Machine learning based prediction of treatment requirements for neovascular age-related macular degeneration (NAMD)

Abstract

A method and system for managing a treatment for a subject diagnosed with neovascular age-related macular degeneration (nAMD). Spectral domain optical coherence tomography (SD-OCT) imaging data of the subject's retina is received. Retinal feature data is extracted for a plurality of retinal features using the SD-OCT imaging data, the plurality of retinal features being associated with at least one of a set of retinal fluid or a set of retinal layers. Input data formed using the retinal feature data of the plurality of retinal features is sent to a first machine learning model. Based on the input data, a treatment level for an anti-vascular endothelial growth factor (anti-VEGF) treatment to be administered to the subject is predicted via the first machine learning model.

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Provisional Patent Application No. 63 / 172,082, entitled “Machine Learning-Based Prediction of Treatment Requirements for Neovascular Age-Related Macular Degeneration (nAMD),” filed April 7, 2021, which is incorporated by reference in its entirety.

[0002] Field This application relates to treatment requirements for neovascular age-related macular degeneration (nAMD), and more particularly to machine learning-based prediction of treatment requirements in nAMD using spectral domain optical coherence tomography (SD-OCT). [Background technology]

[0003] background Age-related macular degeneration (AMD) is the leading cause of vision loss in subjects over the age of 50. AMD first appears as a dry form of AMD and progresses to a wet form of AMD, also called neovascular AMD (nAMD). In the dry form, small deposits (drusen) form under the macula on the retina, causing deterioration of the retina over time. In the wet form, abnormal blood vessels originating from the choroid layer of the eye grow into the retina and leak fluid from the blood into the retina. Once in the retina, the fluid can immediately distort a subject's vision and over time can damage the retina itself, for example by causing loss of retinal photoreceptors. The fluid can cause the macula to separate from its base, resulting in severe and rapid vision loss.

[0004] Anti-vascular endothelial growth factor (anti-VEGF) agents are frequently used to treat wet AMD (or nAMD). Specifically, anti-VEGF agents can dry the subject's retina, so that the subject's wet AMD can be better controlled to reduce or prevent permanent vision loss. Anti-VEGF agents are typically administered via intravitreal injection, which can be both unfavorable to the subject and can be accompanied by side effects (e.g., redness, eye pain, infection, etc.). The number or frequency of injections can also be a burden to the patient, leading to reduced disease control. Summary of the Invention

[0005] overview In one or more embodiments, a method is provided for managing a treatment for a subject diagnosed with neovascular age-related macular degeneration (nAMD). Spectral domain optical coherence tomography (SD-OCT) imaging data of the subject's retina is received. Retinal feature data is extracted for a plurality of retinal features using the SD-OCT imaging data, and the plurality of retinal features are associated with at least one of a set of retinal fluid or a set of retinal layers. Input data formed using the retinal feature data of the plurality of retinal features is sent to a first machine learning model. Based on the input data, a treatment level for an anti-vascular endothelial growth factor (anti-VEGF) treatment to be administered to the subject is predicted via the first machine learning model.

[0006] In one or more embodiments, a method is provided for managing anti-vascular endothelial growth factor (anti-VEGF) therapy for a subject diagnosed with neovascular age-related macular degeneration (nAMD). A machine learning model is trained using training input data to predict a therapeutic level for the anti-VEGF therapy, the training input data being formed using training optical coherence tomography (OCT) imaging data. Input data for the trained machine learning model is received, the input data including retinal feature data for a plurality of retinal features. A therapeutic level for the anti-VEGF therapy to be administered to the subject is predicted using the input data via the trained machine learning model.

[0007] In one or more embodiments, a system for administering anti-vascular endothelial growth factor (anti-VEGF) therapy for a subject diagnosed with neovascular age-related macular degeneration (nAMD) comprises a memory including a machine-readable medium including machine-executable code, and a processor coupled to the memory, the processor configured to execute the machine-executable code to cause the processor to receive spectral domain optical coherence tomography (SD-OCT) imaging data of the subject's retina, extract retinal feature data for a plurality of retinal features using the SD-OCT imaging data, the plurality of retinal features being associated with at least one of a set of retinal fluid or a set of retinal layers, transmit input data formed using the retinal feature data for the plurality of retinal features to a first machine learning model, and predict, via the first machine learning model, a treatment level for the anti-vascular endothelial growth factor (anti-VEGF) therapy to be administered to the subject based on the input data.

[0008] In some embodiments, a system is provided that includes one or more data processors and a non-transitory computer-readable storage medium that includes instructions that, when executed on the one or more data processors, cause the one or more data processors to perform some or all of one or more methods disclosed herein.

[0009] In some embodiments, a computer program product is provided that is tangibly embodied in a non-transitory machine-readable storage medium and includes instructions configured to cause one or more data processors to perform some or all of one or more of the methods disclosed herein.

[0010] Some embodiments of the present disclosure include a system including one or more data processors. In some embodiments, the system includes a non-transitory computer-readable storage medium including instructions that, when executed on the one or more data processors, cause the one or more data processors to perform some or all of the methods and / or some or all of the processes disclosed herein. Some embodiments of the present disclosure include a computer program product tangibly embodied in a non-transitory machine-readable storage medium including instructions configured to cause the one or more data processors to perform some or all of the methods and / or some or all of the processes disclosed herein.

[0011] The terms and expressions used are used as terms of description and not of limitation, and in the use of such terms and expressions there is no intention to exclude equivalents of the features shown and described or portions thereof, but it is recognized that various modifications are possible within the scope of the invention as claimed. Thus, although the invention as claimed has been specifically disclosed by embodiments and optional features, it will be understood that modifications and variations of the concepts disclosed herein may be resorted to by those skilled in the art, and such modifications and variations are considered to be within the scope of the invention as defined by the appended claims. [Brief description of the drawings]

[0012] For a more complete understanding of the principles disclosed herein and the advantages thereof, reference is now made to the following description taken in conjunction with the accompanying drawings.

[0013] [Figure 1] FIG. 1 is a block diagram of a therapy management system according to one or more embodiments.

[0014] [Diagram 2]FIG. 2 is a block diagram of the treatment level prediction system from FIG. 1 being used in a training mode in accordance with one or more embodiments.

[0015] [Diagram 3] 1 is a flowchart of a process for managing treatment for a subject diagnosed with nAMD, according to one or more embodiments.

[0016] [Figure 4] 1 is a flowchart of a process for managing treatment for a subject diagnosed with nAMD, according to one or more embodiments.

[0017] [Diagram 5] 1 is a flowchart of a process for managing treatment for a subject diagnosed with nAMD, according to one or more embodiments.

[0018] [Figure 6] FIG. 2 is a diagram of a segmented OCT image in accordance with one or more embodiments.

[0019] [Figure 7] FIG. 2 is a diagram of a segmented OCT image in accordance with one or more embodiments.

[0020] [Figure 8] 1 is a plot showing the results of a 5-fold cross-validation for a "low" therapeutic level classification according to one or more embodiments.

[0021] [Figure 9] 1 is a plot showing the results of a 5-fold cross-validation for a "high" therapeutic level classification according to one or more embodiments.

[0022] [Figure 10] 1 is a plot of AUC data showing the results of repeated 5-fold cross-validation for the "high" therapeutic level classification according to one or more embodiments.

[0023] [Figure 11] FIG. 1 is a block diagram illustrating an example of a computer system in accordance with one or more embodiments.

[0024] It should be understood that the figures are not necessarily drawn to scale, and that objects within the figures are not necessarily drawn to scale relative to each other. The figures are representations intended to bring clarity and understanding to the various embodiments of the devices, systems, and methods disclosed herein. Wherever possible, the same reference numbers are used throughout the drawings to refer to the same or similar parts. Furthermore, it should be understood that the drawings are not intended to limit the scope of the present teachings in any way. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0025] Detailed Description I. Overview Neovascular age-related macular degeneration (nAMD) can be treated by anti-vascular endothelial growth factor (anti-VEGF) agents designed to treat nAMD by drying the subject's retina to avoid or reduce permanent vision loss. Examples of anti-VEGF agents include ranibizumab and aflibercept. Typically, anti-VEGF agents are administered by intravitreal injection at a frequency ranging from about every 4 weeks to about every 8 weeks. However, some patients may not require such frequent injections.

[0026] The frequency of treatments can generally be a burden to patients and lead to a decline in disease suppression in the real world. For example, after an initial stage of treatment, patients can be scheduled for regular monthly visits pro re nata (PRN) or for the required period. This PRN period can be, for example, 21 to 24 months, or some other monthly period. Visiting the clinic for monthly visits during the PRN period can be a burden for patients who do not require frequent treatment. For example, if a patient requires no more than five infusions during the entire PRN period, traveling for monthly visits can be overly cumbersome. Thus, patient compliance with visits can decrease over time, leading to a decline in disease suppression.

