System and method for determining risk of deciduous tooth retention

Abstract

Various embodiments of the present disclosure are generally directed to predicting a level of risk for the presence of deciduous tooth retention (PDT) in one or more pets. The method includes: receiving, by one or more processors, pet data corresponding to a pet from a user device, the pet data including one or more pet attributes; determining, by the one or more processors, a result value indicative of a PDT attribute weight for each of the one or more pet attributes based on the one or more pet attributes; analyzing, by the one or more processors, a resultant value for each of the one or more pet attributes to determine a PDT risk level, the analyzing including utilizing a PDT risk level prediction algorithm; and displaying, by the one or more processors, the PDT risk level on one or more user interfaces of the user device.

Description

[0001] Cross Reference to Related Applications

[0002] This application claims priority to U.S. Application No. 18 / 467,939, filed September 15, 2023, the entirety of which is incorporated by reference herein. TECHNICAL FIELD

[0003] Various embodiments of the present disclosure generally relate to systems and methods for analyzing pet data to determine a pet’s Persistent Deciduous Teeth (PDT) risk. BACKGROUND

[0004] Persistent Deciduous Teeth (PDT), i.e., deciduous teeth that fail to exfoliate at the appropriate time, is a common problem in puppy dentistry. PDT leads to oral problems, including malocclusion, soft tissue trauma, and increased risk of periodontal disease. It is recommended that retained deciduous teeth be identified and extracted by a veterinarian in a timely manner, while avoiding damage to the underlying permanent tooth germs, to avoid future damage. Further, the risk of PDT depends on the attributes of the pet, such as the pet’s body size, breed, frequency of visits to the veterinarian, etc. For example, small breed dogs can have a higher likelihood of PDT than large breed dogs. Early detection and mitigation of PDT can help prevent an increased risk of related problems, such as periodontal disease and malocclusion, and help veterinarians and owners establish a customized oral care regimen for individual pets. Thus, there is a need to determine a pet’s PDT risk level.

[0005] The present disclosure is directed to addressing the challenges described above. The background description provided herein is for the purpose of generally presenting the context of the disclosure. Unless otherwise indicated herein, the materials described in this section are not prior art to the claims of this application and are not admitted to be prior art by inclusion in this section. SUMMARY

[0006] According to certain aspects of the present disclosure, embodiments are disclosed for predicting a Persistent Deciduous Teeth (PDT) risk level for one or more pets.

[0007] In one aspect, an example embodiment of a method for predicting a primary dentition retention (PDT) risk level for one or more pets is disclosed. The method can include receiving, by one or more processors, pet data corresponding to a pet from a user device, the pet data comprising one or more pet attributes. The method can include determining, by the one or more processors, a result value indicative of a PDT attribute weight for each of the one or more pet attributes based on the one or more pet attributes. The method can include analyzing, by the one or more processors, the result value for each of the one or more pet attributes to determine the PDT risk level, the analyzing comprising utilizing a PDT risk level prediction algorithm. The method can include displaying, by the one or more processors, the PDT risk level on one or more user interfaces of the user device.

[0008] In one aspect, a computer system for predicting a primary dentition retention (PDT) risk level for one or more pets is disclosed. The computer system can include at least one memory storing instructions and at least one processor configured to execute the instructions to perform operations. The operations can include receiving pet data corresponding to a pet from a user device, the pet data comprising one or more pet attributes. The operations can include determining a result value indicative of a PDT attribute weight for each of the one or more pet attributes based on the one or more pet attributes. The operations can include analyzing the result value for each of the one or more pet attributes to determine the PDT risk level, the analyzing comprising utilizing a PDT risk level prediction algorithm. The operations can include displaying the PDT risk level on one or more user interfaces of the user device.

[0009] In one aspect, a non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform operations for predicting a primary dentition retention (PDT) risk level for one or more pets. The operations can include receiving pet data corresponding to a pet from a user device, the pet data comprising one or more pet attributes. The operations can include determining a result value indicative of a PDT attribute weight for each of the one or more pet attributes based on the one or more pet attributes. The operations can include analyzing the result value for each of the one or more pet attributes to determine the PDT risk level, the analyzing comprising utilizing a PDT risk level prediction algorithm. The operations can include displaying the PDT risk level on one or more user interfaces of the user device.

[0010] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosed embodiments, as claimed. BRIEF DESCRIPTION OF DRAWINGS

[0011] The accompanying drawings, which are included in and form part of this specification, illustrate various exemplary embodiments and, together with the specification, serve to explain the principles of the disclosed embodiments.

[0012] Figure 1 A block diagram of an exemplary system for analyzing pet-related data according to one or more embodiments is depicted.

[0013] Figure 2 A flowchart illustrating an exemplary process for predicting the risk level of deciduous tooth retention (PDT) in one or more pets, according to one or more embodiments, is depicted.

[0014] Figure 3 An exemplary chart is shown that classifies canines by breed size risk and individual risk according to one or more embodiments.

[0015] Figure 4 An exemplary network computing environment, which can be used with the techniques described herein, is depicted according to one or more embodiments.

[0016] Figure 5 Examples of computing devices capable of performing the techniques described herein, according to one or more embodiments, are depicted. Detailed Implementation

[0017] According to certain aspects of this disclosure, methods and systems for analyzing pet data to determine the risk of retained deciduous teeth (PDT) in pets are disclosed.

[0018] Dogs use their teeth for many tasks, so maintaining their oral health is crucial for their health and well-being. Retained deciduous teeth (PDT), which are baby teeth that fail to fall out at the appropriate time, can lead to jaw misalignment, gum damage, and an increased risk of gum disease. PDT causes oral problems including malocclusion (abnormal bite), soft tissue trauma, and an increased risk of periodontal disease. It is recommended that a veterinarian promptly identify and remove retained deciduous teeth while avoiding damage to the underlying permanent tooth germ to prevent future harm. Furthermore, the risk of PDT depends on the pet's attributes, such as size, breed, and the veterinarian who treated it. For example, small dogs may be more likely to develop PDT than large dogs. Additionally, the chances of developing PDT increase significantly if more than two years have passed since the last professional dental cleaning and polishing. If it has been one to two years since the last cleaning and polishing, the chances of developing PDT are approximately 50% higher than if it has been less than one year.

[0019] Furthermore, early detection and mitigation of periodontal disease (PDT) can help reduce the severity of some of its consequences or delay their onset, such as malocclusion, soft tissue trauma, and an increased risk of periodontal disease. Timely identification can also help veterinarians remove retained deciduous teeth as early as possible while avoiding damage to the underlying permanent tooth germ. Therefore, it is necessary to determine the pet's PDT risk level.

[0020] Therefore, embodiments of this disclosure relate to systems and methods for predicting the level of retained deciduous teeth (PDT) risk in one or more pets. The system and method may include receiving pet data corresponding to a pet from a user device by one or more processors, the pet data including one or more pet attributes. The system and method may further include determining, by one or more processors, a resulting value indicating a PDT attribute weight for each of the one or more pet attributes based on the one or more pet attributes. The system and method may further include analyzing, by one or more processors, the resulting value for each of the one or more pet attributes to determine the PDT risk level, the analysis including utilizing a PDT risk level prediction algorithm. The system and method may further include displaying the PDT risk level on one or more user interfaces of the user device by one or more processors.

[0021] The advantages of such systems and methods can include improving the accuracy of predicting PDT risk levels by analyzing specific attributes of pets, thereby providing personalized PDT risk assessments. Additional advantages can include improved efficiency by leveraging predictive algorithms and machine learning models. Other advantages can include helping pet owners identify PDT and corresponding diseases, and providing personalized recommendations to pet owners.

