Systems and methods for cold hypersensitivity assessments as an indicator for cipn

Abstract

Among the various aspects of the present disclosure is the provision of systems and methods for cold hypersensitivity assessments as an indicator for CIPN. The present teachings include the process for predicting a chemotherapy-induced neuropathy (CIPN) condition and providing a recommendation for changes in treatment based on the prediction of the CIPN condition. Also disclosed is a mobile application for data capture and processing to predict individual risk of CIPN development.

Description

TITLE OF THE INVENTIONSYSTEMS AND METHODS FOR COLD HYPERSENSITIVITY ASSESSMENTS AS AN INDICATOR FOR CIPNCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This PCT application claims priority from U.S. Provisional Application Serial No. 63 / 518,958 filed on August 11 , 2023, the content of which is incorporated herein by reference in its entirety.STATEMENT REGARDING FEDERALLY SPONSORED RESEARCH OR DEVELOPMENT

[0002] Not applicable.MATERIAL INCORPORATED BY REFERENCE

[0003] Not applicable.FIELD OF THE INVENTION

[0004] The present disclosure relates generally to the detection of chemotherapy induced peripheral neuropathy (CIPN), and more specifically to using cold hypersensitivity assessments as an early detection indicator for CIPN.BACKGROUND OF THE INVENTION

[0005] Colorectal cancer (CRC) is the third deadliest cancer globally, and oxaliplatin-based chemotherapy regimens are commonly used in its treatment. However, chemotherapy-induced peripheral neuropathy (CIPN), characterized by peripheral nerve damage away from the brain and spinal cord, significantly hinders treatment completion in at least a portion of treatments. Symptoms of CIPN can include tingling, pins and needles sensations, pain, burning, numbness, sensitivity to hot, cold, or changing temperatures, and difficulty with fine motor skills, often presenting symmetrically and progressing from the fingers and toes toward the body.

[0006] The mechanisms by which different cancer treatments cause neuropathy differ, but patient presentation of symptoms is often similar. In a sizeable portion of patients, this presentation is characterized by glove and / orsock distribution of numbness, pain, and sensory disturbances.

[0007] CIPN is associated with cumulative oxaliplatin use, impairing function, reducing quality of life, and being difficult to treat. Cold hypersensitivity in the extremities is a common feature of acute CIPN, affecting most patients receiving oxaliplatin. While there are associations between acute cold hypersensitivity and the development of long-term CIPN, a quantifiable relationship has not yet been demonstrated.

[0008] Numerous approaches have been tested to prevent CIPN but have had limited success. The occurrence of CIPN may lead to dose reduction or discontinuation of the chemotherapy, negatively affecting treatment success and patient survival. Even in patients who complete their chemotherapy, about 20% are left with long-term symptoms that substantially diminish their quality of life and functioning.

[0009] CIPN may develop slowly throughout chemotherapy or appear abruptly after several cycles of treatment with drugs such as oxaliplatin. Early identification of at-risk patients would be extremely valuable in informing care and preventing CIPN. Current CIPN prevention studies randomize chemotherapy recipients to interventions versus control, including patients who are at low risk and would not develop CIPN. A biomarker that can identify patients at risk would be extremely useful for stratified / personalized design targeting prevention approaches in high-risk patients only.SUMMARY OF THE INVENTION

[0010] Among the various aspects of the present disclosure is the provision of systems and methods for cold hypersensitivity assessments as an indicator for CIPN.

