A digital medical guide to treating and managing skin conditions

Abstract

A digital medical guide for managing skin diseases (e.g., atopic dermatitis, psoriasis) may include a patient wearable device that passively collects patient data, a patient user device with a healthcare application for the patient to input health-related data, a central analysis for flare prediction and disease progression tracking, and a physician dashboard. For flare prediction, a predictive tool may be trained using a ground truth of recorded flare occurrences to predict whether a trained model may cause a flare or not. Upon predicting a possible flare, an alert notification may be generated, for example, for a physician and / or a patient. Furthermore, a baseline may be established based on data passively collected from the wearable and data actively collected from the patient user device. Continuously collected data may be compared against the established baseline. Upon detection of a significant deviation, an alert may be sent to the patient and / or physician.

Description

[Technical field]

[0001] Related Applications This application claims priority to U.S. Provisional Application No. 63 / 291,798, filed December 20, 2021. This application also claims priority to U.S. Provisional Application No. 63 / 043,108, filed June 23, 2020, and U.S. Provisional Application No. 63.213,592, filed June 22, 2021, PCT / US2021 / 038699 (WO 2021 / 262857), filed June 23, 2021, each of which is incorporated herein by reference in its entirety.

[0002] The subject matter presented herein is directed to systems and methods for monitoring skin conditions, particularly for monitoring scratching caused by skin conditions and for predicting the likelihood of redness. [Background technology]

[0003] Chronic relapsing and remitting skin conditions / diseases such as atopic dermatitis and psoriasis are characterized by flares, which are significant exacerbations of the disease accompanied by extreme itching, increased scratching, skin lesions, reduced sleep, and other associated physical, mental, and social discomforts. Therefore, managing flares is an essential part of successfully managing these skin diseases.

[0004] Managing flares is traditionally reactive and therefore remains inadequate. Patients may experience flares and seek treatment, which is generally not immediately available and often not easy. Meanwhile, flares, in addition to causing the general discomfort of itching and the physical act of scratching, may result in highly visible skin lesions, thus incurring a kind of social stigma. Thus, as flares develop and progress, the quality of life of patients may be significantly reduced. In addition, skin diseases have been found to be associated with psychological problems, depression, anxiety, self-harming behaviors, obesity, food allergies, asthma, and allergic rhinitis / rhinoconjunctivitis, all of which may be exacerbated by flares. Thus, reactive medical interventions after flares, where patients are at potential risk of developing and / or worsening these and other conditions, are inadequate.

[0005] As well as managing redness, traditional skin disease management is also inadequate in managing other associated uncertainties. Because the disease relapses and goes into remission, patients have difficulty monitoring and reporting progress given the dynamic nature of the disease. Patient reports to physicians can be inaccurate and prone to different human biases, thus creating extra challenges for physicians in determining the minimum required drug dosage. Uncertainties persist even after a drug is prescribed. Patients may discontinue medication if they are not provided with adequate support to manage side effects (e.g., nausea), even if the drug provides efficacy with continued use. Remission may also cause patients to stop taking the drug. Physicians tend to manage these uncertainties in clinical interviews with patients, but these interviews are, however, very infrequent, can be influenced by human factors, and may involve inaccurate information exchange. Other associated symptoms such as anxiety, insomnia, and fatigue may be present, which cannot be adequately detected and resolved by physicians in these clinical interviews and are dependent on the patient's memory. These symptoms may require consistent interventions to encourage better behavioral choices in exercise, nutrition, mindfulness, etc. Patients may also need to be provided with relevant clinical information about their disease in order to understand and manage it. The use of these scattered clinical interviews has been inadequate for disease tracking, determining the minimum dosage required, managing side effects, promoting medication adherence, providing information about the disease, and recommending better disease management behaviors. Summary of the Invention [Problem to be solved by the invention]

[0006] In some embodiments, the present disclosure relates to a digital medical guide for treating and managing skin diseases (e.g., atopic dermatitis, psoriasis, etc.) that may include patient wearable and / or invisible devices (e.g., non-wearable sensors) that passively collect patient movement and / or biometric data, a patient user device with a healthcare application for the patient to input health-related data, central analytics for flare prediction and disease progression tracking, and a physician dashboard. For flare prediction / assessment, a predictive tool may be trained using a supervised training approach using ground truth of recorded flare occurrences such that the trained model predicts whether the currently observed scratching event and other contextual data may be likely to cause a flare. In response to a prediction of a possible flare, one or more alert notifications may be generated, for example, for the physician to increase the dosage and / or for the patient to take an increased dosage. When managing atopic dermatitis, a baseline may be established based on data passively collected from digital technologies (e.g., patient wearable and / or invisible devices) and data actively collected from the patient. These acquired data may be compared against established baselines to assess any deviations. In response to detecting significant deviations in the patient's condition, an alert may be sent to the patient and / or physician (and in some embodiments, to a scientist for further study). Furthermore, a two-way connection may be established between the patient and physician through the healthcare application and physician dashboard, respectively. [Means for solving the problem]

[0007] In one embodiment, a computer-implemented method may be provided, which may include the steps of: acquiring, by a server, a scratch dataset, the scratch dataset including data records of corresponding scratch events of a patient population suffering from a skin disease; acquiring, by the server, a contextual dataset including data records of additional information associated with the corresponding scratch events; training, by the server, a predictive model using a supervised training approach based on the scratch dataset of the contextual dataset; receiving, by the server, periodic data indicating occurrence of scratch events over a period of time of a particular patient suffering from a skin disease; feeding, by the server, the received periodic data to the trained predictive model; and transmitting, by the server, an alert notification to a user device of the particular patient in response to the predictive model outputting a likelihood of redness.

[0008] In another embodiment, another computer-implemented method may be presented. The method may include: receiving, by a server, health care data periodically for a predetermined time period from a health care application installed on a user device of a patient suffering from a skin disease; establishing, by the server, a baseline health behavior based on the health care data for the predetermined time period; receiving, by the server, new health care data from the health care application installed on the user device; determining, by the server, whether the new health care data has a significant deviation from the baseline health behavior; and triggering an alert notification to a physician dashboard in response to the server determining the significant deviation from the baseline health behavior.

[0009] In yet another embodiment, yet another computer-implemented method may be provided. The method may include: continuously receiving, by a computing device, health care data of a patient having a skin disease from a wearable computing device worn by the patient; periodically prompting, by the computing device, the patient to input additional health care data into an interface generated by a health care application installed on the computing device; transmitting, by the computing device, the health care data and the additional health care data to a remote server; receiving, by the computing device, an alert notification from the remote server in response to the remote server determining a possible deterioration of the skin disease; and generating, by the computing device, a push notification indicating an action for the patient in response to receiving the alert notification.

[0010] Other objects and advantages of the present disclosure will become apparent to those of ordinary skill in the art upon reading the following detailed description of exemplary embodiments and the appended claims, in conjunction with the accompanying drawings, where like reference numerals are used to designate like elements. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1A is a graph illustrating different types of disease progression of atopic dermatitis, an example of a skin disease. FIG. 1B is a graph illustrating different types of disease progression of atopic dermatitis, an example of a skin disease. FIG. 1C is a graph illustrating different types of disease progression of atopic dermatitis, an example of a skin disease. FIG. 1D is a graph illustrating different types of disease progression of atopic dermatitis, an example of a skin disease. FIG. 1E is a graph illustrating different types of disease progression of atopic dermatitis, an example of a skin disease. FIG. 1F is a graph illustrating different types of disease progression of atopic dermatitis, an example of a skin disease. [Diagram 2] 1 is a graph illustrating a prior art clinical evaluation of atopic dermatitis. [Diagram 3] 1 is a graph illustrating the prior art reactive management of atopic dermatitis flares. [Figure 4] 1 is a graph illustrating the preventative management of skin conditions, such as atopic dermatitis, that may be achieved using one or more embodiments of the present disclosure. [Diagram 5] FIG. 1 is a block diagram of an illustrative operating environment for using one or more embodiments of the present disclosure. [Figure 6] FIG. 1 is a block diagram of the architecture of an illustrative computing device that may perform one or more functions in accordance with some embodiments of the present disclosure. [Figure 7] 7 is a block diagram of an exemplary architecture of an operating environment 700 in which one or more embodiments disclosed herein may be used. [Figure 8] FIG. 1 is a flow diagram of an illustrative method for training a predictive model for flare prediction, according to some embodiments of the present disclosure. [Figure 9] FIG. 1 is a flow diagram of an illustrative method for developing a predictive model for flare prediction, according to some embodiments of the present disclosure. [Figure 10] FIG. 1 is a flow diagram of an illustrative method for generating an analytical model of baseline disease behavior of a skin disease, according to some embodiments of the present disclosure. [Figure 11] FIG. 1 is a flow diagram of an illustrative method for deploying an analytical model to determine whether currently observed behavior deviates significantly from baseline disease behavior, in accordance with some embodiments of the present disclosure. [Figure 12A] FIG. 1 illustrates an illustrative patient interface according to some embodiments of the present disclosure. [Figure 12B] FIG. 1 illustrates an illustrative patient interface according to some embodiments of the present disclosure. [Figure 12C] FIG. 1 illustrates an illustrative patient interface according to some embodiments of the present disclosure. [Figure 12D] FIG. 1 illustrates an illustrative patient interface according to some embodiments of the present disclosure. [Figure 13A] FIG. 1 illustrates an exemplary physician interface, according to some embodiments of the present disclosure. [Figure 13B] FIG. 1 illustrates an exemplary physician interface, according to some embodiments of the present disclosure. [Figure 13C] FIG. 1 illustrates an exemplary physician interface, according to some embodiments of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] It should be understood that the figures are for purposes of illustrating example embodiments and that the disclosure is not limited to the arrangements and instrumentality shown in the drawings, in which like reference numbers identify at least generally similar elements.