[0027] Thus, there is a need for methods and systems that allow for predicting anti-VEGF treatment requirements to help guide and ensure effective treatment of nAMD patients with infusions of anti-VEGF agents. The embodiments described herein provide methods and systems for predicting the level of treatment required for a patient.

[0028] Some patients may have "low" therapeutic needs or requirements, while others may have "high" therapeutic needs or requirements. The thresholds for defining these therapeutic levels (i.e., "low" or "high" therapeutic levels) may be based on the number of anti-VEGF injections and the duration over which the injections are administered. For example, a patient who has received eight or fewer anti-VEGF injections over a 24-month period may be considered to have a "low" therapeutic level. For example, a patient may receive monthly anti-VEGF injections for three months and five or fewer anti-VEGF injections over a 21-month PRN period. On the other hand, a patient who has received 19 or more anti-VEGF injections over a 24-month period may be considered to belong to the group of patients with a "high" therapeutic level. For example, a patient may receive monthly anti-VEGF injections for three months and 16 or more injections over a 21-month PRN period.

[0029] Additionally, other treatment levels may be evaluated, such as, for example, a "medium" treatment level (e.g., 9-18 injections over a 24 month period) indicating treatment requirements between "low" and "high" treatment needs or requirements. The frequency of injections administered to a patient may be based on what is needed to effectively reduce or prevent ocular complications of nAMD, such as, but not limited to, leakage of vascular fluid into the retina.

[0030] The embodiments described herein use machine learning models to predict treatment levels. In one or more embodiments, a spectral domain optical coherence tomography (SD-OCT) image of a subject's eye with nAMD may be acquired. OCT is an imaging technique in which light is directed at a biological sample (e.g., biological tissue such as an eye) and light reflected from features of the biological sample is collected to capture two- or three-dimensional high-resolution cross-sectional images of the biological sample. In SD-OCT, also known as Fourier domain OCT, signals are detected as a function of light frequency (e.g., as opposed to a function of time).

[0031] The SD-OCT images may be processed using a machine learning (ML) model (e.g., a deep learning model) configured to automatically segment the SD-OCT images and generate segmented images. These segmented images identify one or more retinal fluids, one or more retinal layers, or both at the pixel level. Quantitative retinal feature data may then be extracted from these segmented images. In one or more embodiments, a machine learning model is trained for both segmentation and feature extraction.

[0032] The retinal features may be associated with one or more retinal pathologies (e.g., retinal fluid), one or more retinal layers, or both. Examples of retinal fluid include, but are not limited to, intraretinal fluid (IRF), subretinal fluid (SRF), fluid associated with pigment epithelial detachment (PED), and subretinal hyperreflective material (SHRM). Examples of retinal layers include, but are not limited to, the inner limiting membrane (ILM) layer, the outer plexiform layer-Henle fiber layer (OPL-HFL), the inner limiting retinal pigment epithelial detachment (IB-RPE), the outer limiting retinal pigment epithelial detachment (OB-RPE), and Bruch's membrane (BM).

[0033] The embodiments described herein may use another machine learning model (e.g., a symbolic model) to process the retinal feature data (e.g., some or all of the retinal feature data extracted from the segmented image) to predict the treatment level (e.g., a classification for the treatment level). Different retinal features may have different levels of importance to the predicted treatment level. For example, one or more features associated with PED during the early stage of anti-VEGF treatment (e.g., the second month of anti-VEGF treatment during the 24-month treatment schedule described above) may be strongly associated with a low treatment level during the PRN stage. As another example, one or more features associated with SHRM during the early stage of anti-VEGF treatment (e.g., the first month of anti-VEGF treatment during the 24-month treatment schedule) may be strongly associated with a high treatment level.

[0034] The predicted treatment levels may be used to generate outputs (e.g., reports) that help guide overall treatment management. For example, if the predicted treatment levels are high, the output may identify a strict set of protocols that can be put in place to ensure patient compliance with clinic visits. If the predicted treatment levels are low, the output may identify a more relaxed set of protocols that can be put in place to reduce patient burden. For example, rather than the patient having to travel for monthly clinic visits, the output may identify that the patient can be evaluated in clinic every two or three months.

[0035] Using an automatically segmented image generated by a machine learning model (e.g., a deep learning model) to automatically extract retinal feature data for use in predicting treatment levels via another machine learning model (e.g., a symbolic model) may reduce the overall computing resources and / or time required to predict treatment levels and ensure improved accuracy of predicted treatment levels. Using these methods may improve the efficiency of predicting treatment levels. Furthermore, being able to accurately and efficiently predict treatment levels may aid in overall nAMD treatment management in reducing the overall burden felt by nAMD patients.

[0036] Recognizing and considering the importance and utility of methodologies and systems that can provide the above-mentioned improvements, the embodiments described herein allow for predicting treatment requirements for nAMD with anti-VEGF agent injections. More specifically, the embodiments described herein use SD-OCT and ML-based predictive modeling to predict anti-VEGF treatment requirements for patients with nAMD.

[0037] II. Illustrative Definitions and Context The present disclosure is not limited to these example embodiments and applications or to the manner in which the example embodiments and applications operate or are described herein. Further, the figures may show simplified or partial views, and dimensions of elements in the figures may be exaggerated or out of proportion.

[0038] Additionally, when the terms "on," "attached to," "connected to," "coupled to," or similar terms are used herein, an element (e.g., a component, material, layer, substrate, etc.) can be "on," "attached to," "connected to," or "coupled to" the other element, regardless of whether one element is directly on, directly attached to, connected to, or coupled to the other element, or whether there are one or more intervening elements between the one element and the other element. Additionally, when a list of elements (e.g., elements a, b, c) is referenced, such reference is intended to include any one of the listed elements by itself, any combination of less than all of the listed elements, and / or all combinations of the listed elements. The division of sections herein is merely for ease of review and is not intended to limit any combination of the elements described.

[0039] The term "subject" may refer to a subject of a clinical trial, a person undergoing treatment, a person undergoing anti-cancer treatment, a person being monitored for remission or recovery, a person undergoing preventative health analysis (e.g., due to their medical history), or any other person or subject of interest. In various cases, "subject" and "subject" may be used interchangeably herein. In various cases, a "subject" may also be referred to as a "patient."

[0040] Unless otherwise defined, scientific and technical terms used in connection with the present teachings described herein shall have the meanings commonly understood by those of ordinary skill in the art. Further, unless otherwise required by context, singular terms shall include the plural and plural terms shall include the singular. In general, the nomenclature and techniques utilized in connection with chemistry, biochemistry, molecular biology, pharmacology and toxicology are described herein and are well known and commonly used in the art.

[0041] As used herein, "substantially" means sufficient to function for the intended purpose. Thus, the term "substantially" allows for minor, slight variations from an absolute or perfect state, dimension, measurement, result, etc., that would be expected by one of ordinary skill in the art, but that do not significantly affect overall performance. When used in reference to a numerical value, or a parameter or characteristic that can be expressed as a numerical value, "substantially" means within 10 percent.

[0042] As used herein, the term "about" when used with respect to a numerical value or a parameter or characteristic that can be expressed as a numerical value means within 10% of the numerical value. For example, "about 50" means a value in the range of 45 to 55.

[0043] The term "plurality" means two or more.

[0044] As used herein, the term "plurality" can be 2, 3, 4, 5, 6, 7, 8, 9, 10 or more.

[0045] As used herein, the term "set" means one or more. For example, a set of items includes one or more items.

[0046] As used herein, the phrase "at least one of," when used with a list of items, means that different combinations of one or more of the listed items may be used, or only one of the items in the list may be required. The items may be specific objects, things, steps, operations, processes, or categories. In other words, "at least one of" means that any combination or number of items from the list may be used, but not all of the items in the list are required. For example, but not limited to, "at least one of item A, item B, or item C" means item A, item A and item B, item B, item A, item B, and item C, item B and item C, or item A and C. In some cases, "at least one of item A, item B, or item C" means, but is not limited to, two of item A, one of item B, and ten of item C, four of item B and seven of item C, or some other suitable combination.

[0047] As used herein, a "model" may include one or more algorithms, one or more mathematical techniques, one or more machine learning algorithms, or a combination thereof.

[0048] As used herein, "machine learning" may be the practice of using algorithms to analyze data, learn from it, and then make decisions or predictions about something in the world. Machine learning may use algorithms that can learn from data without relying on rule-based programming.

[0049] As used herein, an "artificial neural network" or "neural network" (NN) may refer to a mathematical algorithm or computational model that mimics an interconnected group of artificial neurons that processes information based on a connectionist approach to computation. A neural network, sometimes called a neural net, may employ one or more layers of linear units, nonlinear units, or both to predict an output for a received input. Some neural networks include one or more hidden layers in addition to an output layer. The output of each hidden layer may be used as an input to the next layer in the network, in other words, the next hidden layer or the output layer. Each layer of the network may generate an output from a received input according to the current value of a corresponding set of parameters. In various embodiments, a reference to a "neural network" may be a reference to one or more neural networks.