[0011] In one aspect, a computer-implemented method for predicting a chemotherapy-induced neuropathy (CIPN) condition in a subject undergoing a chemotherapy treatment is disclosed that includes receiving, at a computing device, one or more cold rankings from a subject, wherein the one or more cold rankings quantify the subject’s reaction to applying a cold test object to the subject. The method further includes storing, using the computing device, the oneor more cold rankings into a cold ranking database, the cold ranking database comprising the one or more cold rankings and a plurality of previously obtained cold rankings. The method further includes transforming, using the computing device, at least a portion of the cold ranking database into at least one summary parameter. The method further includes transforming, using the computing device, the at least one summary parameter into a prediction category selected from subject not likely to develop the CIPN condition and subject likely to develop the CIPN condition. The method further includes transmitting, using the computing device, the prediction category to a practitioner device. In some aspects, the method further includes transforming, using the computing device, the prediction category into a recommendation for treatment; and transmitting, using the computing device, the recommendation for treatment to the practitioner device. The recommendation is selected from maintaining a dosage of the chemotherapy treatment if the classification comprises low risk of the CIPN condition; and reducing the treatment dosage or changing the treatment composition if the classification comprises low risk of the CIPN condition. In some aspects, the method further includes applying the cold test object to the subject for a predetermined duration. In some aspects, the predetermined duration comprises about ten seconds. In some aspects, the cold test object is a stainless- steel cylinder configured to be gripped in a hand of the subject. In some aspects, the cold test object is maintained at a temperature ranging from 0 degrees C to 16 degrees C. In some aspects, the cold rankings are selected from a pain score, an unpleasantness score, and any combination thereof. In some aspects, transforming the at least a portion of the cold ranking database into at least one summary parameter further includes dividing, using the computing device, at least a portion of the cold ranking database into at least one group; and transforming, using the computing device, each group of the at least one group of cold rankings into one portion of the at least one summary parameters. Each group includes one portion of the cold rankings obtained during one recurring interval of a chemotherapy treatment cycle of the subject. In some aspects, the at least one summary parameter is selected from at least one of: an area under the curve for each chemotherapy treatment cycle, a maximum rating within each chemotherapy treatment cycle, a range between minimum and maximum ratingswithin each chemotherapy treatment cycle, and a maximum rate of increase of ratings within each chemotherapy treatment cycle. In some aspects, the at least one summary parameter is the area under the curve for each of the chemotherapy treatment cycles. In some aspects, the method further includes comparing the areas under the curve for each of the chemotherapy treatment cycles. In some aspects, transforming the at least one summary parameter into a prediction category further includes comparing the areas under the curve for each of the chemotherapy treatment cycles to at least one threshold value comprising a high-risk threshold value. The subject is assigned a prediction category of high risk of the CIPN condition if the AUC exceeds the high-risk threshold value or assigned a prediction category of low risk of the CIPN condition if the AUC falls below the high-risk threshold value. In some aspects, the method further includes executing, using the computing device, a trained machine learning model to determine the prediction category based on the cold ranking database.

[0012] In another aspect, a system for predicting a chemotherapy-induced neuropathy (CIPN) condition in a subject undergoing a chemotherapy treatment is disclosed. The system includes a cold test object comprising a stainless-steel cylinder configured to be gripped in a hand of the subject for a predetermined duration of about ten seconds, wherein the cold test object is maintained at a temperature ranging from 0 degrees C to 16 degrees C; and a computing device comprising at least one processor. The at least one processor is configured to receive one or more cold rankings from a subject, the one or more cold rankings quantifying the subject’s reaction to applying the cold test object, wherein the one or more cold rankings are selected from a pain score, an unpleasantness score, and any combination thereof. The at least one processor is further configured to store the one or more cold rankings into a cold ranking database, the cold ranking database comprising the one or more cold rankings and a plurality of previously obtained cold rankings. The at least one processor is further configured to transform at least a portion of the cold ranking database into at least one summary parameter. The at least one processor is further configured to transform the at least one summary parameter into a prediction category selected from subject not likely to develop the CIPN condition and subject likely to develop theCIPN condition. The at least one processor is further configured to transform the prediction category into a recommendation for treatment; and transmit the recommendation for treatment to a practitioner device. In some aspects, the recommendation for treatment is selected from maintaining a dosage of the chemotherapy treatment if the classification comprises low risk of the CIPN condition; and reducing the treatment dosage or changing the treatment composition if the classification comprises low risk of the CIPN condition. In some aspects, the at least one processor is further configured to: divide at least a portion of the cold ranking database into at least one group, each group comprising one portion of the cold rankings obtained during one recurring interval of a chemotherapy treatment cycle of the subject; and t transform each group of the at least one group of cold rankings into one portion of the at least one summary parameters. In some aspects, determining the prediction category of the subject developing the CIPN condition based on the at least one summary parameter further includes comparing the summary parameter for each of the chemotherapy treatment cycles to at least one threshold value comprising a high- risk threshold value. The subject is assigned a prediction category of high risk of developing the CIPN condition if the summary parameter exceeds the high-risk threshold value and a prediction category of low risk of developing the CIPN condition if the summary parameter is below the high-risk threshold value. In some aspects, the at least one summary parameter is selected from at least one of: an area under the curve for each chemotherapy treatment cycle, a maximum rating within each chemotherapy treatment cycle, a range between minimum and maximum ratings within each chemotherapy treatment cycle, and a maximum rate of increase of ratings within each chemotherapy treatment cycle.