[0013] Skin diseases / conditions (e.g., atopic dermatitis, psoriasis, etc.) are characterized by years of flares and exacerbations. There are other uncertainties associated with skin diseases, the diseases are unstable, they cause the skin to appear clinically normal yet immunologically abnormal, and their long-term management may require patients to adhere to strict treatment regimens and make better behavioral choices. There is also social stigma, especially due to the highly visible lesions formed by the flares. The diseases are also associated with psychosocial problems, depression, anxiety, self-injury behaviors, obesity, food allergies, asthma, and allergic rhinitis / rhinoconjunctivitis.

[0014] Conventional methods for managing skin diseases remain inadequate. For example, flares are generally transient, and managing these flares has traditionally been reactive. For example, patients may visit a doctor after a flare, and the doctor may prescribe medication (e.g., higher doses of existing and / or new medications). This reactive management carries the risk of further flare-ups and aggravating other conditions, such as psychosocial problems, depression, and anxiety. Therefore, it is desirable to have a method for predictively managing flares proactively.

[0015] Since skin diseases are generally dynamic, their progression may have ups and downs. Thus, patients may have difficulty tracking the progression and may not be able to recall the details during clinical encounters, or it may have already resolved by the time the patient is able to interact with the physician. In other words, physicians may not get a complete picture of disease progression during these encounters and therefore struggle to prescribe the minimum required dose of a prescription (e.g., abrocitinib for atopic dermatitis). Furthermore, the prescription may have unpleasant side effects (e.g., nausea), and patients may discontinue treatment if proper counseling is not provided to manage these side effects. Remission may also cause patients to stop taking the medication. Furthermore, without a complete picture of the patient's response to the medication, physicians may be concerned about the long-term safety of the prescribed medication. Additionally, skin diseases may be associated with other ailments, such as anxiety, sleep, and fatigue, that may not be addressed by physicians generally focusing on solving the visible problem (i.e., the skin disease itself) during clinical encounters. These other diseases may need to be addressed along with the skin condition, but they may not become apparent during the few clinical encounters without continuous monitoring and ongoing dialogue with the patient. Thus, traditional methods of reactive clinical encounters, which are more focused on solving visible and immediate problems, are inadequate in several aspects.

[0016] The embodiments disclosed herein seek to predict and preemptively avoid flare-ups of skin diseases. The embodiments described herein may further enable continuous monitoring of the patient: collecting data on the patient's condition and maintaining a continuous patient-physician dialogue. To that end, an exemplary operating environment may include devices (e.g., wearable devices, invisible devices) that may passively (e.g., without active action by the patient) collect patient data, such as hand movements, and healthcare applications that may actively encourage the patient to input disease information (e.g., how the patient was feeling at a particular point in time). Data from other sensors (e.g., blood pressure monitors) and contextual data (e.g., EHR data, weather data) may also be received. A back-end predictive model may use the collected data to determine the likelihood of flare-ups. In some embodiments, flare-up prediction may be based on using scratch detection technology disclosed in PCT / US2021 / 038699 (International Publication No. WO2021 / 262857), which is incorporated herein by reference in its entirety. The prediction of a possible flare may trigger one or more alert notifications: one to the patient, indicating that a flare is imminent and that a remedial action may be taken, and / or one to the physician, indicating that the particular patient is prone to an imminent flare. Based on these alerts, the patient and physician may initiate synchronous or asynchronous communication and decide on a remedial action accordingly (e.g., increasing the dosage of a prescribed medication such as abrocitinib for atopic dermatitis). The communication between the physician and the patient may also be used for educational purposes, and the physician may also advise the patient on how to mitigate future flare-ups, how to make healthy behavioral choices about food, exercise, etc.

[0017] Alternatively or additionally, the exemplary operating environment may also be used for skin disease progression tracking. For example, using a patient-facing healthcare application, the patient may periodically input healthcare data, such as side effects, redness, and / or any other quality of life metrics. The wearable (and / or invisible) may also passively capture patient data, such as movement and exercise data. In response, the patient may periodically receive educational materials (e.g., audio, video, text, in-person live counseling) on ​​how to manage the condition and make healthy behavioral choices. The continuously collected time series data (both passive and active data, and / or any other contextual data) may be used to establish a statistical analysis model (and / or train a machine learning model) that may indicate baseline disease behavior. The baseline disease behavior may indicate normal levels of scratching events, stress, anxiety, and / or any other health or quality of life metrics. New incoming data may be compared to the analysis model to determine whether the new data indicates a significant deviation from the baseline, e.g., whether side effects are particularly prominent. In such cases, an alert notification may be generated for the patient and / or physician. Based on the alert notification, the patient and physician may initiate synchronous or asynchronous communication to determine treatment. The communication may also be used to continually educate and advise the patient for better disease management and to improve the quality of life.

[0018] Thus, compared to traditional reactive and sporadic clinical encounters with suboptimal information exchange, the embodiments disclosed herein may enable continuous and preventative patient monitoring. Back-end analytics may use continuously collected data to predict adverse situations (e.g., impending flares) or detect exacerbations (e.g., worsening side effect symptoms). Such issues may be immediately brought to attention and addressed through alert notifications sent to the patient and physician. Such monitoring and prediction / detection of disease exacerbations may help physicians determine the minimum dosage required. Moreover, the two-way connection between patient and physician may enable physicians to continually educate and advise the patient.

[0019] In general, the embodiments disclosed herein may provide more context and understanding of skin diseases, thus enabling better treatment. Furthermore, patients may have a sense of "disease ownership" since they are active participants in their treatment. Physicians may have the full picture based on continuously collected data. Early treatment options may be explored and used based on collected data. Treatment may be continuously and dynamically adjusted (e.g., by adjusting drug dosage). Safety of treatment may be increased since large amounts and / or continuous administration is not required. Furthermore, environmental influences on disease progression may be detected and mitigated.

[0020] 1A-1F show graphs (modified from Jonathan Silverberg, "Atopic Dermatitis: Clinical Features, Patient Type, Burden, and Epidemiology") illustrating disease progression of different types of atopic dermatitis, an example of a skin disease. In particular, FIG. 1A shows a graph 100a illustrating good control of atopic dermatitis. As shown, disease activity has remained consistently lower over the course of a year, and flares are absent. FIG. 1B shows a graph 100b illustrating atopic dermatitis with frequent moderate flares. As shown, five moderate flares 102b1, 102b2, 102b3, 102b4, and 102b5 have been observed over the course of a year. FIG. 1C shows a graph 100c illustrating atopic dermatitis with seasonal severe flares. As shown, a severe flare 102c is observed at the beginning of the year. FIG. 1D shows a graph 100d illustrating a moderate atopic dermatitis with several severe flare episodes. As shown, the baseline of the atopic dermatitis is moderate, but three severe flare episodes 102d1, 102d2, and 102d3 are observed over the course of a year. FIG. 1E shows a graph 100e illustrating a severe case of atopic dermatitis with significantly higher disease activity. FIG. 1F shows a graph 100f illustrating another severe case of atopic dermatitis, also with significantly higher disease activity.

[0021] FIG. 2 shows a graph 200 illustrating a prior art clinical evaluation of atopic dermatitis. As shown, atopic dermatitis may vary between subclinical inflammation 208 and clinical inflammation 206. Subclinical inflammation 208 may not generally be observed by clinical means (e.g., naked eye observation), whereas clinical inflammation 206 may be observed by clinical means. Clinical inflammation 206 shows two peaks 202 and 204 that may correspond to redness. In graph 200, two clinical evaluation points 210 and 212 are shown. However, both clinical evaluation points 210 and 212 are at completely different time points, and therefore, only relate to these point observations. In particular, clinical evaluation point 210 may detect a possibly severe inflammation because clinical evaluation point 210 is close to the first peak 202. On the other hand, clinical evaluation point 212 may not detect any inflammation because the existing inflammation is subclinical inflammation 208 where no observable inflammation exists. In other words, clinical endpoints 210 and 212 may not detect long-term trends in disease progression, but may simply detect short-term visible pathology. Thus, current clinical interviews are essentially aimed at attempting to detect and address atopic dermatitis in the short term, and do not provide optimal long-term management of the disease.

