Predicting efficacy and improving skin care treatment outcome based on responder / non-responder information

Abstract

In some implementations, techniques for improving treatment outcomes are provided. A computing system measures at least one skin condition of a subject. The computing system receives a plurality of types of omics data of the subject. For each type of omics data, the computing system determines whether the subject belongs to at least one responder category using at least one classifier associated with the type of omics data. The computing system predicts a treatment outcome for a plurality of treatments of the at least one skin condition of the subject based on the at least one responder category. The computing system determines a skin care regimen based on the predicted treatment outcome.

Description

[0001] Cross-reference of related applications

[0002] This application claims priority to provisional application number 63 / 182664, filed April 30, 2021. It also claims priority to French patent application number 2108018, filed July 23, 2021. The entire disclosure of both applications is incorporated herein by reference for all purposes. Attached Figure Description

[0003] Many of the incidental advantages of the invention will become more readily apparent when taken in conjunction with the accompanying drawings and the following detailed description, in which:

[0004] Figure 1 This is a block diagram illustrating aspects of non-limiting exemplary embodiments of processing improvements to a computing system according to various aspects of this disclosure.

[0005] Figure 2 This is a flowchart illustrating a non-limiting example implementation of a method for improving the outcome of aging treatment according to various aspects of this disclosure.

[0006] Figure 3 This is a block diagram illustrating a non-limiting example embodiment of a computing device suitable for use as an embodiment of the present disclosure. Detailed Implementation

[0007] In some embodiments of this disclosure, systems, apparatuses, and / or methods are provided to predict the efficacy of various skin care treatments to improve treatment outcomes based on responder / non-responder information determined from omics data.

[0008] The techniques disclosed herein offer several technological improvements. As a non-limiting example, using classifiers for multiple types of omics data to automatically determine the responder category of a subject improves the accuracy of responder category determination, which is itself a technological improvement and further improves the treatment outcome for the subject because the treatment can be based on more accurate information. As another non-limiting example, considering responder categories that change over time also improves the accuracy of responder category determination, a technological improvement for similar reasons. As yet another non-limiting example, measuring clinical signs of aging after applying a skin care regimen and updating at least one classifier based on the measurements helps improve the performance of at least one classifier, thereby allowing for further improved responder category determination and providing further improved treatment outcomes.

[0009] Figure 1This is a block diagram illustrating aspects of a non-limiting example implementation of a processing improvement computing system according to various aspects of this disclosure. The processing improvement computing system 110 shown can be implemented by any computing device or collection of computing devices, including but not limited to desktop computing devices, laptop computing devices, mobile computing devices, server computing devices, computing devices of cloud computing systems, and / or combinations thereof. The processing improvement computing system 110 is configured to use a classifier to process omics data to determine an ideal skin care regimen for a subject to address clinical signs of aging, skin conditions including but not limited to acne or eczema, or any other skin care purpose.

[0010] As shown in the figure, the processing improvement computing system 110 includes one or more processors 102, one or more communication interfaces 104, a data storage device 108, and a computer-readable medium 106.

[0011] In some implementations, processor 102 may include any suitable type of general-purpose computer processor. In some implementations, processor 102 may include one or more dedicated computer processors or AI accelerators optimized for a specific computing task, including but not limited to graphics processing units (GPUs), vision processing units (VPTs), and tensor processing units (TPUs).

[0012] In some implementations, the communication interface 104 includes one or more hardware and / or software interfaces suitable for providing a communication link between components. The communication interface 104 may support one or more wired communication technologies (including but not limited to Ethernet, FireWire, and USB), one or more wireless communication technologies (including but not limited to Wi-Fi, WiMAX, Bluetooth, 2G, 3G, 4G, 5G, and LTE), and / or combinations thereof.

[0013] As shown in the figure, computer-readable medium 106 stores logic that responds to the execution of one or more processors 102, such that the processing improvement computing system 110 provides a responder engine 112 and a processing recommendation engine 114.

[0014] As used herein, “computer-readable medium” means a removable or non-removable device that implements any technology capable of storing information in a volatile or non-volatile manner that can be read by a processor of a computing device, including but not limited to: hard disk drives; flash memory; solid-state drives; random access memory (RAM); read-only memory (ROM); CD-ROM, DVD or other disc storage; magnetic cartridges; magnetic tape; and disk storage.