[0013] Other objects and features will be in part apparent and in part pointed out hereinafter.DESCRIPTION OF THE DRAWINGS

[0014] Those of skill in the art will understand that the drawings, described below, are for illustrative purposes only. The drawings are not intended to limit the scope of the present teachings in any way.

[0015] FIG. 1 illustrates a block diagram of a system for monitoring a patientto detect peripheral neuropathy in accordance with an embodiment.

[0016] FIG. 2 is a flowchart illustrating an example process of monitoring a patient to detect peripheral neuropathy using the system shown in FIG. 1 .

[0017] FIG. 3 is a simplified block diagram of an example system for monitoring a patient to detect peripheral neuropathy using the process shown in FIG. 2 in accordance with the system shown in FIG. 1 .

[0018] FIG. 4 illustrates an example configuration of a client computer device shown in FIG. 3.

[0019] FIG. 5 illustrates an example configuration of the server system shown in FIG. 3.

[0020] FIG. 6A is a graph summarizing the daily patient-reported pain responses to holding a cold rod for 10 seconds over a course of chemotherapy administered every 14 days; each line corresponds to an individual patient.

[0021] FIG. 6B is a graph summarizing the daily patient-reported unpleasantness responses to holding a cold rod for 10 seconds over a course of chemotherapy administered every 14 days; each line corresponds to an individual patient.

[0022] FIG. 7A is a graph comparing the average daily patient-reported pain response to holding a cold rod for 10 seconds over a course of chemotherapy administered every 14 days, in which a portion of the patients was administered lidocaine, and a portion was administered a placebo.

[0023] FIG. 7B is a graph comparing the average daily patient-reported unpleasantness response to holding a cold rod for 10 seconds over a course of chemotherapy administered every 14 days, in which a portion of the patients was administered lidocaine, and a portion was administered a placebo.

[0024] FIG. 8A is a graph (top) showing the average daily patient-reported pain response to holding a cold rod for 10 seconds over a single cycle of chemotherapy, in which a portion of the patients were administered intravenous lidocaine as a CIPN prevention approach and a second portion of the patients were administered a placebo. A table (bottom) summarizes average areas under the curve (AUCs) for the patient populations as well as the percentage of daysthat patients reported pain scores of over 4 and over 7.

[0025] FIG. 8B is a graph (top) showing the average daily patient-reported unpleasantness response to holding a cold rod for 10 seconds over a single cycle of chemotherapy, in which a portion of the patients were administered intravenous lidocaine as a CIPN prevention approach and a second portion of the patients were administered a placebo. A table (bottom) summarizes average areas under the curve (AUCs) for the patient populations as well the percentage of days that patients reported unpleasantness scores of over 4 and over 7.

[0026] FIG. 9A is a graph showing the average AUCs of daily patient- reported pain response to holding a cold rod for 10 seconds over a single cycle of chemotherapy for patients exhibiting dose-limiting CIPN (i.e. needed to stop chemotherapy or reduce chemotherapy dose due to CIPN), other dose-limiting toxicity symptoms (other DLT), and no dose-limiting toxicity symptoms (no DLT).

[0027] FIG. 9B is a graph showing the average AUCs of daily patient- reported unpleasantness responses to holding a cold rod for 10 seconds over a single cycle of chemotherapy for patients exhibiting dose-limiting CIPN (i.e. needed to stop chemotherapy or reduce chemotherapy dose due to CIPN), other dose-limiting toxicity symptoms (other DLT), and no dose-limiting toxicity symptoms (no DLT).