[0022] FIG. 3 shows a graph 300 (modified from Thomas Bieber, "Atopic Dermatitis," Ann Dermatol. May 2010, 22(2):125-137) illustrating prior art reactive management of atopic dermatitis flares. As shown, atopic dermatitis, ranging from subclinical inflammation 308 and clinically detectable inflammation 306, has two flares 302 and 304. However, clinical interventions 310, 312, 314, and 316 are merely reactive to the flares 302 and 304. Notably, patients have sought clinical help after the flares 302 and 304 have been observed. Such reactive management is insufficient at least because the patient must first experience the physical, mental, and social discomfort of having the flares 302 and 304. To avoid these and other discomforts, it is desirable to predict having a flare and proactively avoid it.

[0023] FIG. 4 shows a graph 400 (modified from Thomas Bieber, “Atopic Dermatitis,” Ann Dermatol. May 2010, 22(2):125-137) illustrating preventative management of a skin condition (e.g., atopic dermatitis) that may be achieved with one or more embodiments of the present disclosure. As shown, a first clinical intervention 410 begins before a moderate flare 402. In other words, the flare 402 may have been predicted and the clinical intervention 410 may have reduced the severity of the flare 402. At the peak of the flare 402 there is another clinical intervention 412 for its management. Another clinical intervention 414 is also aimed at managing the flare 402. Subsequent clinical interviews 416 and 418 are aimed at preventatively avoiding the flare.

[0024] However, current sporadic reactive clinical consultations are inadequate for such preventative management of flares. Clinical consultations are essentially aimed at short-term treatment to subside existing flares. Because physicians traditionally do not have access to longitudinal data accumulated over time, physicians may not be able to optimally manage atopic dermatitis (and generally any other skin disease) over the long term.

[0025] FIG. 5 shows a block diagram of an exemplary operating environment 500 for using one or more embodiments of the present disclosure. It should be understood that this and other arrangements described herein are set forth merely as examples. Other arrangements and elements (e.g., machines, interfaces, functions, sequences, and groups of functions) may be used in addition to or instead of those shown in FIG. 5 and other figures, and some elements may be omitted entirely for clarity. Furthermore, many of the elements described herein are functional entities that may be implemented as separate or distributed components, or in conjunction with other components, and in any suitable combination or location. Various functions and operations described herein are performed by one or more entities, including hardware, firmware, software, and combinations thereof. For example, some functions may be performed by a processor executing instructions stored in a memory.

[0026] As shown, the operating environment may include patient user devices 502a-502n (collectively or commonly referred to as devices 502), a server 506, an electronic health record (EHR) system 504, a data store 550, and a physician user device 508. It should also be understood that the description of devices in singular or plural is merely for clarity in the description and should not be considered limiting. For example, the server 506 may include multiple servers and the physician user device 508 may include multiple user devices. The different devices in the operating environment 500 may be connected to a network 510.

[0027] The patient-directed user devices 502 may include any type of computing and / or sensing device with which a patient may interact. Non-limiting examples shown within the operating environment 500 may include smart watches 502a, mobile devices 502b (e.g., smartphones), other smart sensors 502c (e.g., smart rings, invisible sensors such as motion sensors, etc.), fitness trackers 502d, and other patient-directed user devices 502n (e.g., tablets, laptop computers, desktop computers, smart speakers, smart home systems, etc.). The patient-directed user devices 502 may either passively collect or actively prompt the patient to enter data associated with a skin condition (e.g., atopic dermatitis, psoriasis) for flare prediction and / or long-term management of the condition.

[0028] For example, the smartwatch 502a may have multiple sensors to passively collect data from the patient. The multiple sensors may include accelerometers, gyroscopes, and / or other types of motion sensors that may track the patient's hand movements. The hand movements may be used by the operating environment (e.g., one or more software modules in the server 506) to detect scratching events (e.g., by using the embodiments disclosed in PCT / US2021 / 038699 (International Publication No. WO2021 / 262857)). In addition to detecting hand movements, the smartwatch 502a passively detects other biometric parameters, such as blood glucose, body temperature, blood oxygen saturation, and / or any other type of biometric parameter.

[0029] The mobile device 502b may be used by the patient to actively input health-related data. For example, the mobile device 502d may be a smartphone in which a health care application may be installed. The health care application may prompt the patient to input health-related data. For example, the health care application may generate a push notification for the patient to input data regarding how the patient is feeling at a given time point. The prompt may be "How are you feeling this morning?" and the patient may input "Feeling great." The health care application may also display an alert notification that may be generated due to the operating environment predicting that a flare may occur. Another type of alert notification displayed by the health care application may be when the patient's current disease behavior significantly deviates from the established baseline behavior. The health care application may further enable the patient to communicate with the doctor synchronously or asynchronously.

[0030] The other sensors 502c may include devices such as smart rings, skin patches, ingestible sensors, and / or any other type of body-worn or non-body-worn sensors (commonly referred to as invisible or invisible devices / sensors). The other sensors 502c may detect biometric or non-biometric data. For example, the other sensors 502c may include smart fabrics that measure the patient's body temperature. As another example, the other sensors 502c may include smart home sensors that measure the temperature and / or humidity of a home. As yet another example, the other sensors 502c may include motion sensors that may detect / measure movement in a room. The other patient devices 502n may include any other type of device associated with a patient. For example, the other patient devices 502n may include tablet computers, laptop computers, desktop computers, and / or any other computing devices associated with a patient and connected to the network 510. The other contextual data sources 540 may include devices that provide other contextual data that may provide additional information to the data collected from the patient-directed devices 502. For example, other contextual data sources 540 may provide weather data that may be associated with data collected from the patient device 502.

[0031] The network 510 may include any type of communication network. For example, the network 510 may include a packet switching network supporting protocols such as TCP / IP. The network 510 may also include a circuit switching network supporting both wired and wireless telephony. Thus, the network 510 may include components such as wires, wireless transmitters, wireless receivers, signal repeaters, signal amplifiers, switches, routers, communication satellites, and / or any other type of network and communication devices. Some non-limiting examples of the network 510 may include a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN) such as the Internet, and the like. These are merely a few examples, and any type of communication linkage between different components of an operating environment should be considered within the scope of this disclosure.

[0032] The server 506 may include any type of computing device that may provide analytical capabilities to train and deploy one or more machine learning models and / or establish and deploy statistical analysis models. For example, the server 506 may train a predictive model using the ground truth as indicated by the scratch data and other contextual data, and then use the predictive model to predict the likelihood of a flare when new scratch and / or contextual data is received. The server 506 may also establish an analytical model based on the continuously collected time-series healthcare data, which may indicate a baseline health behavior. When new healthcare data is received, the server 506 may compare the received data with the analytical model (e.g., against the baseline health behavior) to determine whether the new healthcare data indicates a significant deviation from the baseline health behavior. The server 506 may also generate one or more alert notifications, for example, to the patient and / or physician indicating a flare prediction or indicating that the patient's health behavior has significantly deviated from the baseline behavior.

[0033] An electronic health record (EHR) 504 may store a patient's health record. The health record may include, for example, a patient's ongoing medical condition (e.g., atopic dermatitis), prescribed medications (e.g., abrocitinib), clinical encounter summaries, and / or any other health care related data associated with the patient. In some embodiments, the EHR 504 may be managed by a health care delivery facility (e.g., a hospital system).

[0034] The data store 550 may include any type of database that stores data collected from various sources within the operating environment 500. For example, the data store 550 may store both passively and actively collected data from the patient devices 502. The data store 550 may also store data collected from other contextual data sources 540 (e.g., weather data). Additionally, the data store 550 may store data sourced from the EHR 504. Thus, the data source 550 should be understood to store any type of data within the operating environment 500.

[0035] The physician user device 508 may be any type of computing device that presents a physician dashboard. Non-limiting examples of physician user devices may include a mobile phone (e.g., a smartphone), a tablet computer, a laptop computer, a desktop computer, and / or any other type of computing device. The physician dashboard may present information (e.g., demographic information, location information), and / or one or more alerts associated with various patients.

[0036] 6 shows a block diagram of an illustrative computing device 600 that may perform one or more functions described herein, according to some embodiments of the present disclosure. The computing device 600 is, however, one example of a suitable computing environment and is not intended to suggest any limitation as to the scope of use or functionality of the embodiments of the present disclosure. The computing device 600 should not be interpreted as having any dependency or requirement relating to any one or combination of illustrated components.