[0015] In some embodiments, responder engine 112 is configured to determine whether a given subject belongs to a responder category or a non-responder category across various components based on omics data obtained for that subject. In some embodiments, processing recommendation engine 114 is configured to determine a skincare regimen for a given subject based on the responder category determined by responder engine 112. Responder engine 112 may use omics data stored in data storage 108 and / or a classifier stored in data storage device 108. Processing recommendation engine 114 may also use information stored in data storage device 108 for its processing.

[0016] The following provides a further description of the configuration of each of these components.

[0017] As used herein, "engine" refers to the logic embodied in hardware or software instructions, which can be written in one or more programming languages, including but not limited to C, C++, C#, COBOL, and JAVA. TM The languages ​​used by engines include PHP, Perl, HTML, CSS, JavaScript, VBScript, ASPX, Go, and Python. Engines can be compiled into executable programs or written in interpreted programming languages. Software engines can be invoked from other engines or from themselves. Generally, the term "engine" as used herein refers to a logical module that can be combined with other engines or divided into sub-engines. Engines can be implemented using logic stored in any type of computer-readable medium or computer storage device, and can be stored and executed by one or more general-purpose computers, resulting in a dedicated computer configured to provide the engine or its functionality. These engines can be implemented using logic programmed into application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other hardware devices.

[0018] As used herein, "data storage device" refers to any suitable device configured to store data accessible to computing devices. One example of a data storage device is a highly reliable, high-speed relational database management system (DBMS) that runs on one or more computing devices and is accessible via a high-speed network. Another example of a data storage device is a key-value store. However, any other suitable storage technology and / or device capable of providing stored data quickly and reliably in response to queries may be used, and the computing device may be locally accessible rather than via a network, or may be provided as a cloud-based service. A data storage device may also include data stored in an organized manner on computer-readable storage media such as hard disk drives, flash memory, RAM, ROM, or any other type of computer-readable storage media. Those skilled in the art will recognize that the individual data storage devices described herein may be combined into a single data storage device, and / or the single data storage device described herein may be divided into multiple data storage devices without departing from the scope of this disclosure.

[0019] Figure 2 This is a flowchart illustrating a non-limiting example implementation of a method for improving the outcome of aging treatment according to various aspects of this disclosure.

[0020] At box 202, the computational system measures at least one clinical sign of aging in the subject. Clinical signs of aging can be any type of age-related skin condition change that is clinically observable, including but not limited to shiny skin, rough skin, uneven skin tone, wrinkles around the eyes, photoaging, loss of elasticity, and enlarged pores. The computational system may use any suitable technique to measure at least one clinical sign of aging, including but not limited to computer visual analysis of images or 3D scans of the subject, providing questionnaires completed by the subject, and providing questionnaires completed by the clinician observing the subject.

[0021] At box 204, the computing system receives various types of omics data from the subjects. The computing system itself can collect omics data, can receive omics data from another device that samples omics data from the subjects, or can receive omics data as input from the subjects or clinicians. Any type of omics data reflecting useful information about the subjects can be used, including but not limited to:

[0022] • Genome data

[0023] Analysis of the genome structure of the entire organism

[0024] o can be collected using next-generation sequencing technology

[0025] • Exome data

[0026] The exome is the protein-coding content of the genetic code, and it is the part of the genome formed by exons. The exome accounts for 1-2% of the genome.

[0027] o Solution-based: In solution-based whole exome sequencing (WES), DNA samples are fragmented and selectively hybridized with target regions in the genome using biotinylated oligonucleotide probes (decoys).

[0028] o Array-based: The array-based method is similar, except that the probe is combined with a high-density microarray.

[0029] Transcriptome data

[0030] Analysis of all transcripts produced at any given moment in an individual, disease state, or cell can tell us which genes are turned on or off.

[0031] o can be collected using cDNA microarrays or RNA-seq technology

[0032] o reflects the different transcription rates (how a specific organism, tissue, or cell type synthesizes RNA molecules at a given time).

[0033] Epigenome data

[0034] Chemical markers on DNA regulate whether genes are "on" or "off".

