide processed data; evaluating the processed data using a first machine learning algorithm; generating the expected outcome of the procedure based on the evaluating the processed data; and causing the expected outcome to be presented to a user.

16. The non-transitory computer-readable medium of claim 15, wherein the medical data is 3D matrix image data from a computed tomography (CT) scan.

17. The non-transitory computer-readable medium of claim 15, wherein processing the medical data includes at least one of decompressing, intensity scaling, and resizing the medical data.

18. The non-transitory computer-readable medium of claim 15, wherein the first machine learning algorithm is a deep convolutional neural network.

19. The non-transitory computer-readable medium of claim 15, wherein the method further comprises: evaluating procedure data using a second machine learning algorithm, wherein expected outcome generated also based on the evaluating of the procedure data.

20. The non-transitory computer-readable medium of claim 19, wherein the second machine learning algorithm is a deep neural network.

21. The non-transitory computer-readable medium of claim 15, wherein the expected outcome includes a prediction of a risk associated with an outcome and an indication of a risk threshold for the outcome.

Images