[0050] A neural network may process information in two ways. For example, a neural network may process information when it is being trained in a training mode and when it implements what it has learned in an inference (or prediction) mode. A neural network may learn through a feedback process (e.g., backpropagation) that allows the network to adjust the weight coefficients (which modify the network's behavior) of individual nodes in an intermediate hidden layer so that the output matches the output of the training data. In other words, a neural network may learn by being fed training data (training examples) and eventually learn how to arrive at the correct output even when presented with a new range or set of inputs. A neural network may include, for example, but is not limited to, at least one of a feedforward neural network (FNN), a recurrent neural network (RNN), a modular neural network (MNN), a convolutional neural network (CNN), a residual neural network (ResNet), an ordinary differential equation neural network (neural ODE), a squeeze-and-excite embedded neural network, a MobileNet, or another type of neural network.

[0051] As used herein, "deep learning" may refer to the use of multi-layer artificial neural networks to automatically learn representations from input data, such as images, videos, text, etc., without human-provided knowledge, to provide highly accurate predictions in tasks such as object detection / identification, speech recognition, language translation, etc.

[0052] III. Neovascular Age-Related Macular Degeneration (NAMD) Treatment Management III.A. Exemplary Treatment Management System Referring now to the drawings, FIG. 1 is a block diagram of a therapy management system 100 according to one or more embodiments. The therapy management system 100 may be used to manage therapy for a subject diagnosed with neovascular age-related macular degeneration (nAMD). In one or more embodiments, the therapy management system 100 includes a computing platform 102, a data storage 104, and a display system 106. The computing platform 102 may take a variety of forms. In one or more embodiments, the computing platform 102 includes a single computer (or computer system) or multiple computers in communication with each other. In other examples, the computing platform 102 takes the form of a cloud computing platform, a mobile computing platform (e.g., a smartphone, a tablet, etc.), or a combination thereof.

[0053] The data storage 104 and the display system 106 each communicate with the computing platform 102. In some examples, the data storage 104, the display system 106, or both may be considered part of or otherwise integrated with the computing platform 102. Thus, in some examples, the computing platform 102, the data storage 104, and the display system 106 may be separate components that communicate with each other, while in other examples some combination of these components may be integrated.

[0054] III. Ai Prediction Mode The treatment management system 100 includes a treatment level prediction system 108, which may be implemented using hardware, software, firmware, or a combination thereof. In one or more embodiments, the treatment level prediction system 108 is implemented on the computing platform 102. The treatment level prediction system 108 includes a feature extraction module 110 and a prediction module 111. Each of the feature extraction module 110 and the prediction module 111 may be implemented using hardware, software, firmware, or a combination thereof.

[0055] In one or more embodiments, each of the feature extraction module 110 and the prediction module 111 is implemented using one or more machine learning models. For example, the feature extraction module 110 may be implemented using a retinal segmentation model 112, and the prediction module 111 may be implemented using a treatment level classification model 114.

[0056] The retina segmentation model 112 is used to process at least the OCT imaging data 118 and generate a segmented image that identifies one or more retinal pathologies (e.g., retinal fluid), one or more retinal layers, or both. In one or more embodiments, the retina segmentation model 112 takes the form of a machine learning model. For example, the retina segmentation model 112 may be implemented using a deep learning model. The deep learning model may be comprised of, for example, but is not limited to, one or more neural networks.

[0057] In one or more embodiments, the treatment level classification model 114 may be used to classify the treatment level for a treatment. The classification may be, for example, a binary (e.g., high and low; or high and non-high) classification. In other embodiments, some other type of classification may be used (e.g., high, medium, low). In one or more embodiments, the treatment level classification model 114 is implemented using a symbolic model, sometimes also referred to as a feature-based model. The symbolic model may include, for example, but is not limited to, the extreme gradient boosting (XGBoost) algorithm.

[0058] The feature extraction module 110 receives as input subject data 116 for a subject diagnosed with nAMD. The subject may be, for example, a patient who is undergoing, has undergone, or will undergo treatment for nAMD symptoms. The treatment may include, for example, an anti-vascular endothelial growth factor (anti-VEGF) agent, which may be administered via multiple injections (e.g., intravitreal injections).

[0059] The subject data 116 may be received from a remote device (e.g., remote device 117), obtained from a database, or received in some other manner. In one or more embodiments, the subject data 116 is obtained from data storage 104.

[0060] The subject data 116 includes optical coherence tomography (OCT) imaging data 118 of the retina of a subject diagnosed with nAMD. The OCT imaging data 118 may include, for example, spectral domain optical coherence tomography (SD-OCT) imaging data. In one or more embodiments, the OCT imaging data 118 includes one or more SD-OCT images captured at a time point before treatment, immediately before treatment, immediately after the first treatment, another time point, or a combination thereof. In some examples, the OCT imaging data 118 includes one or more images generated during an initial phase of treatment (e.g., a three-month initial phase for months M0-M2). During the initial phase, treatment is administered monthly by injection over a three-month period.

[0061] In one or more embodiments, the subject data 116 further includes clinical data 119. The clinical data 119 may include, for example, data of a set of clinical features. The set of clinical features may include, for example, but is not limited to, best corrected visual acuity (BCVA) (e.g., for a baseline time point before treatment), central subfield thickness (CST) (e.g., extracted from one or more OCT images), pulse, systolic blood pressure (SBP), diastolic blood pressure (DBP), or combinations thereof. This clinical data 119 may have been generated at a baseline time point before treatment and / or at another time point during the treatment phase.

[0062] The feature extraction module 110 uses the OCT imaging data 118 to extract retinal feature data 120 for a plurality of retinal features. The retinal feature data 120 includes values ​​of various features associated with the retina of the subject. For example, the retinal feature data 120 may include values ​​of various features associated with one or more retinal pathologies (e.g., retinal fluid), one or more retinal layers, or both. Examples of retinal fluid include, but are not limited to, intraretinal fluid (IRF), subretinal fluid (SRF), fluid associated with pigment epithelial detachment (PED), and subretinal hyperreflective material (SHRM). Examples of retinal layers include, but are not limited to, the inner limiting membrane (ILM) layer, the outer plexiform layer-Henle fiber layer (OPL-HFL), the inner limiting retinal pigment epithelial detachment (IB-RPE), the outer limiting retinal pigment epithelial detachment (OB-RPE), and Bruch's membrane (BM).

[0063] In one or more embodiments, the feature extraction module 110 inputs at least a portion of the subject data 116 (e.g., OCT imaging data 118) into a retinal segmentation model 112 (e.g., a deep learning model) to identify one or more retinal segments. For example, the retinal segmentation model 112 may generate a segmented image (e.g., a segmented OCT image) that identifies one or more retinal segments by pixel. A retinal segment may be, for example, a retinal lesion (e.g., fluid), a retinal layer boundary, or an identification of a portion of an image as a retinal layer. For example, the retinal segmentation model 112 may generate a segmented image that identifies a set of retinal fluid segments 122, a set of retinal layer segments 124, or both. Each segment of the set of retinal fluid segments 122 corresponds to retinal fluid. Each segment of the set of retinal layers 124 corresponds to a retinal layer.

[0064] In one or more embodiments, the retinal segmentation model 112 is trained to output an image that identifies the set of retinal fluid segments 122 and an image that identifies the set of retinal layer segments 124. The feature extraction module 110 may then identify the retinal feature data 120 using these images that identify the set of retinal fluid segments 122 and the set of retinal layer segments 124. For example, the feature extraction module 110 may perform measurements, calculations, or both using the images to identify the retinal feature data 120. In other embodiments, the retinal segmentation model 112 is trained to output the retinal feature data 120 based on the set of retinal fluid segments 122, the set of retinal layer segments 124, or both.

[0065] The retinal feature data 120 may include, for example, one or more values ​​identified (e.g., calculated, measured, etc.) based on the set of retinal fluid segments 122, the set of retinal layer segments 124, or both. For example, the retinal feature data 120 may include a value of a corresponding retinal fluid segment of the set of retinal fluid segments 122. The value may be for the volume, height, width, or some other measurement of the retinal fluid segment. In one or more embodiments, the retinal feature data 120 includes a value of a corresponding retinal layer segment of the set of retinal layer segments 124. For example, the value may include a minimum thickness, a maximum thickness, an average thickness, or another measurement or calculation value associated with the retinal layer segment. In some cases, the retinal feature data 120 includes a value calculated using multiple fluid segments of the set of retinal fluid segments 122, multiple retinal layer segments of the set of retinal layer segments 124, or both.

[0066] The feature extraction module 110 uses the retinal feature data 120 to generate an output, which forms the input data 126 for the prediction module 111. The input data 126 may be formed in a variety of ways. In one or more embodiments, the input data 126 includes the retinal feature data 120. In other embodiments, some or all of the retinal feature data 120 may be modified, combined, or integrated to form the input data 126. In some examples, two or more values ​​in the retinal feature data 120 may be used to calculate a value included in the input data 126. In one or more embodiments, the input data 126 includes clinical data 119 of a set of clinical features.