[0022] Although the terminology used below is used in conjunction with the detailed description of certain specific examples of this disclosure, these terms may be interpreted in their broadest and most reasonable manner. In fact, some terms may even be emphasized below; however, any term intended to be interpreted in any limiting manner will be clearly and specifically defined in the Detailed Description section. The foregoing general description and the following detailed description are exemplary and illustrative only and do not limit the claimed features.

[0023] In the specific implementation described herein, references to "embodiment," "an embodiment," "a non-limiting embodiment," and "in various embodiments" indicate that the embodiment may include specific features, structures, or characteristics, but each embodiment may not necessarily include that specific feature, structure, or characteristic. Furthermore, such phrases do not necessarily refer to the same embodiment. Moreover, when a specific feature, structure, or characteristic is described in connection with an embodiment, it should be understood that, whether explicitly described or not, any combination of other embodiments to affect such feature, structure, or characteristic falls within the knowledge scope of those skilled in the art. After reading this description, those skilled in the art will understand how to implement this disclosure in alternative embodiments.

[0024] Generally, terms can be understood at least in part based on their usage in the context. For example, terms such as “and,” “or,” or “and / or” as used herein can include a variety of meanings that can depend at least in part on the context in which such terms are used. Generally, “or,” when used with an associative list, such as A, B, or C, is intended to mean A, B, and C (used herein in an inclusive sense) and A, B, or C (used herein in an exclusive sense). Furthermore, the term “one or more” as used herein depends at least in part on the context and can be used to describe any feature, structure, or characteristic in a singular sense, or can be used to describe a combination of features, structures, or characteristics in a plural sense. Similarly, terms such as “a,” “an,” or “the” can also be understood to express a singular or plural usage, depending at least in part on the context. Moreover, the term “based on” can be understood to not necessarily express a set of exclusive factors; instead, it can allow for the presence of additional factors that are not necessarily explicitly described, which also depends at least in part on the context.

[0025] As used herein, the terms “comprises,” “comprising,” “includes,” “including,” or any other variation thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements may include not only those elements but also other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0026] The terms “pet” and “domestic pet” as used in this disclosure may refer to (but are not limited to) domesticated or tamed animals, such as dogs, cats, rabbits, horses, etc.

[0027] The term "pet owner" can include (for example, but not limited to) any individual, organization, and / or group of individuals who owns a pet and / or provides food and shelter for the pet. For example, "pet owner" can include pet adopters, pet caregivers, pet pet handlers, and animal shelters.

[0028] The term "veterinarian" can include (for example, but not limited to) any individual, organization, and / or group of individuals who provide medical care for pets. For example, "veterinarian" can include veterinary technicians, veterinary personnel, and veterinary practitioners.

[0029] The terms "canine" and "dog" can include (for example, but not limited to) recognized dog breeds (some of which can be further subdivided). For example, recognized dog breeds can include Afghan Hound, Airedale, Akita, Alaskan Malamute, Basset Hound, Beagle, Belgian Shepherd, Bloodhound, Border Collie, Border Terrier, Borzoi, Boxer, Bulldog, Bull Terrier, Cairn Terrier. Terrier, Chihuahua, Chow Chow, Cocker Spaniel, Collie, Corgi, Dachshund, Dalmatian, Doberman Pinscher, English Setter, Fox Terrier, German Shepherd, Golden Retriever, Great Dane, Greyhound, Brussels Griffon, Irish Setter, Irish Wolfhound, Cavalier King Charles Spaniel, Labrador Retriever, Lhasa Apso, Mastiff, Newfoundland, Old English Sheepdog, Papillon, Pekingese, Pointer, Pomeranian, Poodle, Pug, Rottweiler, Saint Bernard, Saluki, Samoyed, Schnauzer, Scottish Terrier, Shetland Sheepdog, Shih Tzu, Siberian Husky, Skye Terrier, Springer Spaniel, West Highland White Terrier, Yorkshire Terrier, etc.

[0030] As used herein, the term "pet data" or "pet metadata" may include (e.g., but not limited to) biological data, such as any one or a combination of certain biological information or attributes of a pet, including at least its breed, age, body size, weight, physical condition, head shape (e.g., skull shape), predicted body type, genetic markers associated with a higher risk of PDT, predicted adult weight, and / or oral health data associated with common symptoms of PDT. Pet data may also include environmental data (e.g., external factors). Environmental data may include information about the frequency of the pet's veterinary visits, the pet's most recent oral assessment, or the pet's oral care routine (e.g., frequency of brushing and / or use of dental treats, oral rinsing solutions, oral gels, and chew toys). Other environmental data may include changes in pet behavior that may indicate PDT (e.g., eating habits and scratching the face). Furthermore, for example, pet data may include, but is not limited to, answers to questions related to the aforementioned biological information, environmental / external factors, and attributes.

[0031] As used herein, a “machine learning model” generally encompasses a model that receives instructions, data, and / or is configured to receive input and apply one or more of weights, biases, classifications, or analyses to the input to generate an output. The output may include, for example, a classification of the input, an analysis based on the input, a design, process, prediction, or recommendation associated with the input, or any other suitable type of output. Machine learning models are typically trained using training data (e.g., empirical data and / or samples of input data) that are fed into the model to establish, adjust, or modify one or more aspects of the model, such as weights, biases, criteria for forming classifications or clusters, etc. Aspects of a machine learning model may operate on the input linearly and in parallel via a network (e.g., a neural network) or via any suitable configuration.

[0032] The execution of a machine learning model can include deploying one or more machine learning techniques, such as linear regression, logistic regression, random forests, gradient boosted machines (GBM), deep learning, and / or deep neural networks. Supervised and / or unsupervised training can be employed. For example, supervised learning can involve providing training data and corresponding labels, such as ground truth. Unsupervised methods can include clustering, classification, etc. Any suitable type of training can be used, such as randomized training, gradient boosting training, randomized seed training, recursive training, epoch-based training, or batch training.

[0033] The term “diagnosis” may include (e.g., but not limited to) the identification and / or characterization of a disease or condition (e.g., PDT), the prediction of the course of a disease or condition, the prediction of the likelihood of a disease or condition, and a conclusion about the level of risk associated with a disease or condition (e.g., low risk, medium risk, and high risk).

[0034] Certain non-limiting embodiments are described below with reference to block diagrams and operating instructions of methods, processes, apparatuses, and devices. It should be understood that each block in the block diagram or operating instructions, and combinations of blocks in the block diagram or operating instructions, can be implemented by analog or digital hardware and computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer to modify its functionality (as described herein), a special-purpose computer, an ASIC, or other programmable data processing means, such that instructions executed by the processor of the computer or other programmable data processing means implement the function / action specified in the block diagram or one or more operating blocks. In some alternative embodiments, the functions / actions shown in the blocks may not be performed in the order shown in the operating instructions. For example, two blocks displayed consecutively may actually be executed substantially simultaneously, or sometimes in reverse order, depending on the functions / actions involved.

[0035] Example embodiments for analyzing data associated with pets

[0036] Figure 1 An exemplary embodiment of a system 100 for analyzing pet-related data is shown. Typically, system 100 may include a pet information database 110, a PDT risk assessment component 120, an analysis module 130, a logical data structure interpretation module 140, a results server 150, a health report 160, an archive 170, and a cloud platform 180.

[0037] System 100 can be implemented on cloud platform 180, thereby allowing data to be transferred or shared between each of the pet information database 110, PDT risk assessment component 120, analysis module 130, interpretation logic data structure 140, results server 150, health report 160 and archive 170 in the cloud environment.