[0028] FIG. 10A is a graph showing the average AUCs of daily patient- reported pain response to holding a cold rod for 10 seconds over a single cycle of chemotherapy for patients exhibiting dose-limiting CIPN (DLT) and no doselimiting toxicity symptoms (no DLT) stratified into DLT risk levels (low, medium, and high).

[0029] FIG. 10B is a graph showing the average AUCs of daily patient- reported unpleasantness response to holding a cold rod for 10 seconds over a single cycle of chemotherapy for patients exhibiting dose-limiting CIPN (DLT) and no dose-limiting toxicity symptoms (no DLT) stratified into DLT risk levels (low, medium, and high).DETAILED DESCRIPTION OF THE INVENTION

[0030] The present disclosure is based, at least in part, on the discoverythat Allo-Cold technology - a system that incorporates at-home cold-evoked hypersensitivity testing with a customized metal rod with a mobile application for data capture and processing, to predict individual risk of CIPN development. Communicating this risk prediction will inform shared decision-making between the care team and the patient. Allo-Cold uses a 10-second daily cold sensitivity quantification to predict CIPN. This biomarker will be fast and straightforward, allowing high adherence and scalability for adoption in diverse environments.

[0031] Currently, there are no validated methods for the early identification of patients at high risk for CIPN. Moreover, no targeted intervention has consistently mitigated CIPN without first identifying high-risk patients. Although several interventions potentially prevent CIPN, patients are often reluctant to try them due to side effects unless identified as high risk. Modified chemotherapy regimens, such as less intense dosing or extended cycle lengths, offer alternatives, but physicians hesitate to recommend them without strong indications that the current regimen puts their patients at high risk for CIPN. While several clinical biomarkers for CIPN prediction are in development, such as those from skin biopsies and nerve conduction studies, most require specialized equipment and highly trained staff, limiting their feasibility and scalability, especially in low-resource settings.

[0032] Disclosed herein is a method for cold hypersensitivity assessment for early detection of CIPN that is scalable and accessible and reduces opioid use. In some aspects, the Allo-Cold system predicts CIPN early, allowing for interventions that prevent the onset of severe symptoms and improve patient outcomes and quality of life. Allo-Cold system is also scalable and accessible, even in low-resource settings, making it a valuable tool for a wide range of healthcare environments and helping to reduce health disparities among cancer patients. In other aspects, the Allo-Cold system reduces the need for long-term opioid treatments by preventing the development of severe CIPN, which is often prescribed to manage chronic pain associated with CIPN. It contributes to a lower risk of opioid dependency and related complications.

[0033] In various aspects, a method for detecting a chemotherapy-induced neuropathy (CIPN) condition is disclosed that includes storing a plurality ofprevious cold ratings from a patient, providing the patient with a cold test object, applying the cold test object to the patient for a period of time, receiving one or more cold rankings from the patient based on the application of the cold test object to the patient, analyzing the one or more cold rankings and the plurality of previous cold rankings to determine at least one summary parameter, determining a category of the patient developing the CIPN condition based on the at least one summary parameter and transmitting the category to a practitioner computer device. In some aspects, the disclosed combines a tool to assess cold- induced pain and sensitivity in patients receiving potentially neurotoxic chemotherapy with an app for daily data entry of the results of the mentioned cold testing. In an exemplary embodiment, Allo-Cold technology for cold sensitivity quantification is an early susceptibility / risk biomarker for CIPN. The components of the technology include a) a custom-made metal rod that allows stable temperature maintenance with refrigeration for consistent at-home assessment of palmar cold hypersensitivity (already exists and production established), b) interface and data entry of the web application for data collection, c) backend data aggregation, storing and processing for analysis by study team members (overall outline in Fig. 1 ). The Allo-Cold system utilizes cold hypersensitivity quantification as a clinical biomarker for the early prediction of CIPN, resulting in a simple, reliable, scalable, and patient-centered technology. The system aids in early risk prediction of CIPN, facilitating shared decision-making to mitigate painful CIPN and its associated morbidity in patients with colorectal cancer and potentially other types of cancer.