[0037] The embodiments of the present disclosure may be described in the general context of computer code or machine usable instructions, including computer usable or computer executable instructions, such as program modules, executed by a computer or other machine, such as a personal data assistant, smartphone, tablet PC, or other handheld or wearable device, such as a smart watch. Generally, a program module, including routines, programs, objects, components, data structures, and the like, refers to code that may perform specific tasks or implement specific data types. The embodiments of the present disclosure may be practiced in a variety of system configurations, including handheld devices, consumer electronics, general-purpose computers, or more specialized computing devices. The embodiments of the present disclosure may also be practiced in distributed computing environments where tasks are performed by remote processing devices linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including memory storage devices.

[0038] The computing device 600 may include a bus 610 that may directly or indirectly couple the following example devices: memory 612, one or more processors 614, one or more presentation components 616, one or more input / output (I / O) ports 618, one or more I / O components 620, and a power source 622. Some embodiments of the computing device 600 may further include one or more radios 624. The bus 610 represents what one or more buses may be (such as an address bus, a data bus, or a combination thereof). Although the various blocks in FIG. 6 are shown with lines for clarity, these blocks may represent logical components and do not necessarily represent actual components. For example, presentation components such as a display device may be considered to be I / O components. The processor 614 may also have their own memory. Furthermore, no distinction is made between categories such as "workstations," "servers," "laptops," or "handheld devices," all of which are contemplated within the scope of FIG. 6 and in relation to "computing devices."

[0039] Computing device 600 may include a variety of computer readable media. Computer readable media may be any available media that can be accessed by computing device 600 and may include both volatile and nonvolatile, removable and non-removable media. By way of example, and not limitation, computer readable media may comprise computer storage media and communication media. Computer storage media may include both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules, or other data. Some non-limiting examples of computer readable media may include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and that can be accessed by computing device 600. Communication media may embody computer readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and include any information delivery media. The term "modulated data signal" may refer to a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, communication media may include wired media, such as a wired network or direct-wired connection, and wireless media, such as acoustic, RF, infrared and other wireless media. Combinations of any of the above are also intended to be included within the scope of computer-readable media.

[0040] The memory 612 may include computer storage media in the form of volatile and / or non-volatile memory. The memory 612 may be removable, non-removable, or a combination thereof. Some non-limiting examples of hardware devices for the memory 1212 include solid-state memory, hard drives, optical disk drives, etc.

[0041] Computing device 600 may include one or more processors 614 that read data from various entities, such as memory 612 or I / O components 620. A presentation component 616 may present a representation of the data to a user or other device. Exemplary presentation components may include display devices, speakers, printing components, and the like.

[0042] The I / O port 618 may allow the computing device 600 to be logically coupled to other devices, such as an I / O component 620, some of which may be built-in. Non-limiting examples of the I / O component 620 may include a microphone, joystick, gamepad, satellite dish, scanner, printer, or wireless device. The I / O component 620 may provide a natural user interface (NUI) that processes air gestures, voice, or other physiological input generated by a user. In some cases, the input may be transmitted to an appropriate network element for further processing. The NUI may implement any combination of voice authentication, touch and stylus authentication, face authentication, biometric authentication, gesture authentication both on or near the screen, air gestures, head and eye tracking, and touch authentication associated with a display on the computing device 600. The computing device 600 may be equipped with cameras, such as a stereoscopic camera system, an infrared camera system, an RGB camera system, and combinations thereof, for gesture detection and authentication. Additionally, computing device 600 may be equipped with an accelerometer or gyroscope to enable detection of movement.

[0043] Some embodiments of the computing device 600 may include one or more radios 624 (or similar wireless communication components). A radio may transmit and receive radio or wireless communications. The computing device 600 may be a wireless terminal adapted to receive communications and media over various wireless networks. The computing device 600 may communicate via wireless protocols such as Code Division Multiple Access ("CDMA"), Global System for Digital Cellular Communications ("GSM"), or Time Division Multiple Access ("TDMA"), as well as others, to communicate with other devices. The wireless communications may be short-range connections, long-range connections, or a combination of both short-range and long-range wireless telecommunications connections.

[0044] 7 shows a block diagram of an exemplary architecture of an operating environment 700 in which one or more embodiments disclosed herein may be used. The architecture shown may be implemented by one of the many more components / devices of the operating environment 500 shown in FIG. It should be understood that the architecture shown is merely an example, and that architectures with additional, alternative, or fewer components should also be considered within the scope of the present disclosure. It should be further understood that components shown as a single component or multiple components are also merely examples, and that a single component may include multiple iterations of the same component or multiple constituent subcomponents, and that the functionality of multiple components may be accomplished by a single component.

[0045] The operating environment 700 may be used for continuous or near-continuous digital monitoring of a patient suffering from a skin condition (e.g., atopic dermatitis, psoriasis) and, if necessary, to trigger an alert notification to the patient, for example, when a condition is predicted to worsen or is detected to have changed significantly from an established baseline. To that end, the operating environment 700 may include patient-facing devices (e.g., wearable devices 702a, patient user devices 702b, other sensors 702c, etc.) to collect healthcare and other data from the patient, to provide alert notifications to the patient, and to facilitate communication between a physician and the patient. Data collected from the patient-facing devices and other sources (e.g., other contextual data sources 740) may be stored in storage 770 (e.g., personal records 780). Analysis components (e.g., flare predictor 780, disease progression tracker 760) may use the stored data and other data to predict flare and track the progression of the skin condition (e.g., atopic dermatitis, psoriasis). Based on the analysis, an alert notification may be sent to the physician (eg, via the physician user device 708). The components of the operating environment 700 may be interconnected through a network 710.

[0046] With respect to patient-facing devices, these devices may include, for example, wearable devices 702a, patient user devices 702b, and other sensors 702c. The wearable devices 702a may include any type of wearable device, non-limiting examples include smart watches, fitness trackers, smart rings, and the like. In some embodiments, the wearable devices 702a may include a healthcare application 722. The healthcare application 722 may be a computer program installed on the wearable devices 702a to collect healthcare data, in some cases perform pre-processing of the collected data, and transmit the data to the patient user devices 702b or to a remote server (e.g., implementing one or more of the flare predictor 750, disease progression tracker 760, or storage 770). In particular, the healthcare application 722 may interface (e.g., through API calls) with the operating system of the wearable devices to collect data from the sensors 724.

[0047] The sensors 724 may include any type of sensor that may continuously or periodically collect data from a patient wearing the wearable device 702a. For example, the sensors 724 may include an accelerometer to determine directional movement, a gyroscope to detect orientation, and / or any other type of sensor to collect position or movement data. The sensors 724 may include biosensors, such as a temperature sensor to measure body temperature (it should be understood that the temperature sensor may be non-biological and may measure ambient temperature), a heart rate monitor, an electrocardiogram sensor to collect electrocardiogram data when prompted by the patient, a glucose monitor, a sweat monitor, a blood oxygen saturation monitor, and / or any other type of biosensor. These sensors may be triggered by the healthcare application 722 (e.g., through an API call to the operating system of the wearable device 702a) to collect the corresponding data. Alternatively, the wearable device 702a may not have a healthcare application 722, and the trigger may be received from the patient user device 702b (e.g., from its healthcare application 732) or remotely through the network 710. In other embodiments, the wearable device 702a may itself continuously or periodically activate the sensor 724 and communicate collected sensor data to the healthcare application 724 (and / or the healthcare application 732, or a remote device connected via the network 710).

[0048] In other words, the sensor 724 may passively collect patient data without the patient's active involvement. For example, the sensor 724 may monitor the patient's physical movements and / or other biometric data because the sensor 724 is within the wearable device 702a and is continuously worn by the patient. Such passive collection of movements and biometric data does not require the patient's continuous attention and is less burdensome.

[0049] The patient user device 702b may include any type of computing device used by a patient. For example, the patient user device 702b may include a mobile phone such as a smartphone, a tablet device, a laptop computer, a desktop computer, and / or any other type of computing device. The healthcare application 732 may be installed on the patient user device 702b. The healthcare application 732 should be understood to include a standalone application (e.g., a smartphone app) or a web-based application (e.g., accessed using a browser). The healthcare application 732 may provide an interface (e.g., a graphical user interface) for the patient to view alert notifications, communicate with a physician, and / or actively input health-related data.

[0050] As an example, the healthcare application 732 may be used to gather further information regarding the prediction based on data collected by the wearable device's sensor 724. For example, using passively collected motion data, the server may detect that the patient is experiencing higher than normal scratching events (e.g., as detected by the scratch detection algorithm disclosed in PCT / US2021 / 038699 (International Publication No. 2021 / 262857)). In response to this determination, the server may transmit an alert notification to the healthcare application 732. The alert notification may be, for example, "We detected a high amount of scratching activity last night. How are you feeling this morning?" prompting the patient to respond. In response, the healthcare application 732 may provide options such as "fatigued," "feverish," and "normal."

[0051] In addition to prompts corresponding to alert notifications, the healthcare application 732 may periodically (e.g., without triggering data entry) require the user to enter healthcare data. For example, the healthcare application 732 may prompt the patient to enter how they are feeling each morning, regardless of nighttime scratching activity. Other non-limiting examples of actively entered data include body temperature (if not collected by the sensor 724 of the wearable device 702a), bowel movements, pain levels experienced, stress levels, anxiety levels, time of taking prescription medications, athletic activity (if not captured by the wearable device 702a), side effects of prescription medications, and / or any other type of healthcare data that may affect the patient's quality of life.