[0038] Pet information database 110 includes storage 112. Storage 112 in pet information database 110 may contain pet data associated with pets (e.g., biological data and environmental data). One or more users can access pet information database 110 via a server through one or more user devices. The one or more users may include pet owners or veterinarians. One or more users may use one or more user devices to input pet data associated with their pets. The user device may be... Figure 4 The computing devices described herein are consistent with those described in the text, such as desktop computers, tablets, laptops, smartphones, smartwatches, etc.

[0039] Pet data associated with a pet and entered into the pet information database 110 by one or more users may include one or more of the following pet attributes: pet type (e.g., breed, pet category), pet head shape, pet weight and body type category, pet weight, pet physical condition, predicted pet body type category, pet adult weight category, pet age, frequency of pet veterinary visits (e.g., veterinarian), and pet's planned or most recent veterinary visit (e.g., veterinarian). Additional pet data (which may be entered by one or more users and stored in the pet information database 110) may include oral health data related to common symptoms and consequences of pet dental degeneration (PDT), as well as information related to routine pet oral care. For example, one or more users may enter information about whether the pet has malocclusion (malbite), food impaction, soft tissue trauma, swollen gums, inflammation, redness and / or bleeding, behavioral changes (e.g., changes in eating habits or scratching the face), stomach sensitivity, halitosis, plaque or tartar buildup, and the frequency of brushing and use of dental treats, oral rinsing solutions and / or oral gels. Pet data associated with a pet can be stored in storage 112 of the pet information database 110.

[0040] In some embodiments, both the pet owner and the veterinarian can input pet-related data into the pet information database 110. In other embodiments, only one of the pet owner and the veterinarian can input pet-related data into the pet information database 110. In at least some embodiments, one or more users may be prompted to input at least one of the following pet attributes into the pet information database 110: pet type (e.g., breed, pet category), pet head shape, pet weight and body type category, pet weight status, pet physical condition, predicted pet body type category, pet adult weight category, pet age, frequency of pet veterinary visits (e.g., veterinarian), pet schedule, most recent veterinary visit (e.g., veterinarian), and any other pet data described in this disclosure (e.g., data described in the preceding paragraph). In some examples, one or more users may be prompted to input a halitosis status of "none" or "yes" into the pet information database 110.

[0041] The pet information database 110 can transmit pet data associated with a pet to the PDT risk assessment component 120. The pet information database 110 can also transmit pet data associated with a pet to the analysis module 130. In some embodiments, the pet information database 110 can also receive data from the analysis module 130, such as one or more outcome statements related to the pet's oral health.

[0042] The PDT risk assessment component 120 can receive pet-related pet data from the pet information database 110, as described above. The PDT risk assessment component 120 can be deployed in an application programming interface (API). The PDT risk assessment component 120 can also transmit PDT risk data to the analysis module 130. The PDT risk assessment component 120 described herein can also be used in other applications outside of system 100 (e.g., websites).

[0043] Results server 150 includes storage 152. Users can input results from one or more tests or samples collected from pets via a user device into results server 150. For example, results may be related to determining the breed of a pet. Results may be related to novel biomarkers. For example, biomarkers may include genetic markers that can identify a pet's genetic susceptibility to PDT. Results may be stored in storage 152. Results server 150 can transmit results to analysis module 130.

[0044] Analysis module 130 can receive pet-related data from one or more data sources in system 100 and pet-related result data from result server 150. For example, analysis module 130 can receive pet-related data directly from pet information database 110 and from PDT risk assessment component 120. In some embodiments, selected pet data associated with a pet can be transferred from pet information database 110 to PDT risk assessment component 120 for analysis, and the PDT risk data generated based on this analysis can be transferred to analysis module 130. In some embodiments, certain types of pet data, such as pet veterinary visit frequency, can be transferred directly from pet information database 110 to analysis module 130 without first transferring it to PDT risk assessment component 120.

[0045] Analysis module 130 can use the interpretation logic data structure 140 to analyze the received pet data and results. Based on the analysis of the pet data and results using the interpretation logic data structure 140, analysis module 130 can identify one or more statements related to the pet's oral health and generate a health report 160 containing these statements. Health report 160 may include a pet owner report 162 and / or a veterinarian report 164. Analysis module 130 can also transmit / store the generated statements to a repository 170. Repository 170 can store the analysis data received from analysis module 130 in storage 172.

[0046] It should also be noted that although system 100 describes analysis module 130 using interpreting logical data structure 140, in some embodiments, analysis module 130 may use machine learning models. In these embodiments, trained machine learning models may be stored and used by analysis module 130.

[0047] Example methods for predicting a level of risk of PDT

[0048] Figure 2 A flowchart illustrating an exemplary method 200 for predicting the risk level of retained deciduous teeth (PDT) in one or more pets according to one or more embodiments is depicted. In some embodiments, a PDT risk determination component 120 may perform the exemplary method 200. Furthermore, method 200 may be performed by one or more processors of a server communicating with one or more user devices and other external systems via a network. However, it should be noted that method 200 may be performed by the server, one or more user devices, or any one or more of the other external systems.

[0049] The method may include receiving pet data corresponding to a pet from a user device by one or more processors, the pet data including one or more pet attributes (step 202). In some embodiments, the PDT risk assessment component 120 may receive pet data from a user device and / or one or more databases (e.g., pet information database 110). The pet data may include at least one of the following: an image of the pet, a corresponding medical record, pet data input via the user device, or pet data stored in one or more pet data repositories. The pet image may include digital photographs or dental X-rays of the pet's teeth, face, and / or body. The medical record may include information about the pet's medical history, such as oral examinations, vaccinations, medications, hospitalizations, diagnoses, etc. Pet owners, veterinarians, medical professionals, and / or third parties may input the pet data. Additionally or alternatively, the pet data may have been previously stored in one or more data repositories (e.g., pet information database 110).

[0050] Pet data may include one or more pet attributes (and corresponding pet attribute values), which may include one or more of the following: pet type, pet head shape, pet weight / body type category, pet weight status, pet body condition, predicted pet body type category, pet adult weight category, pet age, frequency of pet veterinary visits (e.g., by a veterinarian), pet schedule, most recent veterinary visit (e.g., by a veterinarian), behavioral and movement data, historical pet data, pet household information, and any other information related to any aspect of the pet's life, health (e.g., diet and oral care program), or environment. Pet type may correspond to one or more breeds. Additionally or alternatively, pet type may correspond to pet category, such as dog, cat, bird, rabbit, horse, etc. Pet head shape may correspond to the shape of the pet's head. Pet weight / body type category may include at least one of the following: toddler, small, medium-sized, medium-large, large, or extra-large. Pet weight may include at least one of the following: underweight, average weight, overweight, obese, etc. Additionally or alternatively, pet weight may include a numerical value corresponding to the pet's weight. Pet body condition may include a pet body condition score (“BCS”). For example, the BCS can include numerical values ​​(e.g., 0-9 on a 9-point scale). The BCS can be recorded on a 5-point scale (e.g., 1 = malnutrition, 3 = normal, 5 = obesity) or as a diagnostic input for overweight / obesity or underweight / emaciated. Furthermore, for example, if multiple conflicting BCSs exist on the same day, an abnormal BCS can be used (e.g., if a pet's BCS input is "normal" but the diagnosis is overweight, then the pet can be considered overweight at that visit). Additionally or alternatively, the BCS can be converted to a 3-point scale (e.g., 1 = underweight, 2 = ideal, 3 = overweight).

[0051] The predicted pet body size category can correspond to the predicted body size of the pet at adulthood. The pet adult weight category can correspond to the pet adult weight. The pet age can correspond to the pet's age. The frequency of pet veterinary visits (e.g., veterinarian visits) can correspond to the frequency of the pet's visits to a veterinarian. The pet plan can correspond to the pet's health plan. The most recent veterinary visit (e.g., veterinarian visit) can correspond to the time of the pet's most recent veterinary visit, such as the pet's medical data. Behavioral and motor data can describe how the pet walks, sits, runs, eats, etc. Historical pet data can include previously entered pet data, as well as data describing the pet's past behavior. Pet family information can describe the pet's residence, other pets living with the pet, other people living with the pet, etc. In some embodiments, one or more pet attributes can include outcome data (e.g., results stored in outcome server 150).