[0067] The prediction module 111 predicts the treatment level 130 using the input data 126 received from the feature extraction module 110. The treatment level 130 may be a classification for the number of infusions predicted to be required for the subject. The number of infusions required for the subject may be based on, for example, but not limited to, one or more of the following: The number of infusions required for the subject may be the overall number of infusions or the number of infusions within a selected time period. For example, the treatment for the subject may include an early stage and a pro re nata (PRN) or required stage. The prediction module 111 may be used to predict the treatment level 130 for the PRN stage. In some examples, the time period for the PRN stage includes 21 months after the early stage. In these examples, the treatment level 130 is a classification of "high" or "low", with "high" defined as 16 or more infusions during the PRN stage and "low" defined as 5 or fewer infusions during the PRN stage.

[0068] As described above, treatment level 130 may include a classification for the number of infusions expected for treatment of a subject during the PRN stage, the number of infusions during the PRN stage or another period, the frequency of infusions, another indication of the treatment requirements for the subject, or a combination thereof.

[0069] In one or more embodiments, the prediction module 111 sends the input data 126 to the treatment level classification model 114 to predict the treatment level 130. For example, the treatment level classification model 114 (e.g., an XGBoost algorithm) may be trained to predict the treatment level 130 based on the input data 126.

[0070] In one or more embodiments, the prediction module 111 generates the output 132 using the treatment level 130. In some examples, the output 132 includes the treatment level 130. In other examples, the output 132 includes information generated based on the treatment level 130. For example, if the treatment level 130 identifies a predicted number of infusions for a treatment of a subject during the PRN stage, the output 132 may include a classification for this treatment level. In another example, the treatment level 130 predicted by the treatment level classification model 114 includes the number of infusions and a classification for the number of infusions (e.g., high, low, etc.), and the output 132 includes only the classification. In another example, the output 132 includes a name of the treatment, a dosage of the treatment, or both.

[0071] In one or more embodiments, the output 132 may be transmitted to the remote device 117 via one or more communication links (e.g., wired, wireless, and / or optical communication links). For example, the remote device 117 may be a device or system, such as a server, cloud storage, a cloud computing platform, a mobile device (e.g., a mobile phone, a tablet, a smart watch, etc.), some other type of remote device or system, or a combination thereof. In some embodiments, the output 132 is transmitted as a report that may be viewed on the remote device 138. The report may include, for example, but is not limited to, at least one of a table, a spreadsheet, a database, a file, a presentation, an alert, a graph, a chart, one or more graphics, or a combination thereof.

[0072] In one or more embodiments, the output 132 may be displayed on the display system 106, stored in the data storage 104, or both. The display system 106 includes one or more display devices in communication with the computing platform 102. The display system 106 may be separate from the computing platform 102 or may be at least partially integrated as part of the computing platform.

[0073] The treatment level 130, the output 132, or both may be used to manage treatment of a subject diagnosed with nAMD. A prediction of the treatment level 130 may enable, for example, a clinician.

[0074] III.A.ii. Training Mode 2 is a block diagram of the treatment level prediction system 108 from FIG. 1 used in a training mode in accordance with one or more embodiments. In the training mode, the retina segmentation model 112 of the feature extraction module 110 and the treatment level classification model 114 of the prediction module 111 are trained using training subject data 200. The training subject data 200 may include, for example, training OCT imaging data 202. In some embodiments, training the subject data 200 includes training clinical data 203.

[0075] The training OCT imaging data 202 may include, for example, SD-OCT images capturing the retina of a subject receiving an anti-VEGF injection over an initial phase of treatment (e.g., the first 3 months, the first 5 months, the first 9 months, the first 10 months, etc.), a PRN phase of treatment (e.g., 5 to 25 months after the initial phase), or both. In one or more embodiments, the training OCT imaging data 202 includes a first portion of SD-OCT images for a subject receiving an injection of 0.5 mg of ranibizumab over a 21-month PRN phase and a second portion of SD-OCT images for a subject receiving an injection of 2.0 mg of ranibizumab over a 21-month PRN phase. In other embodiments, OCT images for subjects receiving injections of other dosages (e.g., 0.25 mg to 3 mg) may be included, OCT images for subjects monitored over a longer or shorter PRN phase may be included, OCT images for subjects administered a different anti-VEGF agent may be included, or a combination thereof may be included.

[0076] The training clinical data 203 may include, for example, data of a set of clinical features for a training subject. The set of clinical features may include, but is not limited to, for example, best corrected visual acuity (BCVA) (e.g., for a baseline time point before treatment), central subfield thickness (CST) (e.g., extracted from one or more OCT images), pulse, systolic blood pressure (SBP), diastolic blood pressure (DBP), or combinations thereof. The training clinical data 203 may have been generated at a baseline time point before treatment (e.g., before the initial stage) and / or at another time point during the treatment stage (e.g., between the initial stage and the PRN stage).

[0077] In one or more embodiments, the retina segmentation model 112 may be trained using the training subject data 200 to generate segmented images that identify the set of retinal fluid segments 122, the set of retinal layer segments 124, or both. The set of retinal fluid segments 122 and the set of retinal layer segments 124 may be segmented for each image in the training OCT imaging data 202. The feature extraction module 110 generates the training retinal feature data 204 using the set of retinal fluid segments 122, the set of retinal layer segments 124, or both. In one or more embodiments, the feature extraction module 110 generates the training retinal feature data 204 based on the output of the retina segmentation model 112. In other embodiments, the retina segmentation model 112 of the feature extraction module 110 is trained to generate the training retinal feature data 204 based on the set of retinal fluid segments 122, the set of retinal layer segments 124, or both.

[0078] The feature extraction module 110 generates an output using the training retinal feature data 204 that forms the training input data 206 for input to the prediction module 111. The training input data 206 may include the training retinal feature data 204 or may be generated based on the training retinal feature data 204. For example, the training retinal feature data 204 may be filtered to form the training input data 204. In one or more embodiments, the training retinal feature data 204 is filtered to remove feature data for any subject for which more than 10% of the features of interest are missing data. In some examples, the training retinal feature data 204 is filtered to remove retinal feature data for any subject for which complete data does not exist for the entire early stage, the entire PRN stage, or both the early stage and the PRN stage. In some embodiments, the training input data 206 further includes the training clinical data 203 or at least a portion of the training clinical data 203.

[0079] The prediction module 111 receives training input data 206, and the treatment level classification model 114 may be trained to predict the treatment level 130 using the training input data 206. In one or more embodiments, the treatment level classification model 114 may be trained to predict the treatment level 130 and to predict the output 132 based on the treatment level 130.

[0080] In other embodiments, training of the treatment level prediction system 108 may include only training of the prediction module 111 and thereby only training of the treatment level classification model 114. For example, the retinal segmentation model 112 of the feature extraction module 1110 may be pre-trained to perform segmentation and / or generate feature data. Thus, the training input data 206 may be received from another source (e.g., the data storage of FIG. 1, the remote device 117 of FIG. 1, some other device, etc.).

[0081] III.B. Exemplary Methods of Managing NAMD Treatment 3 is a flowchart of a process 300 for managing therapy for a subject diagnosed with nAMD, according to one or more embodiments. In one or more embodiments, the process 300 is implemented using the therapy management system 100 described in FIG. 1. More specifically, the process 300 may be implemented using the therapy level prediction system 108 of FIG. 1. For example, the process 300 may be used to predict the therapy level 130 based on the subject data 116 (e.g., OCT imaging data 118) of FIG. 1.

[0082] Step 302 includes receiving Spectral Domain Optical Coherence Tomography (SD-OCT) imaging data of a subject's retina. In step 302, the SD-OCT imaging data may be an example of an implementation for the OCT imaging data 118 of FIG. 1. In one or more embodiments, the SD-OCT imaging data may be received from a remote device, retrieved from a database, or received in some other manner. The SD-OCT imaging data received in step 302 may include, for example, one or more SD-OCT images captured at a baseline time point, a time point immediately before treatment, a time point immediately after treatment, another time point, or a combination thereof. In one or more examples, the SD-OCT imaging data includes one or more images generated at any pre-treatment baseline time point (e.g., day 0), a time point before and after the first month of injection (e.g., M1), a time point before and after the second month of injection (e.g., M2), a time point before and after the first and third month of injection (e.g., M3), or a combination thereof.

[0083] Step 304 includes extracting retinal feature data for a plurality of retinal features using the SD-OCT imaging data, the plurality of retinal features being associated with at least one of the set of retinal fluid or the set of retinal layers. In one or more embodiments, step 304 may be implemented using the feature extraction module 110 of FIG. 1. For example, the feature extraction model 110 may be used to extract retinal feature data 120 for a plurality of retinal features associated with at least one of the set of retinal fluid segments 122 or the set of retinal layer segments 124 using the SD-OCT imaging data received in step 302. In step 304, the retinal feature data may take the form of, for example, the retinal feature data 120 of FIG. 1.