[0034] In various aspects, the plurality of previous cold ratings is obtained from previous applications of the cold test object to the patient. In some aspects, the level of pain and the unpleasantness of the patients' cold sensations are recorded over the course of oxaliplatin chemotherapy treatment administered every 14 days (FIGS. 6A and 6B). In an exemplary embodiment, patients are daily subjected to a cold sensitivity test, where they hold the rod in their hand for a predetermined period and rate their sensitivity to cold on a numerical scale. These ratings are collected daily throughout the chemotherapy treatment cycle, providing a comprehensive dataset of the patient's cold sensitivity over time. Each rating reflects the patient's experience of cold sensitivity at a specific point,and together, these ratings provide a comprehensive view of how the patient's sensitivity changes throughout their chemotherapy treatment cycles. This continuous data collection allows for detailed analysis and comparison of cold sensitivity trends across different treatment cycles. The previous cold ratings are derived from earlier applications of the cold test object to the patient.

[0035] In various aspects, the cold test object is a stainless-steel cylinder. In some aspects, the cold test object is a custom-made solid metal cylinder with a height of 10 cm and a diameter of 5 cm, which the patients keep in their home refrigerator and use instructions for daily measurements (that take less than 1 minute). In other aspects, the patient holds the rod in their hand for a predetermined period, including, but not limited to, 10 seconds, and rates the level of pain and / or the level of unpleasantness of the cold sensation.

[0036] In various aspects, a surface of the cold test object is applied to the patient at a temperature ranging from 0 to 16 degrees Celsius. In some aspects, the custom-made metal rod is designed to maintain a stable temperature with refrigeration, allowing for consistent at-home assessment of palmar cold hypersensitivity. In other aspects, the test object is maintained at a temperature ranging from 0 to 16 degrees Celsius since some individuals have less or more severe cold hypersensitivity. In an exemplary embodiment, the surface temperature of the Allo-Cold rod, when kept under home refrigeration conditions, remains stable, averaging between 8.8°C and 11.0°C within 30-120 seconds upon removal from the refrigerator. The temperature increase of the Allo-Cold rod is linear, 0.08°C per minute, and the overall temperature increase is 1.0°C in 12 minutes, demonstrating excellent temperature stability for assessing cold sensitivity within the recommended time of removing the rod from home refrigeration.

[0037] In various aspects, analyzing the one or more rankings and the plurality of previous cold rankings to determine at least one summary parameter further includes dividing the plurality of previous cold ratings into at least two groups based on a recurring interval of a chemotherapy treatment cycle of the patient, and analyzing the one or more previous rankings and the plurality of cold ratings based on each group of the at least two groups. In some aspects, previouscold ratings are divided into groups based on the chemotherapy treatment cycle intervals. In an exemplary embodiment, the cold sensitivity data obtained daily through the Allo-Cold method are grouped into intervals corresponding to each 14-day cycle (FIGS. 6A and 6B). This method enables a comparative analysis of the patient's cold sensitivity within consistent periods, allowing for the observation of trends and changes in response to each chemotherapy treatment cycle.

[0038] In other aspects, each group of ratings is analyzed to determine trends or changes within each defined chemotherapy treatment interval, including calculating the AUC unpleasantness and AUC pain within each group (FIGS. 8A and 8B). In an exemplary embodiment, the method involves patients assessing their cold sensitivity daily by placing their hand on a pre-refrigerated metal rod for 10 seconds. This method quantifies the intensity of cold unpleasantness and pain on a 0-10 numerical rating scale. The cold sensitivity assessments for each chemotherapy treatment cycle are evaluated, allowing for a detailed comparison of how cold sensitivity varies overtime within these specific periods. By reviewing the cold ratings in each group, the intensity of cold unpleasantness and pain changes are discerned to determine the rate of change and predict the likelihood of dose-limiting CIPN.