[0035] • Proteomics data

[0036] Proteins produced by a specific genome

[0037] Metabolomics data

[0038] metabolites produced by a single organism

[0039] o can be obtained using NMR spectroscopy.

[0040] Microbiome data

[0041] o Microorganisms (and their genes) that live in specific environments (such as the gut, skin)

[0042] Metagenomic data

[0043] Genes of microorganisms under specific environments

[0044] Hormone group data

[0045] This may include estrogen, progesterone, testosterone, cortisol, melatonin, serotonin, growth hormone, leptin, ghrelin, and insulin.

[0046] o can be measured through blood tests or saliva tests.

[0047] Hormone levels fluctuate over time and indicate points in the menstrual cycle, such as the menstrual cycle.

[0048] At box 206, for each type of omics data, the computational system uses at least one classifier associated with the type of omics data to determine whether the subject belongs to at least one responder category. A responder category indicates whether a subject will respond to a specific skincare product ingredient associated with that responder category. For example, responder categories may include, but are not limited to, retinol responder categories, Proxylane responder categories, vitamin C responder categories, hyaluronic acid responder categories, endosomalin responder categories, and lipohydroxy acid (LHA) responder categories.

[0049] In some implementations, a separate classifier can be trained for each type of omics data and each responder category. In some implementations, a single classifier can be trained to receive multiple types of omics data to determine a single responder category. In some implementations, a single classifier can be trained for each type of omics data, but classification for multiple responder categories can be provided. Any suitable type or combination of types of classifiers can be used, including but not limited to decision trees, Naive Bayes classifiers, k-nearest neighbor classifiers, support vector machines, and artificial neural networks. Any suitable technique can be used to train the classifier, including but not limited to using subjects with known baseline responder category information to determine a set of labeled training data, and using labeled training data to train the classifier using techniques including but not limited to gradient descent.

[0050] In addition to the information described above, other information may be used to determine responder categories. For example, in some implementations, indicators of time-dependent modifications of DNA methylation (DNAm) are used to estimate the molecular age of human tissues relative to their chronological age. See, for example, Boroni, M., Zonari, A., Reis de Oliveira, C. et al. “Highly accurate skin-specific methylome analysis algorithm as a platform to screen and validate therapyeutics for healthy aging,” Clin Epigenet 12, 105 (2020); available at https: / / doi.org / 10.1186 / s13148-020-00899-1; incorporated herein by reference in its entirety. As another example, in some implementations, an indication of genetic susceptibility to UV damage is used to classify an individual as a responder to sun protection (see, e.g., Lear JT et al., “Detoxifying Enzyme Genotypes and Susceptibility to Cutaneous Malignancy,” Br J Dermatol. 2000 Jan; 142(1):8-15 doi:10.1046 / j.1365-2133.2000.03339.x.PMID:10651688; available at https: / / pubmed.ncbi.nlm.nih.gov / 10651688 / (describing how polymorphisms in detoxification enzyme genes are important in determining susceptibility to skin cancer, incorporated herein by reference in its entirety). As another example, in some implementations, one or more genomic, transcriptomic, proteomic, or metabolomic biomarkers of psoriasis are used to classify an individual as a responder to certain skin care products (see, e.g., Jiang S et al.). al., “Biomarkers of An Autoimmune SkinDisease--Psoriasis.” Genomics Proteomics Bioinformatics. 2015; 13(4):224-233; doi:10.1016 / j.gpb.2015.04.002; incorporated herein by reference in its entirety).

[0051] At box 208, the computational system predicts treatment outcomes for at least one clinical sign of aging in subjects receiving multiple treatments based on at least one responder category. In some embodiments, the computational system may be configured with information about the effects of various skincare treatments on different responder categories. For example, the computational system may be configured to know how a given skincare treatment affects a given clinical sign of aging in subjects within a responder category that is not a responder category that is receiving a given skincare treatment.

[0052] At box 210, the computational system determines a skin care regimen based on the predicted treatment outcome. For example, the computational system may identify one or more products having ingredients identified in box 208 to improve the subject's treatment outcome. In some embodiments, the computational system may provide the subject or clinician with instructions on a skin care regimen to recommend products to be used. In some embodiments, the computational system may provide the device with instructions on a skin care regimen to formulate a customized skin care product containing ingredients identified as improving the treatment outcome. In some embodiments, the computational system may provide visualizations of the effects of the illustrated skin care regimen based on the determination of the subject's responder group and / or other characteristics of the subject.