[0084] In some examples, the retinal feature data includes values ​​(e.g., calculated values, measured values, etc.) corresponding to one or more retinal fluids, one or more retinal layers, or both. Examples of retinal fluids include, but are not limited to, intraretinal fluid (IRF), subretinal fluid (SRF), fluid associated with pigment epithelial detachment (PED), and subretinal hyperreflective material (SHRM). The feature value associated with the corresponding retinal fluid may include, for example, a volume, height, or width value of the corresponding retinal fluid. Examples of retinal layers include, but are not limited to, the inner limiting membrane (ILM) layer, the outer plexiform layer-Henle fiber layer (OPL-HFL), the inner limiting retinal pigment epithelial detachment (IB-RPE), the outer limiting retinal pigment epithelial detachment (OB-RPE), and Bruch's membrane (BM). The feature value associated with the corresponding retinal layer may include, for example, a minimum thickness, maximum thickness, or average thickness value of the corresponding retinal layer. In some cases, the retinal layer-related feature may correspond to two or more retinal layers (e.g., the distance between the boundaries of two retinal layers).

[0085] In one or more embodiments, the plurality of retinal features in step 304 includes at least one feature associated with subretinal fluid (SRF) of the retina and at least one feature associated with pigment epithelial detachment (PED).

[0086] In one or more embodiments, the SD-OCT imaging data includes SD-OCT images captured during a single clinical visit. In some embodiments, the SD-OCT imaging data includes SD-OCT images captured at multiple clinical visits (e.g., every month during the initial phase of treatment). In one or more embodiments, step 304 includes extracting retinal feature data using the SD-OCT imaging data via a machine learning model (e.g., retinal segmentation model 112 of FIG. 1). The machine learning model may include, for example, a deep learning model. In one or more embodiments, the deep learning model includes one or more neural networks, each of which may be, for example, a convolutional neural network (CNN).

[0087] Step 306 includes sending input data formed using retinal feature data of the plurality of retinal features to the machine learning model. In step 306, the input data may take the form of, for example, input data 126 of FIG. 1. In some embodiments, the input data includes the retinal feature data extracted in step 304. In other words, the retinal feature data or at least a portion of the retinal feature data may be sent as input data for the machine learning model. In other embodiments, some or all of the retinal feature data may be modified, combined, or integrated to form the input data. The machine learning model in step 306 may be, for example, the treatment level classification model 114 of FIG. 1. In one or more embodiments, the machine learning model may be a symbolic model (feature-based model) (e.g., a model using the XGBoost algorithm).

[0088] In some embodiments, the input data may further include clinical data of a set of clinical features for the subject. The clinical data may be, for example, the clinical data 117 of FIG. 1. The set of clinical features may include, for example, but is not limited to, best corrected visual acuity (BCVA) (e.g., for a baseline time point before treatment), central subfield thickness (CST) (e.g., extracted from one or more OCT images), pulse, systolic blood pressure (SBP), diastolic blood pressure (DBP), or combinations thereof. The input data may include all or a portion of the retinal feature data described above.

[0089] Step 308 includes predicting, via the machine learning model, a treatment level for an anti-vascular endothelial growth factor (anti-VEGF) treatment to be administered to the subject based on the input data. The treatment level may include a classification for a predicted number of injections (e.g., during the PRN phase of treatment) for the subject's anti-VEGF treatment, a number of injections (e.g., during the PRN phase or another time period), an injection frequency, another indicator of the treatment requirements for the subject, or a combination thereof.

[0090] Process 300 may optionally include step 310. Step 310 includes generating an output using the predicted treatment levels. The output may include information generated based on the treatment levels and / or the predicted treatment levels. In some embodiments, step 310 further includes transmitting the output to a remote device. The output may be, for example, a report that may be used to guide a clinician, a subject, or both regarding the subject's treatment. For example, if the predicted treatment levels indicate that the subject may require a "high" level of infusion over the PRN phase, the output may identify a particular protocol that can be set to help ensure subject compliance (e.g., subject indicating to infusion appointment, evaluation appointment).

[0091] 4 is a flowchart of a process 400 for managing treatment for a subject diagnosed with nAMD, according to one or more embodiments. In one or more embodiments, the process 400 is implemented using the treatment management system 100 described in FIG 1. More specifically, the process 400 may be implemented using the treatment level prediction system 108 of FIGS. 1 and 2.

[0092] Step 402 includes training a first machine learning model using training input data to predict a treatment level for the anti-VEGF treatment. The training input data may be, for example, training input data 206 of FIG. 2. The training input data may be formed using training OCT imaging data, such as, for example, training OCT imaging data 202 of FIG. 2. The first machine learning model may include, for example, a symbolic model, such as, for example, an XGBoost model.

[0093] In one or more embodiments, the training OCT imaging data is automatically segmented using a second machine learning model to generate a segmented image (segmented OCT image). The second machine learning model may include, for example, a deep learning model. Retinal feature data is extracted from the segmented image and used to form training input data. For example, at least a portion of the retinal feature data is used to form at least a portion of the training input data. In some examples, the training input data may further include training clinical data (e.g., measurements for BCVA, pulse, systolic blood pressure, diastolic blood pressure, CST, etc.).

[0094] The training input data may include data of a first portion of training subjects treated with a first dose of anti-VEGF therapy (e.g., 0.5 mg) and data of a second portion of training subjects treated with a second dose of anti-VEGF therapy (e.g., 2.0 mg). The training input data may be data corresponding to a pro re nata phase of treatment (e.g., after 21 months of an initial phase of treatment involving monthly injections, after 9 months of an initial phase of treatment, or some other period of time).

[0095] In one or more embodiments, the retinal feature data may be pre-processed to form the training input data. For example, values ​​for retinal features corresponding to multiple visits (e.g., three visits) may be concatenated. In some examples, highly correlated features may be excluded from the training input data. For example, in step 402, clusters of highly correlated features (e.g., correlation coefficients greater than 0.9) may be identified. For each pair of highly correlated features, a value for one of these features may be randomly selected for exclusion from the training input data. In the case of a cluster of three or more highly correlated features, values ​​for those features that are most correlated with other features in the cluster are iteratively excluded (e.g., until a single feature of the cluster remains). These pre-processing examples may be just one example of the type of pre-processing that may be performed on the retinal feature data.

[0096] In still other embodiments, step 402 includes training a first machine learning model on the first plurality of retinal features. A feature importance analysis may be used to determine which of the first plurality of retinal features are most important in predicting the treatment level. In these embodiments, step 402 may include reducing the first plurality of retinal features to a second plurality of retinal features (e.g., 3, 4, 5, 6, 7, .... 10, or some other retinal features). The first machine learning model may then be trained to use the second plurality of retinal features in predicting the treatment level.

[0097] Step 404 includes generating input data for the subject using a second machine learning model. The input data for the subject may be generated using retinal feature data extracted from OCT imaging data of the subject's retina using the second machine learning model, clinical data, or both. For example, the second machine learning model may be pre-trained to identify a set of retinal fluid segments, a set of retinal layer segments, or both in the OCT image. The set of retinal fluid segments, the set of retinal layer segments, or both may then be used to identify retinal feature data for a plurality of retinal features via calculation, measurement, etc. In some embodiments, the second machine learning model may be pre-trained to identify retinal feature data based on the set of retinal fluid segments, the set of retinal layer segments, or both.

[0098] Step 406 includes receiving input data including retinal feature data for a plurality of retinal features by the trained machine learning model. The input data may further include clinical data for a set of clinical features.

[0099] Step 408 includes predicting, via the trained machine learning model, a therapeutic level for the anti-VEGF therapy to be administered to the subject using the input data. The therapeutic level can be, for example, a classification of "high" or "low" (or "high" and "non-high"). A "high" level can, for example, indicate 10, 11, 12, 13, 14, 15, 16, 17, or 18 or more infusions during the PRN stage (e.g., 8, 9, ...). A "low" level can, for example, indicate 7, 6, 5, 4, or fewer infusions during the PRN stage.

[0100] 5 is a flowchart of a process 500 for managing a treatment for a subject diagnosed with nAMD, according to one or more embodiments. The process 500 may be implemented, for example, using the treatment management system 100 of FIG.

[0101] Step 502 may include receiving subject data for a subject diagnosed with nAMD, the subject data including OCT imaging data. The OCT imaging data may be, for example, SD-OCT imaging data. The OCT imaging data may include one or more OCT (e.g., SD-OCT) images of the subject's retina. In one or more embodiments, the subject data further includes clinical data. The clinical data may include, for example, a BCVA measurement (e.g., obtained at a baseline time point) and vitals (e.g., pulse, systolic blood pressure, diastolic blood pressure, etc.). In some embodiments, the clinical data includes a central subfield thickness (CST), which may be a measurement extracted from one or more OCT images.