[0052] In some embodiments, the PDT risk assessment component 120 may receive one or more pet attributes from one or more user devices. For example, the PDT risk assessment component 120 may prompt one or more users (e.g., pet owners, veterinarians) to input one or more pet attributes via a user interface presented on one or more user devices. Some pet attributes, such as age and weight, may be provided by the pet owner via the user device, while other pet attributes, such as predicted body type, head shape, and / or predicted adult weight, may be provided by the veterinarian via the user device.

[0053] The method may include, by one or more processors, determining a result value (step 204) indicative of a PDT attribute weight for each of the one or more pet attributes, based on one or more pet attributes. Each pet attribute may be analyzed individually or together to determine its PDT attribute weight, wherein the PDT attribute weight may be represented as a result value (e.g., percentage, ratio, number, etc.). Each attribute may have a corresponding PDT probability weight, wherein the PDT probability weight may indicate the likelihood that a pet may be diagnosed with PDT. For example, a pet attribute may include a pet's age of 1 year, wherein the corresponding result value may include an 11% PDT attribute weight. In some embodiments, one or more databases may store result values ​​corresponding to pet attributes, wherein the system may retrieve result values ​​from one or more databases.

[0054] In some embodiments, the machine learning model may analyze one or more pet attributes to determine outcome values ​​that indicate the PDT attribute weights. One or more pet attributes may be input into the machine learning model, which may output outcome values ​​for such attributes. Furthermore, the machine learning model may have been previously trained to determine the PDT attribute weights for one or more pet attributes.

[0055] The method may include having one or more processors analyze the resulting values ​​of each of one or more pet attributes to determine the PDT risk level, the analysis including utilizing a PDT risk level prediction algorithm (step 206). The PDT risk level may be expressed as a percentage, ratio, number, color, phrase (e.g., “low risk,” “medium risk,” or “high risk”), etc.

[0056] In some embodiments, analyzing the resulting values ​​to determine the PDT risk level may include receiving, by one or more processors, one or more pet dental datasets of one or more similar pets from one or more data repositories, wherein the one or more similar pets have at least one attribute similar to the original pet. The data repository may store datasets of multiple other pets, wherein the dataset may include attributes (including corresponding attribute values) for each other pet. As previously described, these attributes may include one or more of the following: pet type (e.g., breed, pet category), pet head shape, pet weight / body type category, pet weight status, pet physical condition, predicted pet body type category, pet adult weight category, pet age, pet veterinary visit frequency (e.g., veterinarian), and pet scheduled or most recent veterinary visit (e.g., veterinarian). The dataset may also include additional pet information describing the other pets, and the PDT risk level of such pets. The method may include receiving and analyzing datasets to determine at least one dataset of similar pets. This dataset may include at least one attribute similar to the original pet. For example, pet data may include an age attribute of 1 year, while the similar pet dataset may include an age attribute of 1 year and a PDT risk level of 0.25.

[0057] Furthermore, analyzing the results to determine the PDT risk level may further include: one or more processors using a PDT risk level prediction algorithm to determine the PDT risk level by comparing the result value corresponding to each of one or more pet attributes with one or more pet dental datasets. The PDT risk level prediction algorithm can predict the risk of a pet having PDT based on pet attributes. For example, the PDT risk level prediction algorithm can analyze dental datasets to determine which datasets include attributes most similar to the pet's attributes. The PDT risk level prediction algorithm can also analyze the corresponding PDT risk levels of such datasets to determine the pet's PDT risk level. The PDT risk level can include low risk, medium risk, or high risk, where the PDT risk level indicates the probability that the pet will be diagnosed with PDT. Additionally or alternatively, the PDT risk level can include scores indicating the weight of PDT attributes.

[0058] For example, if the sum of the percentages of breed-indicating PDTs in a pet dataset exceeds 8%, 3 points can be assigned to the PDT risk level prediction algorithm applied to the initial pets. 2 points can be assigned to pet datasets whose breed shows a PDT between 2% and 5% in the PDT risk level prediction algorithm, and 1 point can be assigned to pet datasets whose breed shows a PDT of less than 2% in the total population. In some embodiments, this score can be represented as high-risk, medium-risk, and low-risk pets.

[0059] Algorithms for predicting PDT risk levels may include the use of machine learning models, which may have been trained to determine PDT risk levels. For example, the machine learning model may have been trained using one or more training outcome values ​​for one or more attributes, one or more training datasets, and / or one or more training PDT risk levels to learn the associations between the outcome values, datasets, and / or PDT risk levels. The machine learning model may receive outcome values ​​for each of one or more pet attributes, and one or more pet dental datasets. The machine learning model may analyze and compare the outcome values ​​and the dental datasets to determine the PDT risk level.

[0060] The method may include displaying a PDT risk level on one or more user interfaces of a user device by one or more processors (step 208). The one or more user interfaces may display the PDT risk level as “low risk,” “medium risk,” or “high risk.” Additionally or alternatively, the one or more user interfaces may display a numerical value. For example, the one or more user interfaces may display “0.1 – Low risk.” The one or more user interfaces may utilize different colors or graphics to display the PDT risk level, depending on the PDT risk level. For example, the one or more user interfaces may display “low risk” in green, “medium risk” in yellow, or “high risk” in red. In some embodiments, the display may include showing a notification on one or more user interfaces of the user device. This notification may remind the user that the pet needs medical attention and / or medical treatment.

[0061] In some embodiments, the PDT risk level may be stored in one or more databases. The PDT risk level may be stored along with a corresponding unique pet identifier. In future analyses, the PDT risk level prediction algorithm may utilize the stored PDT risk levels when performing PDT risk level analysis. Additionally or alternatively, one or more stored PDT risk levels may be combined with the current PDT risk level for analysis to determine whether the pet's PDT risk level is increasing or decreasing. One or more user interfaces may display notifications indicating whether the pet's PDT risk level is increasing or decreasing.

[0062] In some embodiments, the method may further include: determining one or more recommendations by one or more processors based on a PDT risk level. For example, if the PDT risk level is “high risk,” the recommendations may include advice on how to manage or treat PDT, such as recommending regular dental checkups for the pet, or recommending veterinary extraction or monitoring of the teeth. Additionally, for example, if the PDT risk level is “medium risk,” the recommendations may include more frequent scaling and polishing of the pet’s teeth to help prevent or delay periodontal disease. The recommendations may include links to internal or external sources that can provide support on how to identify and treat PDT. The method may also include displaying one or more recommendations by one or more processors on one or more user interfaces of a user device. For example, one or more user interfaces may display links to internal or external sources. Additionally or alternatively, one or more user interfaces may display the recommendations.

[0063] although Figure 2 An example block of exemplary method 200 is shown, but in some implementations, exemplary method 200 may include more than Figure 2 The additional blocks, fewer blocks, different blocks, or blocks with different arrangements depicted. Additionally or alternatively, two or more blocks in the exemplary method 200 may be executed in parallel.