[0039] In various aspects, the summary parameter is any suitable parameter capable of assessing cold sensitivity by the patient upon a 10-second hand contact with a pre-refrigerated metal rod. Non-limiting examples of suitable summary parameters include an area under the curve for each chemotherapy treatment cycle, a maximum rating within each chemotherapy treatment cycle, a range between minimum and maximum ratings within each chemotherapy treatment cycle, and a maximum rate of increase of ratings within each chemotherapy treatment cycle. In one aspect, the summary parameter is an area under the curve for each chemotherapy treatment cycle. The cycle AUC represents the total accumulated sensitivity to cold over one chemotherapy treatment cycle (FIGS. 8A and 8B). The overall level of cold sensitivity experienced by a patient during each cycle is quantified by calculating the AUC. In another aspect, the summary parameter is a maximum rating within each chemotherapy treatment cycle. The maximum rating is the highest cold sensitivity rating reported by the patient during a chemotherapy treatment cycle (FIGS. 7Aand 7B). The peak sensitivity rating within a cycle means the most extreme level of cold unpleasantness or cold pain the patient experiences, assessing the worstcase scenario for cold sensitivity during treatment. In another aspect, the summary parameter is a range between minimum and maximum ratings within each chemotherapy treatment cycle. The range is the difference between the lowest and highest cold sensitivity ratings reported within a chemotherapy treatment cycle, showing the variability and the fluctuations in cold sensitivity within a cycle (FIGS. 7A and 7B).

[0040] In some aspects, the method further includes comparing the areas under the curve for each chemotherapy treatment cycle. This method involves calculating the AUC for each cycle and comparing these values across different cycles (FIGS. 9A and 9B). Comparing the cycle AUCs consists of examining how the total cold sensitivity (as quantified by AUC) changes from one chemotherapy treatment cycle to the next. Comparing the cycle AUCs helps identify trends in a patient's cold sensitivity throughout their chemotherapy treatment and determine if a patient eventually develops dose-limiting CIPN or if there is an early identification of patients who will develop dose-limiting neurotoxicity.

[0041] In various aspects, determining the category of the patient developing the CIPN condition based on the at least one summary parameter further includes comparing the areas under the curve for each of the chemotherapy treatment cycles to at least one threshold value comprising a high- risk threshold value, wherein the patient is assigned a category of high risk of the CIPN condition if the AUC exceeds the high-risk threshold value. In an exemplary embodiment, the method uses daily assessments of cold sensitivity, where patients rate the pain and unpleasantness of holding a pre-refrigerated metal rod, with these ratings being recorded. These ratings calculate the AUC for cold unpleasantness and pain over a 14-day interval between chemotherapy treatment cycles. If the AUC values exceed the high-risk threshold, the patient is categorized as high risk for developing dose-limiting CIPN (FIGS. 10A and 10B). The method enables early identification of patients at risk for neuropathy (4-16 weeks before developing painful CIPN) and integrates with an app to provide EMR reports for shared decision-making between patients and their oncologists regarding treatment adjustments.

[0042] Although the systems, devices, and methods are described herein in terms of CIPN associated with Oxaliplatin treatment, the disclosed systems, devices, and methods may be used to identify, stratify, predict, and / or otherwise characterize CIPN associated with any other treatment known to be associated with the development of CIPN. Non-limiting examples of other treatments include Oxaliplatin, Cisplatin, Carboplatin, Paclitaxel, Docetaxel, Vincristine, Vinblastine, Bortezomib, Thalidomide, and Brentuximab. It is to be noted that different treatment compositions may induce neuropathy and cold hypersensitivity at different rates, with different presentations, and at different dosages as compared to Oxaliplatin.

[0043] In various aspects, the systems and methods described herein can be used as a biomarker to detect which patients are most likely to develop neuropathy to allow the healthcare provider to counteract or prevent the likelihood from developing into full-blown neuropathy. This biomarker could also be used to determine which patients would be the most likely to need treatment for neuropathy and thus allow those patients to be chosen for potential treatments, including those treatments that are being tested in studies. The ability to detect patients likely to develop neuropathy can also be used for choosing patients for different treatment studies.