[0053] At optional box 212, the computational system measures at least one clinical sign of aging in the subject after applying the skin care regimen. The computational system can use a technique similar to that used in box 202 to measure at least one clinical sign of aging. At optional box 214, the computational system updates at least one classifier based on the difference in measurements of at least one clinical sign of aging in the subject after applying the skin care regimen. For example, the difference in measurements of at least one clinical sign of aging can be used to determine a baseline true value for whether the subject belongs to the responder or non-responder category for the ingredients used in the skin care regimen (e.g., if there is improvement, the baseline true value is that the subject belongs to the responder category; if there is no improvement or the improvement is less than expected, the baseline true value is that the subject belongs to the non-responder category). This baseline true value can then be used with the subject's omics data to retrain an appropriate classifier. Optional boxes 212 and 214 are shown as optional because in some implementations, this data collection and classifier retraining may not be performed.

[0054] While the discussion of the above method 200 primarily focuses on the treatment of clinical signs affecting aging, in some implementations, treatments for other conditions may be considered. For example, responder categories can be used to determine skin care protocols to address medical conditions including, but not limited to, acne or eczema. As another example, responder categories can be used to determine skin care protocols to address skin tone management.

[0055] Figure 3This is a block diagram illustrating various aspects of an exemplary computing device 300 suitable for use as a computing device according to this disclosure. While many different types of computing devices have been discussed above, the exemplary computing device 300 describes various elements common to many different types of computing devices. Figure 3 This description is made with reference to a computing device implemented as a device on a network, and the following description applies to servers, personal computers, mobile phones, smartphones, tablet computers, embedded computing devices, and other devices that can be used to implement portions of the embodiments of this disclosure. Some embodiments of the computing device may be implemented in or may include application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other custom devices. Furthermore, those skilled in the art and others will recognize that computing device 300 may be any of any number of currently available or under-development devices.

[0056] In its most basic configuration, computing device 300 includes at least one processor 302 and system memory 310 connected via a communication bus 308. Depending on the exact configuration and type of the device, system memory 310 may be volatile or non-volatile memory, such as read-only memory (“ROM”), random access memory (“RAM”), EEPROM, flash memory, or similar memory technologies. Those skilled in the art and others will recognize that system memory 310 typically stores data and / or program modules that are readily accessible and / or currently being operated by processor 302. In this respect, processor 302 can act as the computing center of computing device 300 by supporting instruction execution.

[0057] like Figure 3 As further shown, computing device 300 may include network interface 306, which includes one or more components for communicating with other devices via a network. Embodiments of this disclosure may use public network protocols to access basic services that utilize network interface 306 for communication. Network interface 306 may also include a wireless network interface configured to communicate via one or more wireless communication protocols, such as Wi-Fi, 2G, 3G, LTE, WiMAX, Bluetooth, Bluetooth Low Energy, etc. As will be understood by those skilled in the art, Figure 3 The network interface 306 shown may represent one or more wireless interfaces or physical communication interfaces described and shown above with respect to specific components of computing device 300.

[0058] exist Figure 3 In the exemplary embodiment shown, computing device 300 also includes storage medium 304. However, a computing device that does not include means for persistently storing data to a local storage medium can be used to access the service. Therefore, Figure 3The storage medium 304 depicted is indicated by a dashed line to show that the storage medium 304 is optional. In any case, the storage medium 304 may be volatile or non-volatile, removable or non-removable, and may be implemented using any technology capable of storing information, such as, but not limited to, hard disk drives, solid-state drives, CD-ROMs, DVDs or other disc storage devices, cartridges, magnetic tapes, disk storage devices, etc.

[0059] Suitable implementations of a computing device including processor 302, system memory 310, communication bus 308, storage medium 304, and network interface 306 are known and commercially available. This is for illustrative purposes and because it is not essential for understanding the claimed subject matter. Figure 3 Many typical components of a computing device are not shown. In this regard, computing device 300 may include input devices such as a keyboard, keypad, mouse, microphone, touch input device, touchscreen, tablet, etc. Such input devices can be coupled to computing device 300 via wired or wireless connections, including RF, infrared, serial, parallel, Bluetooth, Bluetooth Low Energy, USB, or other suitable connection protocols using wireless or physical connections. Similarly, computing device 300 may also include output devices such as a display, speaker, printer, etc. Since these devices are well known in the art, they will not be further shown or described herein.