[0064] Example PDT risk score chart

[0065] Figure 3 An exemplary chart categorizes canines by PDT (Protection of Toxic Species) based on breed size risk and individual breed risk. Specifically, the chart illustrates the PDT risk for each individual breed and breed size. Size groups include: toy poodle, small, medium-small, medium-large, large, and extra-large. The chart shows how the PDT risk score decreases for each canine size group as the canine's body size increases. A risk score above 10% indicates a high PDT risk. For example, a toy poodle with a high PDT risk might have a PDT risk score of 14.8%. A risk score between 2% and 10% indicates a medium PDT risk. For example, a dachshund with a medium PDT risk might have a PDT risk score of 9.3%. A risk score below 2% indicates a low PDT risk. For example, a boxer with a low PDT risk might have a PDT risk score of 0.4%.

[0066] Example data

[0067] Medical records collected from nearly 3 million dogs (representing 60 breeds) visiting chain veterinary hospitals across the United States over a five-year period showed an overall prevalence of dental degeneration (PDT) of 7%, with a significantly higher prevalence (15%) in toddler breeds (<6.5 kg) than in all other breed sizes (P<0.001). Statistical modeling of toddler, small, and medium-sized breeds showed a significantly increased risk of PDT in breeds that participated in a wellness plan (WP) or had not received dental preventative care for at least two years (P<0.0001). Within the toddler, small, and medium-sized categories, leaner dogs had a slightly lower risk of PDT (OR 0.57–0.89, P<0.0001), while overweight dogs had a slightly increased risk (OR 1.11–1.60, P<0.0001).

[0068] Statistical analysis

[0069] Specifically, software was used to analyze the data. Descriptive statistics for all breed size categories and individual breeds were calculated. The prevalence of PDT by size category and breed was calculated based on whether the pets had at least one retained deciduous tooth during the five-year study period. The finding of "having at least one retained deciduous tooth before 60 months of age" was modeled using logistic regression.

[0070] PDT was modeled by breed size category using logistic regression. Only the extra-small, small, and medium-sized categories were used because these categories had the highest PDT proportion. For the breed size category model, extra-small was used as a reference, and covariates and their interactions were included. Covariates included dental cleaning status and average pet weight during the five-year study period, dental cleaning status at the time of visit, pet health status (WP), and WP duration (in months). Dummy variables for small and medium-sized, body condition score, sex, neutering status, and days since the last dental cleaning were also included. Odds ratios (OR; with confidence limits) were calculated for each item.

[0071] Bonferroni-corrected pairwise comparisons were performed to compare estimated odds ratios (ORs) between extra-small, small, and medium-sized body types, and between individual breeds within each body type category. For body type analyses, extra-small was used as a reference, and the following covariates (without interaction) were included: dental cleaning and polishing during the study period, dental cleaning and polishing at the time of visit, pet age (in months), normalized pet weight (pet weight - median / median), health plan (WP) at the time of visit, WP duration (in months), dummy variables for BCS: overweight, underweight (with normal as a reference), sex: female (with male as a reference), neutering status: neutered (with unneutered as a reference), and time since last dental cleaning and polishing: less than 2 years, more than 2 years, not recorded (with less than 1 year as a reference). For each breed within a body type analysis, Yorkshire Terriers were used as a reference for the extra-small category, Dachshunds as a reference for the small category, and Pugs as a reference for the medium-sized category. Based on Bonfroni's multiple comparison correction, the results are considered significant if the P-value for comparisons within varietal size categories is less than or equal to 0.017, and the P-value for comparisons within varietal size categories is less than or equal to 0.001.

[0072] The Generalized Estimating Equation (GEE) model with a composite symmetric working covariance structure was used to correct for repeated measurements for each pet, and a final analysis was conducted to determine whether PDT existed for the extra-small, small, and medium-sized body categories over the entire five-year timescale.

[0073] Results: Study population A total of 5,787,581 dogs received 31,306,476 veterinary visits. Of these, 3,320,519 dogs (57.4%) and 18,233,668 visits (58.4%) came from 60 purebred breeds. After applying exclusion criteria, 2,841,032 dogs and 14,746,685 visits were included in the analysis.

[0074] The majority of dogs (36.9%) belong to the toddler breed weight category. Apart from the extra-large breed category, which comprises the remaining 3.1% of dogs, the other breed weight categories account for between 11.7% and 18.4% of the dogs.

[0075] The overall mean age of the study population was 61.8 months (±44.1 months), with a mean age at first visit of 50.9 months (±44.0 months). Males (52.6%) slightly outnumbered females (47.4%), and the majority (70.8%) were castrated / neutered. Overall, the mean weight for each size category was: 4.7 kg (totsubo), 7.6 kg (small), 12.1 kg (medium), 26.1 kg (medium-large), 34.3 kg (large), and 45.9 kg (totsubo). In total, 83.1% of the dogs were considered to have ideal BCS at the start of the study. A small percentage of dogs were recorded as underweight (mean total 2.4%). The totsubo breed weight category had the highest proportion of dogs recorded as underweight at first visit (4.2%), while the small and medium breed categories had the lowest proportions (both 1.4%). A high percentage of dogs were also recorded as overweight (14.5%). Small (17.9%), medium (22.9%), and large (18.7%) breeds had the highest percentage of dogs recorded as overweight at their first visit.

[0076] More than half of the dogs (54.6%–58.6%) joined a Veterinary Hospital Workshop (WP) during the five-year study period, with an average duration of WP participation of 17.4 months. Approximately 81.2% of veterinary hospital inpatient visits were related to WP.

[0077] On average, 30.8% of dogs had undergone dental cleaning and polishing within the 12 months prior to their visit, with the highest percentage in small breeds (39.0%) and the lowest in large breeds (21.8%). Overall, an average of 2.2% of dogs had not undergone dental cleaning and polishing for more than 24 months, with small breeds showing the highest average at 2.8%.

[0078] Prevalence of retained primary teeth

[0079] During the five-year study period, the overall average prevalence of PDT in the 60 dog breeds studied was 7.0%, such as Figure 3 As shown, the prevalence of PDT was highest in the toddler breed (15.0%), followed by small breeds at 6.1% and medium-sized breeds at 3.4%. The average prevalence of PDT in medium-large, large, and extra-large breeds was <1%.

[0080] In terms of individual breeds, Yorkshire Terriers had the highest prevalence of retained deciduous teeth (PDT) (25.1%), followed by Maltese and Toy Poodles (both 14.8%). Regarding the prevalence of retained deciduous teeth, the top 10 breeds included nine toddler breeds and one small breed (Dachshund). The other two breeds with a retained deciduous teeth prevalence exceeding the overall average of 7% were Miniature Schnauzers (7.3%) and Pugs (7.3%). Pekingese were the only toddler breed with a prevalence below the overall average, at 3.8%. 27 breeds were reported to have a PDT prevalence ≤1.0%, all of which were medium, large, or extra-large breeds. The lowest prevalence recorded was in Greyhounds at 0.1%. PDT prevalence data for all 60 breeds during the five-year study period are as follows: Figure 3 As shown.

[0081] Regression analysis modeling using GEE over the entire five-year period showed that, except for females, all covariates had small (OR = 0.98–1.11) but statistically significant effects on PDT outcomes (all P < 0.0001). However, this statistical significance may be due to the large data volume and is therefore unlikely to be clinically relevant. Comparison of breed body size categories over the entire five-year period showed that small and medium-sized breeds had a lower probability of developing PDT compared to extra-small breeds (OR 0.36 and 0.20, respectively, P < 0.001).

[0082] Pairwise comparisons among the toy, small, and medium-sized breeds showed that the small and medium-sized breeds had a significantly lower incidence of PDT compared to the toy breed (ORs were 0.41 and 0.20, respectively; P < 0.0001). The medium-sized breeds also had a lower incidence of PDT compared to small dogs (OR = 0.48; P < 0.0001).

[0083] Based on statistical models within the extra-small breed category, pairwise comparisons showed that Yorkshire Terriers had a significantly higher incidence of PDT than all other extra-small breeds (OR=1.9-7.2, P<0.0001). Pekingese had a significantly lower incidence of PDT than all other breeds in this category (OR=0.14-0.56, P<0.0001).