[0102] Step 504 includes extracting retinal feature data from the OCT imaging data using a deep learning model. In one or more embodiments, a deep learning model is used to segment a set of fluid segments and a set of retinal layer segments from the OCT imaging data. For example, a deep learning model may be used to segment a set of fluid segments and a set of retinal layer segments from each OCT image of the OCT imaging data to generate segmented images. These segmented images may be used to measure and / or calculate values ​​of a plurality of retinal features to form the retinal feature data. In other embodiments, a deep learning model may be used to both perform the segmentation and generate the retinal feature data.

[0103] Step 506 includes using the retinal feature data to form input data for the symbol model. The input data may include, for example, the retinal feature data. In other embodiments, the input data may be formed by modifying, integrating, or combining at least a portion of the retinal feature data to form new values. In yet other embodiments, the input data may further include clinical data as described above.

[0104] Step 508 involves predicting the therapeutic level via a symbolic model using the input data. In one or more embodiments, the therapeutic level may be a classification of "high" or "low" (or "high" and "non-high"). A "high" level may indicate, for example, 10, 11, 12, 13, 14, 15, 16, 17, or 18 or more infusions during the PRN stage (e.g., 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 10, 20, 21, 22, 23, 24 months, or some other period of months). A "low" level may indicate, for example, 7, 6, 5, 4, or fewer infusions during the PRN stage. A "non-high" level may indicate a number of infusions below the number required for the "high" classification.

[0105] Process 500 may optionally include step 510. Step 510 includes generating an output using the predicted treatment level for use in guiding management of the subject's treatment. For example, the output may be a report, an alert, a notification, or other type of output including the treatment level. In some examples, the output includes a set of protocols based on the predicted treatment level. For example, if the predicted treatment level is "high", the output may outline a set of protocols that may be used to ensure the subject's compliance with assessment appointments, infusion appointments, etc. In some embodiments, the output may include specific information when the predicted treatment level is "high", such as specific instructions for the subject or a clinician treating the subject, which information is excluded from the output when the predicted treatment level is "low" or "not high". Thus, the output may take a variety of forms depending on the predicted treatment level.

[0106] III.C. Exemplary Segmented Images 6 is an illustration of a segmented OCT image in accordance with one or more embodiments. The segmented OCT image 600 may have been generated using, for example, the retinal segmentation model 112 of FIG. 1. The segmented OCT image 600 identifies a set of retinal fluid segments 122, which may be one example of an implementation of the set of retinal fluid segments 602 of FIG. 1. The set of retinal fluid segments 602 identifies intraretinal fluid (IRF), subretinal fluid (SRF), fluid associated with pigment epithelial detachment (PED), and subretinal hyperreflective material (SHRM).

[0107] 7 is an illustration of a segmented OCT image in accordance with one or more embodiments. The segmented OCT image 700 may have been generated using, for example, the retinal segmentation model 112 of FIG. 1. The segmented OCT image 700 identifies a set of retinal layer segments 124, which may be an example of an implementation of the set of retinal layer segments 702 of FIG. 1. The set of retinal layer segments 702 identifies the inner limiting membrane (ILM) layer, the outer plexiform layer-Henle fiber layer (OPL-HFL), the inner border retinal pigment epithelium detachment (IB-RPE), the outer border retinal pigment epithelium detachment (OB-RPE), and Bruch's membrane (BM).

[0108] IV. Exemplary Experimental Data IV.A. Test #1: In the first study, a machine learning model (e.g., a symbolic model) was trained using training input data generated from training OCT imaging data. For example, SD-OCT imaging data for 363 training subjects of the HARBOR clinical trial (NCT00891735) from two different ranibizumab PRN arms (one with a 0.5 mg dose and one with a 2.0 mg dose) was collected. The SD-OCT imaging data included monthly SD-OCT images for the 3-month initial phase of treatment and the 21-month PRN phase of treatment, when applicable. A "low" treatment level was classified as 5 or fewer injections during the PRN phase. A "high" treatment level was classified as 16 or more injections during the PRN phase.

[0109] A deep learning model was used to generate segmented images for each month of the early stage (e.g., identifying a set of fluid segments and a set of retinal layer segments in each SD-OCT image). Thus, three fluid segmented images and three layer segmented images were generated (one for each visit). Using these segmented images, training retinal feature data was calculated for each training subject case. The training retinal feature data included data for 60 features calculated using the fluid segmented images and 45 features calculated using the layer segmented images. Training retinal feature data was calculated for each of the three months of the early stage. The training retinal feature data was combined with the BCVA and CST data for each of the three months of the early stage to form training input data. The training input data was filtered to remove any subject case with missing data for more than 10% of all 105 retinal features and to remove any subject case for which complete data was not available for all 24 months of both the early stage and the PRN stage.

[0110] The filtered training input data was then input to a symbolic model implemented using the XGBoost algorithm and evaluated using 5-fold cross-validation. The symbolic model was trained using the training input data to classify a given subject as associated with a "low" or "high" treatment level.

[0111] 8 is a plot showing the results of a 5-fold cross-validation for a "low" treatment level classification in accordance with one or more embodiments. In particular, plot 800 provides validation data for the above-described experiment for subject cases classified by a "low" treatment level. The average AUC for the "low" treatment level was 0.81±0.06.

[0112] 9 is a plot showing the results of a 5-fold cross-validation for a "high" treatment level classification in accordance with one or more embodiments. In particular, plot 900 provides validation data for the above-described experiment for subject cases classified by "high" treatment level. The average AUC for the "high" treatment level was 0.80±0.08.

[0113] Plot 800 in FIG. 8 and plot 900 in FIG. 9 show the feasibility of predicting low or high treatment levels for subjects with nAMD using retinal feature data extracted from automatically segmented SD-OCT images using a machine learning model (e.g., a symbolic model), where the segmented SD-OCT images are generated using another machine learning model (e.g., a deep learning model).

[0114] A Shapley Additive exPlanations (SHAP) analysis was performed to determine the features most associated with the "low" and "high" treatment level classifications. For the "low" treatment level classification, the six most important features included four features associated with retinal fluid (e.g., PED and SHRM), one feature associated with retinal layers, and CST, with five of these six features from the second month of the initial phase of treatment. The "low" treatment level classification was most strongly associated with the low volume of PED height detected at the second month. For the "high" treatment level classification, the six most important features included four features associated with retinal fluid (e.g., IRF and SHRM) and two features associated with retinal layers, with four of these six features from the second month of the initial phase of treatment. The "high" treatment level classification was most strongly associated with the low volume of SHRM detected at the first month.

[0115] IV.B. Test #2: In the second study, a machine learning model (e.g., a symbolic model) was trained using training input data generated from the training OCT imaging data. For example, SD-OCT imaging data for 547 training subjects of the HARBOR clinical trial (NCT00891735) from two different ranibizumab PRN arms (one with a 0.5 mg dose and one with a 2.0 mg dose) was collected. The SD-OCT imaging data included monthly SD-OCT images for the 9-month initial phase of treatment and the 9-month PRN phase of treatment, where applicable. Of the 547 training subjects, 144 were identified as having “high” treatment levels, which were classified as 6 or more infusions during the PRN phase (9 visits between 9 and 17 months).

[0116] A deep learning model was used to generate fluid and layer segmented images from SD-OCT imaging data collected at the 9th and 10th month visits. These segmented images were used to calculate training retinal feature data for each training case. For each of the 9th and 10th month visits, the training retinal feature data included 69 features for retinal layers and 36 features for retinal fluid.

[0117] This training retinal feature data was filtered to remove subject cases with missing data for more than 10% of the retinal features (e.g., failed segmentation) and to remove subject cases for which complete data was not available for the entire 9 months from months 9 to 17, thereby forming the input data.

[0118] This input data was fed into a symbolic model for binary classification using the XGBoost algorithm, with 10 repeated 5-fold cross-validation. Tests were performed for each feature set (retinal fluid-related features and retinal layer-related features) as well as for the combined set of all retinal features. Further tests were performed using only 9-month features, and both 9-month and 10-month features together.

[0119] FIG. 10 is a plot of AUC data showing the results of repeated 5-fold cross-validation for the “high” treatment level classification, according to one or more embodiments. As shown in plot 1000, the best performance was achieved using features from all retinal layers. The AUC for using only retinal layer-related features was 0.76±0.04 when using only 9-month data, and 0.79±0.05 when using 9-month and 10-month data together. These AUCs are close to the performance observed when using both retinal layer-related and retinal fluid-related features. The addition of 10-month data slightly improved the performance, as shown in plot 1000. The SHAP analysis confirmed that features associated with SRF and PED were among the most important features for predicting treatment level.

[0120] Thus, this study demonstrated the feasibility of using retinal feature data extracted from automatically segmented SD-OCT images to identify future high treatment levels (e.g., 6 or more injections within a 9-month period following a 9-month period of initial treatment) for previously treated nAMD subjects.