[0052] The healthcare application 732 may also provide educational materials to the patient. The educational materials in some embodiments may include cognitive behavioral therapy (CBT) based behavior change encouragement materials. These materials may be provided to the patient based on data passively collected by the wearable device 702a, actively collected by the patient user device 702b, and analyzed by the disease progression tracker 760. The CBT-based materials may be in the form of audio, video, and / or text and may encourage the patient to make healthier choices regarding diet, exercise, stress management, and / or any other metrics associated with maintaining quality of life. The educational materials may also be two-way communication with a physician. For example, the healthcare application 732 may provide a communication platform for voice calls, video calls, and / or exchange of text messages. The patient may pose questions through the healthcare application 732 itself, and the physician's responses may be displayed within the healthcare application. The physician's responses may be educational, advising and encouraging the patient to make healthy choices regarding managing skin conditions (e.g., atopic dermatitis, psoriasis).

[0053] The sensor 734 in the patient user device 702b may include any type of sensor, such as an accelerometer, a gyroscope, a glucose monitor (e.g., using an infrared camera), etc. If the patient user device 702b is a mobile device (e.g., a smartphone), the patient user device 702b may also monitor the user's movements using the sensor 734. The sensor 734 may detect the number of steps taken by the patient throughout the day, and / or other activities (e.g., exercise) performed by the user throughout the day. In other words, the sensor 734 may also passively collect patient movement data. In some embodiments, the sensor 734 may enable active data collection. For example, the sensor 734 may include an infrared camera, and the patient user device 702b may prompt the patient to hold a finger over the camera to detect biological attributes such as blood glucose levels, blood oxygen saturation, etc.

[0054] Camera 736 may include an optical camera that the patient may use to take a picture of an area affected by a skin condition (e.g., atopic dermatitis, psoriasis). The picture may be sent to storage 770 and / or provided to a physician. The physician may use the picture for diagnostic purposes (e.g., to determine if a condition is improving or worsening) and / or for treatment purposes (e.g., to determine if the dosage of a medication the patient is taking should be adjusted).

[0055] The other sensor 702c may be any type of sensor that measures one or more physical or biological attributes of the patient. An example of the other sensor 702c may be an ingestible sensor that may measure the effect of a prescription drug on digestive activity. Another example may be a patch sensor that may be worn on the skin to measure attributes such as skin temperature and / or movement of the body part to which the patch sensor is worn. The sensor 702c may further include a blood pressure monitor that may communicate measurements to the patient user device 702b or any other device in the operating environment 700. Other examples of the sensor 702c may include smart fabrics, smart belts, subcutaneous sensors, and the like. These are merely some examples of sensors, and any type of body-worn or non-body-worn sensor should be considered within the scope of this disclosure. Non-body-worn sensors may be referred to as invisible or invisible sensor devices.

[0056] Other contextual data sources 740 may provide additional context to the data captured by the wearable device 702a, the patient user device 702b, and / or other sensors 702c. For example, the data source 740 may be a weather-related data source providing a weather overview of the area in which the patient is located. In another case, the data source 740 may provide other attributes of the patient's geographic location, such as disease prevalence, general education level, general income level, and / or any other type of contextual data.

[0057] Data collected, either passively or actively, by one or more of the wearable device 702a, the patient user device 702c, the other sensors 702c, and the other contextual data sources 740 may be received by other components in the operating environment through the network 710. The network 710 may include any type of communication network. For example, the network 710 may include a packet switching network that supports protocols such as TCP / IP. The network 710 may also include a circuit switching network that supports both wired and wireless telephony. Thus, the network 710 may include components such as wires, wireless transmitters, wireless receivers, signal repeaters, signal amplifiers, switches, routers, communication satellites, and / or any other type of network and communication devices. Some non-limiting examples of the network 710 may include a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN) such as the Internet, and the like. These are merely a few examples, and any type of communication linkage between different components of the operating environment should be considered within the scope of this disclosure.

[0058] Data received from patient-facing devices may be stored in storage 770. Storage 770 may include any type of storage technology, such as hard drive storage, solid state storage, data server storage, etc. Although a single storage 770 is shown for clarity of explanation, it should be understood that storage 770 includes multiple geographically distributed components. For example, storage 770 may be distributed across multiple data centers and incorporate multiple levels of redundancy.

[0059] In some embodiments, storage 770 may store an individual record 780 that includes data for a corresponding patient. In other words, the individual record 780 may be associated with a patient. However, it should be understood that this individual record 780-based data organization is merely an example and should not be considered limiting. Any type of data organization (e.g., relational, object-oriented) should be considered within the scope of this disclosure.

[0060] As shown, a patient's personal record 780 may include profile / health data (e.g., electronic health record (EHR) data) 781, sensor data 782, patient-entered data 783, contextual data 784, and past events 785. These are only a few examples of data within personal record 780, and additional, alternative, or lesser data should also be considered within the scope of this disclosure.

[0061] Profile / health data 781 may include the corresponding patient's electronic medical record. Thus, profile / health data 781 may include the patient's ongoing medical conditions (e.g., atopic dermatitis, psoriasis), medications the patient is currently taking, allergies, family history, physician appointment summaries, other notes from the physician, and / or any other type of healthcare data for the patient. For example, profile / health data 781 may include information associated with flares, including the timing and severity of the flares. In some embodiments, profile / health data 781 may be provided to storage 770 from other entities. For example, profile / health data 781 may be managed by a healthcare provider (e.g., a hospital), and operating environment 700 may obtain the data from the healthcare provider.

[0062] The sensor data 781 may be data from patient-facing sensors, such as the sensor 724 of the wearable device 702a, the sensor 734 of the patient user device 702b, and / or other sensors 702c. Thus, the sensor data 781 may include data from motion sensors (e.g., accelerometers and / or gyroscopes), biometric sensors (e.g., blood glucose monitors). The sensor data 781 may be stored in association with a timestamp of when the data was collected. The timestamp may enable the operating environment 100 to detect the patient's activities throughout the day. As used herein, the sensor data 782 should be understood to include any type of passively collected data (e.g., motion passively detected by a wearable) or data captured by a patient actively engaging with a sensor (e.g., a patient places a finger over an infrared camera to measure various biological attributes).

[0063] The patient-entered data 783 may include any type of data actively entered by the patient (e.g., through the healthcare application 732). Thus, the patient-entered data 783 may include a patient's input regarding how they were feeling at a particular point in time (e.g., "fatigued," "depressed," "good," etc.). The patient-entered data 783 may further include other biometric data not captured by a sensor (e.g., sensors 724, 734, and / or 702c). For example, such biometric data may include blood glucose levels, blood oxygen saturation, blood pressure, etc. Similar to the sensor data 782, the patient-entered data 783 may also be organized using a timestamp. In other words, the timestamp may be used to correlate the sensor data 782 and the patient-entered data 783.

[0064] The contextual data 784 may include any type of information that may provide further context to the sensor data 782 and / or the patient-input data 783. For example, the contextual data may be weather data that may indicate the weather conditions when the corresponding sensor data 782 and / or patient-input data 783 were collected. As another example, the contextual data 784 may include the prevalence of a disease (e.g., atopic dermatitis, psoriasis) in the patient's geographic location, the education and income level in the patient's geographic location, and / or any other type of contextual data. Like the sensor data 782 and the patient-input data 783, the contextual data 784 may also be time-stamped, such that these three types of data may be correlated in time.

[0065] The past event log 785 may include records of events associated with the patient. For example, the past event log 785 may include scratches detected using the scratch detection algorithm disclosed in PCT / US2021 / 038699 (International Publication No. WO 2021 / 262857). As another example, the past event log may also include flares as reported by the patient. The past event log 785 may include other information related to clinical encounters, prescription fillings and refills, and / or any other type of events associated with managing skin conditions (e.g., atopic dermatitis, psoriasis). The past event log 785 may also be time-stamped, such that these logs may be temporally correlated with one or more of the sensor data 782, the patient input data 783, or the contextual data 784.

[0066] The analytical components (e.g., flare predictor 750 and disease progression tracker 760) may use the personal records 780 (and / or other types of data) in storage 770 to generate / train one or more analytical / machine learning models and then deploy the models for one or more of flare prediction or long-term management of the disease.

[0067] The redness predictor 750 may predict redness based on scratching events (e.g., as detected by the algorithms disclosed in PCT / US2021 / 038699 (WO 2021 / 262857)), contextual data, and / or any other type of data. The redness predictor 750 may predict redness using a predictive model 752. The predictive model 752 may first be trained using a model trainer 752. The module trainer may include computer program instructions that may obtain training data, pre-process the training data, and use the training data to train the predictive model 752 using one or more of supervised or unsupervised training techniques.