[0084] Within the small-sized category, Dachshunds had a significantly higher incidence of PDT than all other breeds in that category (OR=1.21–4.21, P<0.0001). Similarly, Miniature Schnauzers had a higher incidence of PDT than all other breeds in that category except Dachshunds (OR=1.1–3.48, P<0.0001). West Highland White Terriers had a significantly lower incidence of PDT than all other breeds in that category (OR=0.24–0.85, P<0.0001).

[0085] Within the small to medium size category, Pugs had a higher prevalence of PDT than all other breeds in the category (OR=1.62–6.73, P<0.0001). Cavalier King Charles Spaniels also had a higher prevalence of PDT than all other breeds in the same size category except Pugs (OR=1.56–4.15, P<0.0001). Standard Schnauzers had the lowest prevalence of PDT compared to all other breeds in the small to medium size category, although this was not statistically significant after Bonferoni correction (OR=0.15–0.76, P=0.001). This finding may be due to the underrepresentation of Standard Schnauzers, meaning there may not have been a sufficient number of individuals to detect significant differences.

[0086] Risk factors for retained primary teeth

[0087] According to the breed size category model, the probability of PDT (professional dental cleaning and polishing) significantly increased if more than two years had passed since the last professional dental cleaning and polishing (ORs were 3.36, 2.70, and 2.17 for extra-small, small, and medium-small size categories, respectively; all P < 0.0001). Compared to less than one year ago, the probability of PDT increased by approximately 50% when records showed a cleaning and polishing performed one to two years prior (OR = 1.51–1.62; P < 0.0001). When the most recent cleaning and polishing procedure was unknown, the impact on the probability of PDT was minimal (0.99–1.16; P < 0.0001).

[0088] Breed-size classification models showed that weight had a significant impact on the probability of dental dysplasia (PDT). Dogs whose weight deviated further from the median weight of their breed-size category had a lower probability of PDT (ORs were 0.21, 0.16, and 0.14, respectively; all P < 0.0001). For each individual breed within the toy, small, and medium-sized categories, ORs were < 0.29 (P < 0.0001), which was associated with their weight deviating further from their breed-size median weight. The body-size classification model indicated that in toy, small, and medium-sized dogs, being underweight slightly reduced the probability of dental dysplasia (PDT) (ORs were 0.85, 0.89, and 0.57, respectively; P < 0.0001). In contrast, being overweight slightly increased the probability of PDT in toy, small, and medium-sized dogs (ORs were 1.11, 1.45, and 1.60, respectively; P < 0.0001).

[0089] Example environment and example device

[0090] Figure 4An exemplary environment 400 is depicted that can be used with the techniques described herein. One or more user devices 405, one or more external systems 410, and one or more server systems 415 can communicate via network 401. As will be discussed in further detail below, one or more server systems 415 can communicate with one or more other components of environment 400 via network 401. One or more user devices 405 can be associated with a user.

[0091] In some embodiments, components of environment 400 are associated with a common entity, such as a veterinarian, a mobile platform, etc. In some embodiments, one or more components of the environment are associated with another different entity. The systems and devices of environment 400 can communicate in any arrangement. As will be discussed herein, the systems and / or devices of environment 400 can communicate to perform activities such as generating, training, and / or using machine learning models to predict PDT risk levels.

[0092] User equipment 405 may be configured to enable a user to access other systems in environment 400 and / or interact with other systems in environment 300. For example, user equipment 405 may be a computer system, such as a desktop computer, mobile device, tablet computer, etc. In some embodiments, user equipment 405 may include one or more electronic applications, such as programs, plug-ins, browser extensions, etc., installed on the memory of user equipment 405.

[0093] User equipment 405 may include a display / user interface (UI) 405A, a processor 405B, a memory 405C, and / or a network interface 405D. User equipment 405 may execute an operating system (O / S) and at least one electronic application (each stored in memory 405C) via processor 405B. The electronic application may be a desktop program, a browser program, a web client, or a mobile application (which may also be a browser program in a mobile O / S), an applicant-specific program, system control software, system monitoring software, software development tools, etc. For example, environment 400 may extend information on a web client accessible via a web browser. In some embodiments, the electronic application may be associated with one or more other components in environment 400. The application may manage memory 405C (e.g., a database) to transmit streaming data to network 401. The display / UI 405A may be a touchscreen or a display with other input systems (e.g., a mouse, keyboard, etc.) so that the user can interact with the application and / or O / S. The network interface 405D may be a TCP / IP network interface for, for example, Ethernet or wireless communication with network 401. When executing an application, processor 405B may generate data and / or receive user input from display / UI 405A and / or receive / transmit messages to server system 415, and may further perform one or more operations before providing output to network 401.

[0094] External system 410 may be, for example, one or more third-party and / or auxiliary systems, integrated with and / or communicating with server system 415 when performing various PDT risk level prediction tasks. External system 410 may communicate with other devices or systems in environment 400 via one or more networks 401. For example, external system 410 may communicate with server system 415 via API (Application Programming Interface) access through one or more networks 401, or communicate with user device 405 via a web browser access through one or more networks 401.

[0095] In various embodiments, network 401 may be a Wide Area Network (WAN), a Local Area Network (LAN), a Personal Area Network (PAN), etc. In some embodiments, network 401 includes the Internet, and information and data are transmitted online between the systems. "Online" can mean connecting to or accessing source data or information from a remote location from other devices or networks coupled to the Internet. Alternatively, "online" can refer to connecting to or accessing the network via a mobile communication network or device (wired or wireless). The Internet is a global computer network system in which a party, a computer or other device connected to the network, can obtain information from any other computer and communicate with parties, other computers or devices. The most widely used part of the Internet is the World Wide Web (often abbreviated as "WWW" or simply "Web"). A "website page" typically encompasses location, data storage, etc., for example, hosted and / or operated by a computer system for online access, and may include data configured to cause programs (e.g., web browsers) to perform operations such as sending, receiving, or processing data, generating visual displays, and / or interactive interfaces.

[0096] Server system 415 may include an electronic data system, such as a computer-readable storage device, such as a hard disk drive, flash drive, disk, etc. In some embodiments, server system 415 includes and / or interacts with an application programming interface for exchanging data with other systems, such as one or more other components of the environment.

[0097] Server system 415 may include database 415A and at least one server 415B. Server system 415 may be a computer, computer system (e.g., rack server), and / or cloud service computer system. Server system may store or access database 415A (e.g., hosted on a third-party server or in storage 415E). Server may include display / UI 415C, processor 415D, storage 415E, and / or network interface 415F. Display / UI 415C may be a touchscreen or a display with other input systems (e.g., mouse, keyboard, etc.) so that an operator of server 415B can control the functions of server 415B. Server system 415 may execute an operating system (O / S) and at least one servlet (server applet) program instance (each stored in storage 415E) via processor 415D.

[0098] Server system 415 can generate, store, train, or use a machine learning model configured to predict the PDT risk level of a pet. Server system 415 may include the machine learning model and / or instructions associated with it, such as instructions for generating, training, and using the machine learning model. Server system 415 may include instructions for predicting the PDT risk level of a pet (e.g., based on the output of the machine learning model) and / or instructions for operating display 415C to output the PDT risk level (e.g., adjusted based on the machine learning model). Server system 415 may include training data, such as one or more training result values, one or more training datasets, and / or one or more training PDT risk levels.

[0099] In some embodiments, a system or device other than server system 415 is used to generate and / or train the machine learning model. For example, such a system may include instructions for generating the machine learning model, training data, and ground truth, and / or instructions for training the machine learning model. The resulting trained machine learning model can then be provided to server system 415.