[0121] V. Computer Implemented Systems FIG. 11 is a block diagram illustrating an example of a computer system according to one or more embodiments. The computer system 1100 may be an example of one implementation of the computing platform 102 described above in FIG. 1. In one or more examples, the computer system 1100 may include a bus 1102 or other communication mechanism for communicating information and a processor 1104 coupled with the bus 1102 for processing information. In various embodiments, the computer system 1100 may also include a memory, which may be a random access memory (RAM) 1106 or other dynamic storage device, coupled to the bus 1102 for determining instructions to be executed by the processor 1104. The memory may also be used to store temporary variables or other intermediate information during execution of instructions to be executed by the processor 1104. In various embodiments, the computer system 1100 may further include a read-only memory (ROM) 1108 or other static storage device coupled to the bus 1102 for storing static information and instructions for the processor 1104. A storage device 1110, such as a magnetic disk or optical disk, may be provided and coupled to the bus 1102 for storing information and instructions.

[0122] In various embodiments, the computer system 1100 may be coupled via the bus 1102 to a display 1112, such as a cathode ray tube (CRT) or liquid crystal display (LCD), for displaying information to a computer user. An input device 1114, including alphanumeric and other keys, may be coupled to the bus 1102 for communicating information and command selections to the processor 1104. Another type of user input device is a cursor control device 1116, such as a mouse, joystick, trackball, gesture input device, gaze-based input device, or cursor direction keys, for communicating directional information and command selections to the processor 1104 and controlling cursor movement on the display 1112. This input device 1114 typically has two degrees of freedom in two axes, a first axis (e.g., x) and a second axis (e.g., y), that allow the device to specify a position in a plane. However, it should be understood that input devices 1114 that allow three-dimensional (e.g., x, y, and z) cursor movement are also contemplated herein.

[0123] Consistent with a particular implementation of the present teachings, results may be provided by the computer system 1100 in response to the processor 1104 executing one or more sequences of one or more instructions contained in the RAM 1106. Such instructions may be read into the RAM 1106 from another computer-readable medium or computer-readable storage medium, such as the storage device 1110. Execution of the sequences of instructions contained in the RAM 1106 may cause the processor 1104 to perform the processes described herein. Alternatively, hardwired circuitry may be used in place of or in combination with software instructions to implement the present teachings. Thus, implementation of the present teachings is not limited to any specific combination of hardware circuitry and software.

[0124] As used herein, the terms "computer-readable medium" (e.g., data store, storage device, data storage device, etc.) or "computer-readable storage medium" refer to any medium that participates in providing instructions to the processor 1104 for execution. Such media may take many forms, including but not limited to, non-volatile media, volatile media, and transmission media. Examples of non-volatile media may include, but are not limited to, optical, solid-state, and magnetic disks, such as the storage device 1110. Examples of volatile media may include, but are not limited to, dynamic memory, such as the RAM 1106. Examples of transmission media may include, but are not limited to, coaxial cables, copper wire, and fiber optics, including the wires that comprise the bus 1102.

[0125] Common forms of computer readable media include, for example, a floppy disk, a flexible disk, a hard disk, a magnetic tape or any other magnetic medium, a CD-ROM, any other optical medium, punch cards, paper tape, any other physical medium with a pattern of holes, RAM, PROM, and EPROM, flash EPROM, any other memory chip or cartridge, or any other tangible medium from which a computer can read.

[0126] In addition to computer-readable media, instructions or data may be provided as signals on a transmission medium included in a communication device or system to provide a sequence of one or more instructions to the processor 1104 of the computer system 1100 for execution. For example, a communication device may include a transceiver having signals indicative of instructions and data. The instructions and data are configured to cause one or more processors to implement the functions outlined in the disclosure herein. Representative examples of data communication transmission connections include, but are not limited to, a telephone modem connection, a wide area network (WAN), a local area network (LAN), an infrared data connection, an NFC connection, an optical communication connection, and the like.

[0127] It should be understood that the methodologies, flowcharts, diagrams, and accompanying disclosure described herein may be implemented using computer system 1100 as a stand-alone device or on a distributed network of shared computer processing resources, such as a cloud computing network.

[0128] The methodologies described herein may be implemented by various means depending on the application. For example, these methodologies may be implemented in hardware, firmware, software, or any combination thereof. In the case of a hardware implementation, the processing unit may be implemented in one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processors (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, electronic devices, other electronic units designed to perform the functions described herein, or combinations thereof.

[0129] In various embodiments, the methods of the present teachings may be implemented as firmware and / or software programs and applications written in conventional programming languages ​​such as C, C++, Python, etc. When implemented as firmware and / or software, the embodiments described herein may be implemented on a non-transitory computer-readable medium having a program stored thereon for causing a computer to execute the above-described methods. It should be understood that the various engines described herein may be provided in a computer system, such as computer system 1100, whereby processor 1104 receives instructions provided by any one or combination of memory components RAM 1106, ROM 1108, or storage device 1110, and user input provided via input device 1114 to perform the analysis and decisions provided by these engines.

[0130] VI. Description of the Preferred Embodiments Embodiment 1. A method for managing therapy for a subject diagnosed with neovascular age-related macular degeneration (nAMD), comprising: receiving spectral domain optical coherence tomography (SD-OCT) imaging data of the subject's retina; extracting retinal feature data for a plurality of retinal features using the SD-OCT imaging data, the plurality of retinal features being associated with at least one of a set of retinal fluid or a set of retinal layers; sending input data formed using the retinal feature data for the plurality of retinal features to a first machine learning model; and predicting, via the first machine learning model, a treatment level for an anti-vascular endothelial growth factor (anti-VEGF) treatment to be administered to the subject based on the input data.

[0131] Embodiment 2. The method of embodiment 1, wherein the retinal characteristic data includes a value associated with a corresponding retinal fluid of the set of retinal fluids, the value being selected from the group consisting of a volume, a height, and a width of the corresponding retinal fluid.

[0132] Embodiment 3. The method of embodiment 1 or 2, wherein the retinal characteristic data includes values ​​for corresponding retinal layers of the set of retinal layers, the values ​​being selected from the group consisting of a minimum thickness, a maximum thickness, and an average thickness of the corresponding retinal layer.

[0133] Embodiment 4. The method of any one of embodiments 1-3, wherein the retinal fluid of the set of retinal fluids is selected from the group consisting of intraretinal fluid (IRF), subretinal fluid (SRF), fluid associated with pigment epithelial detachment (PED), or subretinal hyperreflective material (SHRM).

[0134] Embodiment 5. The method of any one of embodiments 1-4, wherein the retinal layer of the set of retinal layers is selected from the group consisting of an inner limiting membrane (ILM) layer, an outer plexiform layer-Henle fiber layer (OPL-HFL), an inner limiting retinal pigment epithelium detachment (IB-RPE), an outer limiting retinal pigment epithelium detachment (OB-RPE), or a Bruch's membrane (BM).

[0135] Embodiment 6. The method of any one of embodiments 1 to 5, further comprising forming input data using retinal feature data for a plurality of retinal features and clinical data for a set of clinical features, the set of clinical features including at least one of best corrected visual acuity, pulse, diastolic blood pressure, or systolic blood pressure.

[0136] Embodiment 7. The method of any one of embodiments 1 to 6, wherein predicting the therapeutic level comprises predicting a classification for the therapeutic level as either a high therapeutic level or a low therapeutic level.

[0137] Embodiment 8. The method of embodiment 7, wherein the high therapeutic level refers to 16 or more infusions of anti-VEGF therapy during a selected period of time after an initial phase of treatment.

[0138] Embodiment 9. The method of embodiment 7, wherein the low therapeutic level refers to five or fewer infusions of anti-VEGF therapy during a selected period of time after an initial phase of treatment.

[0139] Embodiment 10. The method of any one of embodiments 1 to 9, wherein the extracting includes extracting retinal feature data for a plurality of retinal features from a segmented image generated using a second machine learning model that automatically segments the SD-OCT imaging data, wherein the plurality of retinal features are associated with at least one of a set of retinal fluid segments or a set of retinal layer segments identified in the segmented image.

[0140]

[0026] Embodiment 11. The method of embodiment 10, wherein the second machine learning model comprises a deep learning model.

[0141] Embodiment 12. The method of any one of embodiments 1 to 11, wherein the first machine learning model comprises an extreme gradient boosting (XGBoost) algorithm.

[0142] Embodiment 13. The method of any one of embodiments 1 to 12, wherein the plurality of retinal features includes at least one feature associated with subretinal fluid (SRF) and at least one feature associated with pigment epithelial detachment (PED).

[0143] Embodiment 14. The method of any one of embodiments 1 to 13, wherein the SD-OCT imaging data comprises SD-OCT images captured during a single clinical visit.

[0144] Embodiment 15. A method for managing anti-vascular endothelial growth factor (anti-VEGF) therapy for a subject diagnosed with neovascular age-related macular degeneration (nAMD), comprising: training a machine learning model using training input data to predict a treatment level for the anti-VEGF therapy, where the training input data is formed using training optical coherence tomography (OCT) imaging data; receiving input data for the trained machine learning model, where the input data includes retinal feature data for a plurality of retinal features; and predicting, via the trained machine learning model, a treatment level for the anti-VEGF therapy to be administered to the subject using the input data.