[0068] In a training example using a supervised training approach, the model trainer may obtain scratch data (e.g., from past event log 785), redness data (e.g., from one or more of profile / health data 781, patient input data, context data 784, or past event log 785), and / or other context data (e.g., from context data 784). Thus, the redness data may provide labeling (e.g., "redness" or "no redness") for the scratch data and / or other input data, thereby enabling the model trainer 754 to minimize the prediction error of the predictive model 752 (e.g., through backpropagation). However, backpropagation is only one example, and any type of machine learning training should be considered within the scope of this disclosure. Furthermore, the model trainer 754 may train the predictive model 752 using an unsupervised approach. In predictive model 752 training and deployment embodiments, any type of information associated with a detected scratch event may be referred to as context data. For example, the entire person record 780, or any combination of the constituent data, may be referred to as contextual data.

[0069] Although the predictive model 752 is described herein as a machine learning model, it should be understood that the predictive model 752 may include a statistical model. In the case of a statistical model, the model trainer 754 may act as a model generator to generate the statistical model. The statistical model may be used to predict which combinations of input variables (e.g., scratch data and other data) are more likely to result in a "flare" output and which combinations of input variables are more likely to result in a "no flare" output.

[0070] It should be appreciated that the model trainer 754 may continually train the predictive model 752. For example, if ground truth is available for a prediction (e.g., the ground truth may indicate whether a prediction was accurate or inaccurate), the model trainer 754 may use such accurate or inaccurate predictions to continually train and improve the predictive model 752.

[0071] The model deployer 756 may be a software module that uses the trained predictive model 752 to predict a flare from received input data. For example, new scratch data and / or other contextual data may be received for a particular patient, and the model deployer 756 may feed the received new data to the trained predictive model 752. The trained predictive model 752 may then output a likelihood of a flare based on the input data.

[0072] The alert notification generator 758 may generate one or more alert notifications based on the trained predictive model 752 indicating a higher likelihood of a flare based on the received input data. The alert notification may be to the patient user device 702b for display by the healthcare application 732. This patient alert notification may include a message to the patient that the patient should seek treatment (e.g., communicate with a doctor through the healthcare application 732) to forestall a potential flare. Another example of a message to the patient may be an increase in the dosage of a prescribed medication (i.e., within predefined limits). In general, the alert notification may trigger the patient to take action to mitigate the likelihood of a flare.

[0073] Another example of an alert notification may be an alert notification to a physician, for example, to the dashboard application 742 in the physician user device 708. This alert notification may indicate to the physician that the patient may have a higher likelihood of a flare. In response to the alert notification, the physician may communicate with the patient (e.g., using communication channels provided by the dashboard application 742 and the healthcare application 732) and / or take other measures, such as prescribing a higher dose of medication.

[0074] A disease progression tracker 760 may be another aspect of the analysis provided within the operating environment 760. The disease progression tracker 760 may continually track different aspects of a patient's health to determine how far a skin condition (e.g., atopic dermatitis, psoriasis) has progressed, the effect of the disease on the patient's overall health, the effect of medication on the disease, and / or any other aspect of the progression of the skin condition. Additionally or alternatively, the disease progression tracker 760 may determine whether a condition has deviated significantly from normal.

[0075] To track disease progression and / or determine if a medical condition has deviated significantly from the norm, the disease progression tracker 760 may generate an analytical model 762 using a model generator 764. The model generator 764 may include computer program instructions that may retrieve longitudinal data (e.g., profile health data 781, past event log 785, etc.) from storage. This longitudinal data may be used by the model generator 764 to generate the analytical model 762. However, it should be understood that the analytical model 762 may be a machine learning model and the model generator 764 may use the retrieved data to train the machine learning model. Thus, the following description of generating and deploying the analytical model 762 should be understood to include training and deploying any type of machine learning model.

[0076] In some embodiments, the model generator 764 may generate a model for an individual patient. For example, the model generator 764 may obtain longitudinal data for an individual patient and then establish a baseline as the corresponding analytical model 762. The baseline may include, for example, normal levels of scratching, physical activity, condition reported by the patient (e.g., "fatigue state"), and / or any other attributes. Thus, the normal levels of a combination of these attributes may be established as the baseline.

[0077] In some embodiments, the model generator 764 may generate a population-level baseline. For example, the model generator 764 may obtain longitudinal data for a population of patients having certain criteria, such as age, sex, geographic location, ethnicity, etc. Analyzing the collected data, the model generator 764 may establish a population-level baseline as the analytical model 762. The model deployer 766 may then use the population-level baseline to determine whether an individual patient's condition has deviated significantly from normal levels.

[0078] The communication facilitator 768 may facilitate communication between the patient, for example, by using the healthcare application 732 and the dashboard application 742. For example, if the analytical model 762 determines that the disease state has deviated significantly from normal, the communication facilitator 768 may transmit a first alert notification to the patient (e.g., to be displayed in the healthcare application) and a second alert notification to the physician (e.g., to be displayed in the dashboard application 742). One or more of these alerts may have a communication prompt. For example, the first alert to the patient may have the prompt "Send message to your physician." The second alert to the physician may be "Contact Patient A, patient's dermatitis may be worsening." In response to these prompts, an asynchronous (e.g., through a text message exchange) or synchronous (e.g., audio / video chat) communication channel may be opened between the healthcare application 732 and the dashboard application 742.

[0079] The physician user device 708 may be any type of user device used by a physician. Non-limiting examples of the physician user device 708 may include a mobile phone (e.g., a smartphone), a tablet computer, a laptop computer, a desktop computer, and the like. The physician user device 708 may have a dashboard application 742, which may be an installed standalone application or a web-based application accessible through a browser. The dashboard application 742 may show disease progression for an individual patient. For example, the dashboard application 742 may show a chart showing how scratching events have increased or decreased over time. The dashboard application may also show other aspects of the patient's health, such as stress and anxiety levels. The dashboard application 742 may further show medications prescribed for the patient.

[0080] 8 shows a flow diagram of an illustrative method 800 of training a predictive model for flare prediction, according to some embodiments of the present disclosure. The illustrative method 800 may be performed by one or more computing devices (e.g., computing device 600, such as used within operating environment 500). It should be understood that the steps of method 800 shown in FIG. 8 and described herein are merely illustrative, and methods with additional, alternative, or fewer steps should be considered within the scope of the present disclosure.

[0081] In step 802, a scratch dataset may be obtained. The scratch dataset may be generated by the embodiments disclosed in PCT / US2021 / 038699 (International Publication No. WO 2021 / 262857). The scratch dataset may include data for a population of patients. For each patient, the corresponding data may include the number of scratches (or scratch events) during a time course. For example, the number of scratches may be organized by hour, day, week, and / or any other time unit of organization. For scratch events, the corresponding data may also include the duration of the scratch. As an example, if a particular patient has three scratch events during an hour, the first scratch event may be three minutes, the second scratch event may be five minutes, and the third scratch event may be two minutes.

[0082] The scratch dataset may further include data indicative of the severity of the scratch. In some embodiments, the duration of the scratch event may serve as a proxy for the severity of the scratch. For example, a longer scratch event may be considered more severe than a shorter scratch event. In other embodiments, the severity may be measured by how intense the scratch was for each individual scratch event. In other words, a scratch event with a greater number of hand movements may be more severe compared to another scratch event with a smaller number of hand movements. Additionally, the forcefulness of the hand movements may also be recorded, for example, using accelerometer data. For example, faster hand movements may indicate a more forceful scratch compared to slower hand movements. These are just some examples of data in a scratch dataset, and other forms of scratch data should also be considered within the scope of this disclosure.

[0083] In step 804, a contextual dataset may be received. The contextual dataset may be received from a variety of sources, such as an EHR (e.g., EHR 781 shown in FIG. 7), weather forecast data, prescription data, and / or any other type of patient data. The contextual dataset may be associated with the scratch dataset and may provide additional information, for example, whether the patient experienced a flare.

[0084] In some embodiments, the contextual data may provide whether the patient experienced a flare. For example, the EHR may indicate that a flare was verified and / or that a medication was prescribed for the flare. Alternatively, the patient may have entered into a healthcare application that they experienced a flare, which may be captured as contextual data. As described with respect to FIG. 7, the contextual data set may be from a variety of sources and provide an indication of whether the patient experienced a flare.

[0085] In addition to indicating whether the patient experienced a flare, the contextual dataset may include additional information associated with the scratching event, which may include demographic information of the patient, weather patterns at the time the scratching event was detected, the geographic location of the patient, prescription medications taken by the patient, health conditions of the patient (e.g., obesity, high blood pressure, mental illness), family history of the patient, etc.