[0100] Typically, machine learning models consist of a set of variables, such as nodes, neurons, and filters, which are adjusted (e.g., weighted or biased) to different values ​​by applying training data. In supervised learning, for example, given a baseline truth of the provided training data, training can be performed by feeding samples of the training data into a model with variables set to initial values, such as random, Gaussian noise-based, or pre-trained models. The output can be compared to the baseline truth to determine the error, which can then be backpropagated through the model to adjust the values ​​of the variables.

[0101] Training can be performed in any suitable manner, such as in batches, and can include any suitable training method, such as stochastic or non-stochastic gradient descent, gradient boosting, random forests, etc. In some embodiments, a portion of the training data can be retained during training and / or used to validate the trained machine learning model, for example, by comparing the output of the trained model with the benchmark truth of that portion of the training data to evaluate the accuracy of the trained model. The training of the machine learning model can be configured such that the machine learning model learns the correlation between the resulting values, the dataset, and / or the PDT risk level.

[0102] In various embodiments, the variables of the machine learning model can be correlated with each other in any suitable arrangement to generate output. For example, the machine learning model may include one or more convolutional neural networks (CNNs) configured to identify PDT risk levels, and may include further architectures, such as connection layers, neural networks, etc., configured to determine relationships between identified features in order to determine the predicted PDT risk level of a pet.

[0103] Despite Figure 4 While depicted as separate components, it should be understood that in some embodiments, a component or portion thereof in environment 400 may be integrated with or incorporated into one or more other components. For example, a portion of display 415C may be integrated into user equipment 405, etc. In some embodiments, the operation or aspects of one or more of the components discussed above may be distributed across one or more other components. Any suitable arrangement and / or integration of various systems and devices can be used with environment 400.

[0104] The methods described above discuss other aspects of machine learning models and / or how to utilize them to predict PDT risk levels in more detail. In these methods, various actions can be described as being derived from... Figure 4 The components (e.g., server system 415, user equipment 405, or components thereof) complete or execute the actions. However, it should be understood that in various embodiments, the various components of the environment 400 discussed above can execute instructions or perform actions, including those discussed below. Actions performed by a device can be considered as being performed by a processor, actuator, etc., associated with that device. Furthermore, it should be understood that in various embodiments, various steps can be added, omitted, and / or rearranged in any suitable manner.

[0105] Generally, what is discussed in this disclosure is understood to be any process or operation that can be implemented by a computer (e.g. Figure 2 The processes shown can all be performed by a computer system (e.g., Figure 4 The process, as described above, is executed by one or more processors in any system or device within the environment 400. A process or process step executed by one or more processors may also be referred to as an operation. One or more processors may be configured to execute such a process by accessing instructions (e.g., software or computer-readable code) that, when executed by one or more processors, cause the one or more processors to perform the process. These instructions may be stored in the memory of the computer system. The processor may be a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), or any suitable type of processing unit.

[0106] A computer system (such as a system or device that implements the processes or operations in the examples above) may include one or more computing devices, such as Figure 4 A computer system may contain one or more systems or devices. One or more processors of a computer system may be located in a single computing device or distributed across multiple computing devices. The memory of a computer system may include the respective memory of each of the multiple computing devices.

[0107] Figure 5 It can be configured to perform, according to exemplary embodiments of the present disclosure. Figure 2 A simplified functional block diagram of a computer 500 is provided for the method of using the device. For example, device 500 may include a central processing unit (CPU) 520. CPU 520 can be any type of processor device, including, for example, any type of dedicated or general-purpose microprocessor device. As those skilled in the art will understand, CPU 520 can also be a single processor in a multi-core / multi-processor system that operates independently, or in a cluster of computing devices operating in a cluster or server farm. CPU 520 can be connected to data communication infrastructure 510, such as a bus, message queue, network, or multi-core messaging scheme.

[0108] Device 500 may also include main memory 540, such as random access memory (RAM), and may also include secondary memory 530. Secondary memory 530 (e.g., read-only memory (ROM)) may be, for example, a hard disk drive or a removable storage drive. Such a removable storage drive may include, for example, a floppy disk drive, a magnetic tape drive, an optical disk drive, flash memory, etc. The removable storage drive in this example reads from and / or writes to the removable storage unit in a known manner. The removable storage unit may include floppy disks, magnetic tapes, optical disks, etc., which are read from and written to by the removable storage drive. As those skilled in the art will understand, such a removable storage unit typically includes a computer-usable storage medium in which computer software and / or data are stored.

[0109] In an alternative implementation, secondary memory 530 may include other similar means to allow computer programs or other instructions to be loaded into device 500. Examples of such means may include program cartridge memory and cartridge interfaces (such as those in video game devices), removable memory chips (such as EPROM or PROM) and associated slots, as well as other removable storage units and interfaces that allow software and data to be transferred from removable storage units to device 500.

[0110] Device 500 may also include a communication interface (“COM”) 560. Communication interface 560 allows the transfer of software and data between device 500 and external devices. Communication interface 560 may include a modem, network interface (e.g., Ethernet card), communication port, PCMCIA slot, and card, etc. The software and data transferred via communication interface 560 may be in the form of signals, which may be electronic signals, electromagnetic signals, optical signals, or other signals that can be received by communication interface 560. These signals may be provided to communication interface 560 via a communication path of device 500, which may be implemented using, for example, wires or cables, optical fibers, telephone lines, cellular telephone links, RF links, or other communication channels.

[0111] The hardware components, operating system, and programming language of such devices are conventional in nature and are presumed to be sufficiently familiar to those skilled in the art. Device 500 may also include input / output ports 550 for connecting input / output devices such as keyboards, mice, touchscreens, monitors, displays, etc. Of course, various server functions can be implemented in a distributed manner on many similar platforms to distribute the processing load. Alternatively, a server can be implemented by appropriately programming a computer hardware platform.

[0112] The programmatic aspect of this technology can be considered a "product" or "manufactured item," typically in the form of executable code and / or related data, carried on or embodied in a machine-readable medium. "Storage" type media includes any or all tangible memory of computers, processors, etc., or related modules thereof, such as various semiconductor memories, tape drives, disk drives, etc., which can provide non-transitory storage for software programming at any time. All or part of the software can sometimes communicate via the Internet or various other telecommunications networks. Such communication, for example, enables the loading of software from one computer or processor to another, such as from a management server or host computer of a mobile communication network to a server's computer platform and / or from a server to a mobile device. Therefore, another type of medium that can carry software elements includes light waves, radio waves, and electromagnetic waves, for example, on physical interfaces between local devices, through wired and optical ground networks, and on various air links. Physical elements carrying such waves (e.g., wired or wireless links, optical links, etc.) can also be considered as media carrying software. As used herein, unless limited to non-transitory tangible "storage" media, the term "readable medium" for a computer or machine refers to any medium that participates in providing instructions to a processor for execution.

[0113] References to any particular activity in this disclosure are for convenience only and are not intended to limit the scope of this disclosure. Those skilled in the art will recognize that the concepts upon which the disclosed devices and methods are based can be used for any suitable activity. This disclosure can be understood with reference to the following description and accompanying drawings, wherein like elements are indicated by like reference numerals.

[0114] Although the terminology used above is used in conjunction with the detailed description of certain specific examples of this disclosure, these terms may be interpreted in their broadest and most reasonable manner. In fact, some terms may even be emphasized above; however, any term intended to be interpreted in any limiting manner will be clearly and specifically defined in this Detailed Description section. The general description and detailed description are exemplary and illustrative only, and not intended to limit the features claimed.