[0060] While exemplary embodiments have been shown and described, it should be understood that various changes may be made therein without departing from the spirit and scope of the invention.

Claims

1. A computer-implemented method for improving processing results, the method comprising: The subject's skin condition is measured by a computing system to obtain a first measurement value; The computing system receives multiple types of omics data from the subject, wherein the multiple types of omics data include two or more of the following: genomic data, exome data, transcriptome data, epigenome data, proteome data, metabolome data, and microbiome data; For each type of omics data, the computing system uses at least one classifier associated with the type of omics data to determine whether the subject belongs to at least one responder category by providing the omics data of that type as input to the at least one classifier, wherein the responder category indicates whether the subject is predicted to respond to a specific skin care product ingredient associated with the responder category; The computing system uses stored data to predict treatment outcomes for at least one skin condition of the subject for multiple treatments, based on the at least one responder category, the stored data indicating how a given skin treatment will affect a given clinical sign of aging for a subject in the at least one responder category; The calculation system determines a skin care plan based on the predicted processing results; The calculation system measures at least one skin condition of the subject after applying the skin care regimen to obtain a second measurement value; as well as The computing system updates the at least one classifier based on the difference between the first measurement and the second measurement.

2. The computer-implemented method of claim 1, wherein the at least one responder category includes at least one of the following: Retinol responder categories; Bosein responder categories; Vitamin C responder categories; Hyaluronic acid responder categories; Endolysin responder categories; and Lipid hydroxy acid (LHA) responder category.

3. The computer-implemented method of claim 1, wherein at least one responder category of the subject changes over time.

4. The computer-implemented method of claim 3, wherein at least one responder category of the subject varies over time based on a date in the subject's physiological cycle.

5. The computer-implemented method according to claim 4, wherein the subject's physiological cycle is a menstrual cycle.

6. The computer-implemented method of claim 1, wherein the at least one skin condition includes at least one of clinical signs of aging, medical condition, and skin tone.

7. A non-transitory computer-readable medium having computer-executable instructions stored thereon, the computer-executable instructions causing the computing system to perform the method according to any one of claims 1 to 6 in response to execution by one or more processors of a computing system.

8. A computing system, comprising: The responder engine includes computational circuitry configured for the following: Measure at least one skin condition of the subject to obtain a first measurement value; Receive multiple types of omics data from the subjects, wherein the multiple types of omics data include two or more of the following: genomic data, exome data, transcriptome data, epigenome data, proteome data, metabolome data, and microbiome data; and Using a classifier associated with at least one responder category, by providing the classifier with the various types of omics data as input, it is determined whether the subject belongs to the at least one responder category, wherein the responder category indicates whether the subject is predicted to respond to a specific skin care product ingredient associated with the responder category; The recommendation engine includes computational circuitry configured for the following: Based on the at least one responder category, stored data is used to predict treatment outcomes for at least one skin condition of the subject in multiple treatments, the stored data indicating how a given skin treatment will affect a given clinical sign of aging for a subject in the at least one responder category; Skin care plans are determined based on the predicted treatment results; After applying the skin care regimen, the subject's at least one skin condition is measured to obtain a second measurement. as well as The classifier is updated based on the difference between the first measurement and the second measurement.

9. The computing system of claim 8, wherein the at least one responder category includes at least one of the following: Retinol responder categories; Bosein responder categories; Vitamin C responder categories; Hyaluronic acid responder categories; Endolysin responder categories; and Lipid hydroxy acid (LHA) responder category.

10. The computing system of claim 8, wherein at least one responder category of the subject changes over time.

11. The computing system of claim 10, wherein at least one responder category of the subject varies over time based on the date in the subject's physiological cycle.

12. The computing system according to claim 11, wherein the subject's physiological cycle is a menstrual cycle.

13. The computing system of claim 11, wherein the at least one skin condition includes at least one of clinical signs of aging, medical condition, and skin tone.

Images