[0086] Thus, the combination of the scratch dataset and the context dataset may provide a training labeled dataset to the predictive model in step 806. In particular, the scratch dataset and some aspects of the context dataset may provide input parameters for training the predictive model, and the aspects of the context dataset indicating whether the corresponding patient experienced a flare may provide a labeled predicted output. Using the flare dataset and the context dataset, the predictive model may be trained by a supervised training approach. For example, each training iteration may generate an output that may be compared to the predicted output, and backpropagation techniques may be used to refine the predictive model so that the predictive model produces an output closer to the predicted output. Some non-limiting examples of predictive models may include ensemble learners such as random forests, light gradient boosting machines (LGBMs), XGBoost, and / or artificial neural networks such as recurrent neural networks (RNNs), long short-term memories (LSTMs), convolutional neural networks (CNNs), and the like. However, it should be understood that these are merely examples and that other predictive / statistical models should be considered within the scope of this disclosure.

[0087] Such techniques for training a predictive model are merely examples, and other techniques should also be considered within the scope of the present disclosure. For example, the predictive model may be trained using an unsupervised training technique. In other examples, the predictive model may be a statistical model, and step 806 may establish the statistical model using the acquired data set. Thus, any type of data analysis for generating a predictive model or for establishing a statistical model should be considered within the scope of the present disclosure.

[0088] 9 shows a flow diagram of an illustrative method 900 of using a trained predictive model for flare prediction, according to some embodiments of the present disclosure. The illustrative method 900 may be performed by one or more computing devices (e.g., computing device 600, such as used within operating environment 500). It should be understood that the steps of method 900 shown in FIG. 9 and described herein are merely illustrative, and methods with additional, alternative, or fewer steps should be considered within the scope of the present disclosure.

[0089] In step 902, periodic data about a patient (e.g., a patient suffering from atopic dermatitis or psoriasis) may be received. The periodic data may include scratch data of the patient over a period of time. For example, the scratch data may be generated using passively collected motion data from a wearable and actively collected data from a healthcare application. The scratch data may indicate the number of scratch events, the severity of the scratch events, and any other attributes associated with the scratch events. In addition to the scratch data, other contextual data may also be included in the periodic data. The other contextual data may include, for example, weather data, demographic data, etc. Any form of periodic data associated with a skin condition should be considered within the scope of this disclosure.

[0090] In step 904, the received periodic dates may be fed to a trained predictive model. The predictive model may have been trained using the steps of method 800. It should also be understood that the trained predictive model includes any type of established statistical model. Some non-limiting examples of predictive models may include ensemble learners such as Random Forest, Light Gradient Boosting Machine (LGBM), XGBoost, and / or artificial neural networks such as Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and the like. In the case of a statistical model, step 904 may include comparing statistics (e.g., z-statistics) to determine whether the received periodic data is significantly close to a possible outcome (e.g., an outcome indicative of redness) that would be generated. However, it should be understood that these are merely examples and other predictive / statistical models should be considered within the scope of this disclosure.

[0091] In step 906, the predictive model (or statistical model) generates an output indicative of a likelihood of redness. The likelihood of redness may indicate corresponding probabilities that the inputs provided are associated with redness and not associated with redness. For example, the output may be a 90% probability of redness and a 10% probability of no redness.

[0092] In step 908, one or more alert notifications may be triggered based on the output of the predictive model. For example, if the predictive model generates a higher probability of a flare, an alert notification may be triggered to a healthcare application installed on the patient user device. The alert notification may indicate that a flare is imminent and that the patient should contact a physician. The alert notification may also provide an option for the patient to initiate synchronous or asynchronous communication with the physician. Another alert notification may be sent to the physician's dashboard. This alert notification may identify the patient and indicate to the physician that a flare may be imminent. The alert notification may also provide an option for the physician to initiate synchronous or asynchronous communication with the patient, transmit a prescription to a pharmacy, and / or take any other mitigating measures.

[0093] 10 shows a flow diagram of an exemplary method 1000 of generating an analytical model of a baseline disease behavior of a skin disease according to some embodiments of the present disclosure. The exemplary method 1000 may be performed by one or more computing devices (e.g., computing device 600 as used in operating environment 500). It should be understood that the steps of method 1000 shown in FIG. 10 and described herein are merely exemplary, and methods with additional, alternative, or fewer steps should be considered within the scope of the present disclosure.

[0094] In step 1002, health care data from a patient (e.g., a patient suffering from atopic dermatitis or psoriasis) may be periodically received. For example, the periodically received data may include health care data that is passively collected from a wearable device (e.g., a smart watch) and / or that is invisible, and / or that is actively collected through a health care application (e.g., installed on a smartphone). Passively collected data may include, for example, motion data and other biometric data (e.g., heart rate). Actively collected data may include, for example, the patient's mood state, prescription medications taken, and / or other biometric data entered by the patient.

[0095] Such periodic collection of data may thus be a time series data set indicative of the progression of the skin disease (e.g., atopic dermatitis, psoriasis). Such collection may thus be used in step 1004 to establish an analytical model of baseline health behavior (and / or machine learning model). The analytical model of baseline health behavior may, for example, represent a normal distribution of a combination of variables such as scratching events, the patient's emotional state (e.g., stress and anxiety levels), the patient's activity level, and / or any other attributes associated with the continued pathology of the skin disease. Some non-limiting examples of machine learning models may include ensemble learners such as Random Forest, Light Gradient Boosting Machine (LGBM), XGBoost, and / or artificial neural networks such as Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN). However, it should be understood that these are merely examples and other predictive / statistical models should be considered within the scope of the present disclosure.

[0096] The generated analytical model may be stored for comparison with future healthcare data in step 1006. As healthcare data continues to be collected, such comparison may enable a determination whether future collected healthcare data falls within the predicted distribution range or deviates significantly from the predicted distribution range.

[0097] 11 shows a flow diagram of an illustrative method 1100 of deploying an analytical model to determine whether currently observed behavior deviates significantly from baseline disease behavior, according to some embodiments of the present disclosure. The illustrative method 1100 may be performed by one or more computing devices (e.g., computing device 600, such as used within operating environment 500). It should be understood that the steps of method 1100 shown in FIG. 11 and described herein are merely illustrative, and methods with additional, alternative, or fewer steps should be considered within the scope of the present disclosure.

[0098] In step 1102, recent healthcare data may be received about a patient (e.g., a patient suffering from atopic dermatitis or psoriasis). The recent healthcare data may be collected passively, e.g., through a wearable or invisible, and / or actively, e.g., by prompting the patient to enter the data into a healthcare application. Such recent healthcare data may be collected on an ongoing basis, as the patient may be continually monitored.

[0099] In step 1104, the recent healthcare data may be compared to an established analytical model (e.g., an analytical model generated by method 1000). This comparison may include determining whether the recent healthcare data exhibits a statistically significant deviation from the established baseline health behavior (as indicated by the analytical model). However, it should be understood that the comparison with the established analytical model is merely an example and that using machine learning models for outcome prediction (e.g., predicting disease progression) should also be considered within the scope of this disclosure. Some non-limiting examples of machine learning models may include ensemble learners such as Random Forest, Light Gradient Boosting Machine (LGBM), XGBoost, and / or artificial neural networks such as Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), etc. However, it should be understood that these are merely examples and that other predictive / statistical models should also be considered within the scope of this disclosure.

[0100] In step 1106, one or more notifications may be triggered based on the comparison. For example, if it is determined that the patient's healthcare behavior has significantly deviated from the established healthcare behavior, an alert notification may be sent to the patient to initiate synchronous or asynchronous communication with the physician. Additionally or alternatively, another alert notification may be sent to the physician to initiate synchronous or asynchronous communication with the patient.

[0101] 12A-12D show illustrative patient-facing interfaces 1200a-1200d according to some embodiments of the present disclosure. The interfaces 1200a-1200d may be displayed on any type of patient-facing device (e.g., patient user device 502 as shown in FIG. 5). The interfaces 1200a-1200d may be generated based on analytics (e.g., machine learning / statistics-based predictions) performed by any type of operating environment (e.g., operating environment 500 shown in FIG. 5, operating environment 700 shown in FIG. 7, etc.).

[0102] As shown in FIG. 12A, the initial interface 1200a may include a graphical object 1202. The graphical object may be based on a “traffic light” type symbol to indicate an alert or non-alert state. For example, a “green light” 1204 may indicate that a skin condition (e.g., atopic dermatitis, psoriasis, etc.) is under control and no change in symptoms is observed. A “yellow light” 1206 may indicate that a skin condition may be in flux. In other words, the yellow light 1206 may indicate that some change in symptoms has been observed. A “red light” 1208 may indicate that an imminent flare and / or other type of worsening of the skin condition is predicted. The patient may select one of the signals 1204, 1206, and 1208, and based on this, one of the updated interfaces 1200b-1200d may provide relevant information, education, and / or action items.