[0115] It should be understood that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes combined in a single embodiment, drawing, or description thereof in order to simplify the disclosure and aid in understanding one or more of the various inventive aspects. However, this method of disclosure should not be construed as reflecting an intention that the claimed invention requires more features than expressly recited in each claim. Rather, as reflected in the following claims, the inventive aspect does not lie in all the features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into this detailed description, wherein each claim exists independently as a separate embodiment of the invention.

[0116] Furthermore, while some embodiments described herein include certain features but not others in other embodiments, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments, as will be understood by those skilled in the art. For example, any claimed embodiments may be used in any combination in the following claims.

[0117] Therefore, although certain embodiments have been described, those skilled in the art will recognize that other and further modifications can be made thereto without departing from the spirit of the invention, and it is intended that all such changes and modifications fall within the scope of the invention. For example, functions can be added or removed from the block diagrams, and the functions can be interchanged. Steps can be added or removed from the methods described within the scope of the invention.

[0118] The subject matter disclosed above should be considered illustrative, not restrictive, and the appended claims are intended to cover all such modifications, enhancements, and other implementations falling within the true spirit and scope of this disclosure. Therefore, to the fullest extent permitted by law, the scope of this disclosure should be determined by the broadest permissible interpretation of the following claims and their equivalents, and should not be limited or constrained by the foregoing detailed description. Although various embodiments of this disclosure have been described, it will be apparent to those skilled in the art that further embodiments are possible within the scope of this disclosure. Therefore, this disclosure is not limited except as provided in the appended claims and their equivalents.

Claims

1. A computer-implemented method for predicting the risk level of retained deciduous teeth (PDT) in one or more pets, the computer-implemented method comprising: One or more processors receive pet data corresponding to a pet from a user device, the pet data including one or more pet attributes; The one or more processors determine, based on the one or more pet attributes, a result value indicating the PDT attribute weight of each of the one or more pet attributes; The one or more processors analyze the resulting values ​​of each of the one or more pet attributes to determine the PDT risk level, the analysis including the use of a PDT risk level prediction algorithm; and The PDT risk level is displayed by the one or more processors on one or more user interfaces of the user equipment.

2. The computer-implemented method according to claim 1, wherein the one or more processors analyze the result value to determine the PDT risk level, further comprising: The processor receives one or more pet dental datasets of one or more similar pets from one or more data repositories, wherein the one or more similar pets have at least one attribute similar to the pet; and The PDT risk level is determined by the one or more processors using the PDT risk level prediction algorithm by comparing the result value corresponding to each of the one or more pet attributes with the one or more pet dental datasets.

3. The computer-implemented method according to claim 1, wherein, The pet data includes at least one of the following: an image of the pet, medical records corresponding to the pet, pet data input via the user device, or pet data stored in one or more pet data repositories.

4. The computer-implemented method according to claim 1, wherein, The PDT risk level includes low risk, medium risk, or high risk.

5. The computer-implemented method according to claim 1, wherein, The PDT risk level indicates the probability that the pet will be diagnosed with PDT.

6. The computer-implemented method according to claim 1, further comprising: The one or more processors determine one or more recommendations based on the PDT risk level; and The one or more recommendations are displayed on one or more user interfaces of the user device by the one or more processors.

7. The computer-implemented method according to claim 1, wherein, The one or more pet attributes include one or more of the following: pet breed type, pet head shape, pet weight and size category, pet weight status, pet physical condition, predicted pet size category, pet adult weight category, pet age, pet veterinary frequency, pet planned or most recent veterinary visit.

8. The computer-implemented method according to claim 7, wherein, The pet weight and size category includes at least one of the following: extra small, small, medium-small, medium-large, large, or extra large.

9. A computer system for predicting the risk level of retained deciduous teeth (PDT) in one or more pets, the computer system comprising: At least one memory for storing instructions; and At least one processor is configured to execute the instructions to perform operations including: Receive pet data corresponding to a pet from a user device, the pet data including one or more pet attributes; Based on the one or more pet attributes, determine the resulting value that indicates the PDT attribute weight of each of the one or more pet attributes; Analyze the resulting value of each of the one or more pet attributes to determine the PDT risk level, the analysis including using a PDT risk level prediction algorithm; and The PDT risk level is displayed on one or more user interfaces of the user equipment.

10. The computer system of claim 9, further comprising analyzing the result value to determine the PDT risk level: Receive one or more pet dental datasets of one or more similar pets from one or more data repositories, wherein the one or more similar pets have at least one attribute similar to the pet; and The PDT risk level is determined by comparing the result value corresponding to each of the one or more pet attributes with the one or more pet dental datasets using the PDT risk level prediction algorithm.

11. The computer system according to claim 9, wherein, The pet data includes at least one of the following: an image of the pet, medical records corresponding to the pet, pet data input via the user device, or pet data stored in one or more pet data repositories.

12. The computer system according to claim 9, wherein, The PDT risk level includes low risk, medium risk, or high risk.

13. The computer system according to claim 9, wherein, The PDT risk level indicates the probability that the pet will be diagnosed with PDT.

14. The computer system according to claim 9, wherein the instructions further include: One or more recommendations are determined based on the PDT risk level; and The one or more recommendations are displayed on one or more user interfaces of the user device.

15. The computer system according to claim 9, wherein, The one or more pet attributes include one or more of the following: pet breed type, pet head shape, pet weight and size category, pet weight status, pet physical condition, predicted pet size category, pet adult weight category, pet age, pet veterinary frequency, pet planned or most recent veterinary visit.

16. The computer system according to claim 15, wherein, The pet weight and size category includes at least one of the following: extra small, small, medium-small, medium-large, large, or extra large.

17. A non-transitory computer-readable medium storing instructions, said instructions, when executed by at least one processor, causing said at least one processor to perform operations for predicting the risk level of retained deciduous teeth (PDT) in one or more pets, said operations comprising: Receive pet data corresponding to a pet from a user device, the pet data including one or more pet attributes; Based on the one or more pet attributes, determine the resulting value that indicates the PDT attribute weight of each of the one or more pet attributes; Analyze the resulting value of each of the one or more pet attributes to determine the PDT risk level, the analysis including using a PDT risk level prediction algorithm; and The PDT risk level is displayed on one or more user interfaces of the user equipment.

18. The non-transitory computer-readable medium according to claim 17, wherein, The pet data includes at least one of the following: an image of the pet, medical records corresponding to the pet, pet data input via the user device, or pet data stored in one or more pet data repositories.

19. The non-transitory computer-readable medium according to claim 17, wherein, The PDT risk level includes low risk, medium risk, or high risk.

20. The non-transitory computer-readable medium of claim 17, further comprising analyzing the resulting value to determine the PDT risk level: Receive one or more pet dental datasets of one or more similar pets from one or more data repositories, wherein the one or more similar pets have at least one attribute similar to the pet; and The PDT risk level is determined by comparing the result value corresponding to each of the one or more pet attributes with the one or more pet dental datasets using the PDT risk level prediction algorithm.

21. A computer-implemented method for predicting the risk level of retained deciduous teeth (PDT) in one or more pets, the computer-implemented method comprising: One or more processors receive pet data corresponding to a pet from a user device, the pet data including one or more pet attributes; The one or more processors determine, based on the one or more pet attributes, a result value indicating the PDT attribute weight of each of the one or more pet attributes; The one or more processors analyze the resulting values ​​of each of the one or more pet attributes to determine the PDT risk level, the analysis including the use of a PDT risk level prediction algorithm; The one or more processors display the PDT risk level and corresponding interventions on one or more user interfaces of the user device, wherein the interventions include recommending the extraction of one or more teeth, recommending more frequent visits to medical professionals, or recommending oral health programs to reduce the risk of periodontal disease that may be caused by PDT. and The intervention is performed by the user on one or more of the pets.

Images