[0145] Embodiment 16. The method of embodiment 15, further comprising generating input data using training OCT imaging data and a deep learning model, wherein the deep learning model is used to automatically segment the training OCT imaging data to form a segmented image, and retinal feature data is extracted from the segmented image.

[0146] Embodiment 17. The method of embodiment 15 or 16, wherein the machine learning model is trained to predict a classification for the treatment level as either a high treatment level or a low treatment level, with a high treatment level indicating 16 or more infusions of anti-VEGF treatment during a selected period of time after an initial phase of treatment.

[0147] Embodiment 18. The method of embodiment 15 or 16, wherein the machine learning model is trained to predict a classification for the therapeutic level as either a high therapeutic level or a non-high therapeutic level, with a high therapeutic level indicating 6 or more infusions of anti-VEGF therapy during a selected period of time after an initial phase of treatment.

[0148] Embodiment 19. A system for administering anti-vascular endothelial growth factor (anti-VEGF) therapy to a subject diagnosed with neovascular age-related macular degeneration (nAMD), comprising: a memory including a machine-readable medium containing machine-executable code; a processor coupled to the memory for executing machine executable code to cause the processor to: receiving spectral domain optical coherence tomography (SD-OCT) imaging data of a subject's retina; extracting retinal feature data for a plurality of retinal features using the SD-OCT imaging data, the plurality of retinal features being associated with at least one of a set of retinal fluid or a set of retinal layers; Sending input data formed using retinal feature data for a plurality of retinal features to a first machine learning model; and a processor configured to cause the system to predict, via a first machine learning model, a treatment level for an anti-vascular endothelial growth factor (anti-VEGF) treatment to be administered to a subject based on input data.

[0149] Embodiment 20. The system of embodiment 19, wherein the machine executable code further causes the processor to extract retinal feature data for a plurality of retinal features from a segmented image generated using a second machine learning model that automatically segments the SD-OCT imaging data, and the plurality of retinal features are associated with at least one of a set of retinal fluid segments or a set of retinal layer segments identified in the segmented image.

[0150] VII. Further Considerations Headings and subheadings among the sections and subsections of this document are included merely to improve readability and do not imply that features cannot be combined across the sections and subsections, and thus the sections and subsections do not describe separate embodiments.

[0151] Some embodiments of the present disclosure include a system including one or more data processors. In some embodiments, the system includes a non-transitory computer-readable storage medium including instructions that, when executed on the one or more data processors, cause the one or more data processors to perform some or all of the methods and / or some or all of the processes disclosed herein. Some embodiments of the present disclosure include a computer program product tangibly embodied in a non-transitory machine-readable storage medium including instructions configured to cause the one or more data processors to perform some or all of the methods and / or some or all of the processes disclosed herein.

[0152] The terms and expressions used are used as terms of description and not of limitation, and in the use of such terms and expressions there is no intention to exclude equivalents of the features shown and described or portions thereof, but it is recognized that various modifications are possible within the scope of the invention as claimed. Thus, although the invention as claimed has been specifically disclosed by embodiments and optional features, it will be understood that modifications and variations of the concepts disclosed herein may be resorted to by those skilled in the art, and such modifications and variations are considered to be within the scope of the invention as defined by the appended claims.

[0153] The description provides only preferred exemplary embodiments and is not intended to limit the scope, applicability or configuration of the present disclosure. Rather, the description of the exemplary embodiments provides those skilled in the art with an effective description for implementing various embodiments. It is understood that various changes may be made in the function and arrangement of elements (e.g., elements of block or schematic diagrams, elements of flow diagrams, etc.) without departing from the spirit and scope of the appended claims.

[0154] Specific details are given in the following description to provide a thorough understanding of the embodiments. However, it will be understood that the embodiments may be practiced without these specific details. For example, circuits, systems, networks, processes, and other components may be shown as components in block diagram form in order to avoid obscuring the embodiments in unnecessary detail. In other examples, well-known circuits, processes, algorithms, structures, and techniques may be shown without unnecessary detail in order to avoid obscuring the embodiments.

Claims

1. 1. A method for predicting a treatment level for a subject diagnosed with neovascular age-related macular degeneration (nAMD), comprising: receiving spectral domain optical coherence tomography (SD-OCT) imaging data of the subject's retina; extracting retinal feature data for a plurality of retinal features using the SD-OCT imaging data, the plurality of retinal features including one or more retinal features associated with a set of retinal fluids, including retinal fluid associated with pigment epithelial detachment (PED), and one or more retinal features associated with a set of retinal layers; sending input data formed using the retinal feature data for the plurality of retinal features to a first machine learning model; predicting, via the first machine learning model, a therapeutic level for an anti-vascular endothelial growth factor (anti-VEGF) treatment to be administered to the subject based on the input data; A method comprising:

2. 2. The method of claim 1, wherein the retinal characteristic data includes a value associated with a corresponding retinal fluid of the set of retinal fluids, the value being selected from the group consisting of a volume, a height, and a width of the corresponding retinal fluid.

3. 3. The method of claim 1 or 2, wherein the retinal characteristic data includes values ​​for corresponding retinal layers of the set of retinal layers, the values ​​being selected from the group consisting of a minimum thickness, a maximum thickness, and an average thickness of the corresponding retinal layer.

4. 3. The method of claim 1 or 2, wherein the set of retinal fluids further comprises one or more of intraretinal fluid (IRF), subretinal fluid (SRF), and subretinal hyperreflective material (SHRM).

5. The method of claim 4, wherein the plurality of retinal features includes at least one feature associated with subretinal fluid (SRF).

6. 3. The method of claim 1 or 2, wherein a retinal layer of the set of retinal layers is selected from the group consisting of an inner limiting membrane (ILM) layer, an outer plexiform layer-Henle fiber layer (OPL-HFL), an inner border retinal pigment epithelium detachment (IB-RPE), an outer border retinal pigment epithelium detachment (OB-RPE), or a Bruch's membrane (BM).

7. 3. The method of claim 1 or 2, further comprising forming the input data using the retinal feature data for the plurality of retinal features and clinical data for a set of clinical features, the set of clinical features including at least one of best corrected visual acuity, central subfield thickness, pulse, diastolic blood pressure, or systolic blood pressure.

8. 3. The method of claim 1 or 2, wherein predicting the therapeutic level comprises predicting a classification for the therapeutic level as either a high therapeutic level or a low therapeutic level.

9. the high therapeutic level represents 16 or more infusions of the anti-VEGF therapy during a selected period of time following an initial phase of treatment; and / or 9. The method of claim 8, wherein the low therapeutic level refers to five or fewer infusions of the anti-VEGF therapy during a selected period of time after an initial stage of treatment.

10. The extracting step comprises:

3. The method of claim 1 or 2, comprising extracting retinal feature data for the plurality of retinal features from a segmented image generated using a second machine learning model that automatically segments the SD-OCT imaging data, wherein the plurality of retinal features is associated with at least one of a set of retinal fluid segments or a set of retinal layer segments identified in the segmented image.

11. The method of claim 10 , wherein the second machine learning model comprises a deep learning model.

12. The method of claim 1 or 2, wherein the first machine learning model comprises an Extreme Gradient Boosting (XGBoost) algorithm.

13. The method of claim 1 or 2, wherein the SD-OCT imaging data comprises SD-OCT images captured during a single clinical visit.

14. The method of claim 1 or 2, further comprising training a machine learning model using training input data to predict a treatment level for the anti-VEGF treatment, wherein the training input data is formed using training optical coherence tomography (OCT) imaging data.

15. 15. The method of claim 14, further comprising generating the input data using the training OCT imaging data and a deep learning model, wherein the deep learning model is used to automatically segment the training OCT imaging data to form a segmented image, and the retinal feature data is extracted from the segmented image.

16. 15. The method of claim 14, wherein the machine learning model is trained to predict a classification for the treatment level as either a high treatment level or a low treatment level, the high treatment level indicating 16 or more or 6 or more infusions of the anti-VEGF treatment during a selected period of time after an initial phase of treatment.

17. 1. A system for predicting a therapeutic level of anti-vascular endothelial growth factor (anti-VEGF) treatment for a subject diagnosed with neovascular age-related macular degeneration (nAMD), comprising: a memory including a machine-readable medium containing machine-executable code; a processor coupled to the memory, receiving spectral domain optical coherence tomography (SD-OCT) imaging data of the subject's retina; extracting retinal feature data for a plurality of retinal features using the SD-OCT imaging data, the plurality of retinal features including one or more retinal features associated with a set of retinal fluids, including retinal fluid associated with pigment epithelial detachment (PED), and one or more retinal features associated with a set of retinal layers; sending input data formed using the retinal feature data for the plurality of retinal features to a first machine learning model; predicting, via the first machine learning model, a therapeutic level for an anti-vascular endothelial growth factor (anti-VEGF) treatment to be administered to the subject based on the input data; a processor configured to execute the machine-executable code to cause the processor to:

Images