[0103] FIG. 12B shows an illustrative updated patient interface 1200b that may be generated when the patient selects the green light 1204 within the interface 1200a. In response, the updated interface 1200b may show an icon 1210 indicating a controlled skin condition, and text 1212 that also indicates that the skin condition is under control. As shown, the text 1212 may indicate that "no change in symptoms has been observed for two weeks." However, this timing is used only as an example and should not be considered limiting. The updated interface 1200b may further provide another text 1214 informing the patient of the skin condition being under control. The text 1214 may also prompt the patient to click on one or more of the appropriate icons 1218 (to receive suggestions or further information regarding sleep), 1216 (to receive suggestions or further information regarding lifestyle), 1224 (to receive suggestions or further information regarding scratching and itching), and 1220 (to receive suggestions or further information regarding lesions). These icons 1216, 1218, 1220, and 1224 may provide corresponding suggestions and further information in a patient's consultation with a physician. For example, upon selecting the sleep icon 1218, the patient may receive suggestions regarding the amount of sleep recommended to keep a skin condition under control.

[0104] 12C shows an illustrative updated patient interface 1200c that may be generated when the patient selects the yellow light 1206 within the interface 1200a. In response, the updated interface 1200c may show an icon 1230 indicating a "fluid" skin condition, and text 1232 that also indicates that the skin condition is fluid. As shown, the text 1232 may indicate that "changes in symptoms have been recorded." The updated interface 1200c may further provide another text 1234 informing the patient that the symptoms of the skin condition have recently increased. The text 1234 may also prompt the patient to click on one or more of the appropriate icons 1238 (to receive suggestions or further information regarding sleep), 1236 (to receive suggestions or further information regarding lifestyle), 1244 (to receive suggestions or further information regarding scratching and itching), and 1240 (to receive suggestions or further information regarding lesions). These icons 1236, 1238, 1240, and 1244 may provide corresponding suggestions and further information in a patient's consultation with a physician. For example, upon selecting the sleep icon 1238, the patient may receive suggestions regarding the amount of sleep recommended to alleviate recently recorded symptoms.

[0105] 12D shows an illustrative updated patient interface 1200d that may be generated when the patient selects the red light 1208 within the interface 1200a. In response, the updated interface 1200d may show an icon 1250 indicating an active reddened skin condition, and text 1252 that also indicates that reddening has been observed or predicted. The updated interface 1200d may further provide another text 1254 informing the patient that an active onset of a symptom (e.g., reddening) has been observed or predicted. The text 1254 may also prompt the patient to click on one or more of the appropriate icons 1258 (to receive suggestions or further information regarding sleep), 1256 (to receive suggestions or further information regarding lifestyle), 1264 (to receive suggestions or further information regarding scratching and itching), and 1260 (to receive suggestions or further information regarding lesions). These icons 1256, 1258, 1260, and 1264 may provide corresponding suggestions and further information in a patient's consultation with a physician. For example, upon selecting the sleep icon 1258, the patient may receive suggestions regarding the amount of sleep recommended to manage active symptoms.

[0106] 13A-13C show illustrative physician interfaces 1300a-1300c according to some embodiments of the present disclosure. The interfaces 1300a-1300c may be displayed on any type of physician device (e.g., physician user device 508 as shown in FIG. 5). The interfaces 1300a-1300c may be generated based on analytics (e.g., machine learning / statistics-based predictions) performed by any type of operating environment (e.g., operating environment 500 shown in FIG. 5, operating environment 700 shown in FIG. 7, etc.).

[0107] As shown, the initial interface 1300a may show a chart 1302 of severity scores for any type of skin condition of a patient. The severity scores may be for a duration (e.g., one month). The interface 1300a may allow a physician to view components of the severity score. For example, a selection within the chart 1302 may generate an updated interface 1300b as shown in FIG. 13B, which may show a chart 1304 of scratching scores that form the severity score shown in the chart 1302. As another example, another selection within the chart 1302 may generate another updated interface 1300c as shown in FIG. 13C, which may show a chart 1306 of sleep scores that form the severity score shown in the chart 1302. Thus, using the interfaces 1300a-1300c, a physician may be able to track the progression of a patient's skin condition.

[0108] It will be understood by those skilled in the art that the present disclosure may be embodied in other specific forms without departing from its spirit and essential characteristics.The presently disclosed embodiments are therefore considered in all respects to be illustrative and not limited.The scope of the present disclosure is indicated by the appended claims, rather than the foregoing description, and all changes that come within the meaning and scope and equivalents are intended to be embraced therein.

[0109] It should be noted that the terms "including" and "comprising" are to be construed to mean "including, but not limited to." Unless otherwise expressly recited in the claim, "a" is to be construed as "at least one," and "the," "the," etc. are to be construed as "at least one," "at least one of," etc. Furthermore, it is Applicant's intent that only those claims which include the language "means for" or "step for" shall be construed under 35 U.S.C. 112(f). Any claim which does not expressly include the language "means for" or "step for" shall not be construed under 35 U.S.C. 112(f).

Claims

1. 1. A computer-implemented method comprising: acquiring, by a server, a scratch dataset, the scratch dataset including data records of corresponding scratching events of a patient population suffering from a skin disease; obtaining, by the server, a contextual data set including data records of additional information associated with the corresponding scratch event; training, by the server, a predictive model based on the scratch dataset and the context dataset using a supervised training approach; receiving, by said server, periodic data indicative of the occurrence of scratching events over a period of time for a particular patient suffering from said skin disease; feeding, by the server, the received periodic data to the trained predictive model; transmitting, by the server, an alert notification to a user device of the particular patient in response to the predictive model outputting a likelihood of flare; A computer-implemented method comprising:

2. 10. The computer-implemented method of claim 1, further comprising transmitting, by the server, a second alert notification to a physician dashboard in response to the predictive model outputting a likelihood of flare.

3. receiving, by the server, a patient communication message that is provided to the physician dashboard in response to the second alert notification; transmitting, by the server, the patient communication message to the user device of the particular patient; The computer-implemented method of claim 2 , further comprising:

4. The computer-implemented method of claim 3 , wherein the patient communication message includes instructions for the particular patient to communicate with a physician.

5. The computer-implemented method of claim 3 , wherein the patient communication message is for a prescription medication to control the redness.

6. The computer-implemented method of claim 3 , wherein the periodic data is received from a healthcare application executing on the user device.

7. The computer-implemented method of claim 6 , wherein the patient communication message is transmitted by the server to the healthcare application executing on the user device.

8. The method of claim 1 , wherein the data records of the corresponding scratch events include a frequency of the scratch events.

9. The method of claim 1 , wherein the data record of the corresponding scratching event includes a severity of the scratching event.

10. The method of claim 1 , wherein the data record of the additional information includes whether a corresponding scratching event was associated with a flare.

11. 2. The method of claim 1, wherein the data records of the additional information include associations of corresponding scratching events with at least one of weather, food intake, other infections, allergens, clothing worn, presence of saliva at the site of skin disease, dry skin, sweat levels, stress levels, exercise levels, or hormone levels.

12. 1. A computer-implemented method comprising: receiving, by a server, periodically, for a predetermined time period, health care data from a health care application installed on a user device of a patient suffering from a skin disease; establishing, by the server, baseline health behaviors based on the health care data over the predetermined time period; receiving, by the server, new healthcare data from the healthcare application installed on the user device; determining, by the server, whether the new healthcare data has a significant deviation from the baseline health behavior; In response to the server determining a significant deviation from the baseline health behavior, triggering an alert notification to a physician dashboard; A computer-implemented method comprising:

13. The method of claim 12 , wherein the baseline health behaviors are established by training a machine learning model.

14. 14. The method of claim 13, wherein determining whether the new healthcare data has a significant deviation from the baseline health behavior comprises feeding the new healthcare data to the trained machine learning model.

15. 13. The method of claim 12, wherein the healthcare data includes at least one of data passively collected from a wearable device worn by the patient or data actively collected from the healthcare application installed on the user device of the patient.

16. 13. The method of claim 12, further comprising, in response to the server determining the significant deviation from the baseline health behavior, triggering a second alert notification to the healthcare application installed on the user device of the patient.

17. 13. The method of claim 12, further comprising, in response to the server determining the significant deviation from the baseline health behavior, facilitating, by the server, communication between the patient and a physician via the healthcare application and the physician dashboard, respectively.

18. 1. A computer-implemented method comprising: receiving, by a computing device, health care data of a patient having a skin disease continuously from a wearable computing device worn by the patient; periodically prompting, by the computing device, the patient to input additional healthcare data into an interface generated by a healthcare application installed on the computing device; transmitting, by the computing device, the healthcare data and additional healthcare data to a remote server; receiving, by the computing device, an alert notification from the remote server in response to the remote server determining a likelihood of the skin condition worsening; generating, by the computing device, a push notification indicating an action for the patient in response to receiving the alert notification; A computer-implemented method comprising:

19. 20. The computer-implemented method of claim 18, wherein the healthcare data received from the wearable computing device includes motion data.

20. 20. The computer-implemented method of claim 18, wherein the action for the patient includes at least one of filling a prescription, refilling a prescription, or communicating with a physician.

Images