[0044] In various aspects, the system further includes executing a trained machine learning model to determine the category based on the one or more cold rankings and the one or more previous rankings. In some aspects, the model analyzes daily cold sensitivity ratings and compares them with previous data to predict if a patient is at high risk. In other aspects, the system's high accuracy is supported by extensive patient data and advanced algorithms, with improvements incorporating additional data like rod surface temperature. In an exemplary embodiment, the algorithm is developed based on a dataset from over 2,000 patient days, where high adherence (>90%) was achieved through daily paper-pencil entries of cold hypersensitivity. The algorithm is configured with an AUROC of 0.81 , demonstrating 83% specificity and 67% sensitivity in predicting dose-limiting CIPN 2-4 months later. The system utilizes a trained machine learning model to analyze the collected cold sensitivity ratings (cold rankings) and previous ratings to predict the risk category for CIPN by comparing new coldsensitivity data with previous cold data.

[0045] As described in the examples below, a user-centered mobile app with a three-tier architecture is developed to facilitate the collection, processing, storing, and aggregation of palmar cold sensitivity data using a pre-refrigerated Allo-Cold rod. In various aspects, the presentation tier includes a user-friendly interface for entering cold pain, cold unpleasantness, and rod surface temperature information, along with a timer for accurate 10-second contact measurement. In some aspects, the application tier enables data aggregation and storage, while the data process / logic tier calculates AUC pain and AUC unpleasantness between treatment cycles. The app prototype must securely prompt and capture daily patient testing and self-reporting, depositing responses in the cloud. It will undergo iterative testing and refinement to resolve major usability issues until it meets acceptability criteria.

[0046] As further described in the examples below, the Allo-Cold system prototype in oxaliplatin-based chemotherapy will be tested. Twenty-four patients with stage lll / IV colorectal cancer will use the Allo-Cold system and self-report cold pain and cold unpleasantness daily for ten weeks (5 cycles) of oxaliplatinbased chemotherapy. Patients will be monitored for the occurrence of CIPN over 24 weeks from the beginning of chemotherapy, with adherence recorded and biweekly feedback collected. The main inclusion criteria are adults >18 years old, diagnosed with Stage III or IV CRC, planned to undergo oxaliplatin-based chemotherapy (any regimen with >8 planned cycles), and possessing a smartphone. Enrolled patients will receive an Allo-Cold metal rod, instructions, and training using the app via web access on mobile devices. Peripheral neuropathy will be graded using CTCAE v5.0 criteria, with additional assessments and patient feedback collected. Combining new and existing data aims to confirm the algorithm's predictive performance and fine-tune the CIPN prediction algorithm. Interviews will also gather further usability data, ensuring a functional prototype with patient-centered design elements.PERIPHERAL NEUROPATHY MONITORING SYSTEM

[0047] FIG. 1 illustrates a block diagram of a system 100 for monitoring a patient to detect peripheral neuropathy in accordance with an embodiment. In theexemplary embodiment, the patient has access to a test object 105. In the exemplary embodiment, the test object 105 is any object that be cooled to a desired temperature, such as by placing the test object 105 in a refrigerator or freezer. In some embodiments, the test object 105 is a solid metal object, such as a cylinder. In various aspects, any suitable object capable of contacting at least a portion of the patient’s fingers and hand for a suitable duration and maintain a surface temperature within the range as described herein may be used as the test object. In one example, the test object 105 is a stainless-steel cylinder with a height of 10 cm and a diameter of 5 cm. In some further embodiments, the test object 105 is a glove, a ski pole handle, a ball, and / or any other object that will keep a cool temperature for a period of time. The test object 105 is kept cold so that it can be used to test the cold tolerances of the patient. In some embodiments, the test object 105 is kept at a temperature of 46 degrees Fahrenheit (8 degrees Celsius) or lower. However, since some individuals have less or more severe cold hypersensitivity the temperature of the test object 105 is maintained above a minimum temperature of about 32 degrees Fahrenheit (0 degrees Celsius) depending on the degree of cold hypersensitivity of the individual. In the exemplary embodiment, the test object 105 is maintained at a temperature range from 0 to 16 degrees Celsius.

[0048] In various aspects, the test object is maintained at a temperature ranging from 0 to 16 degrees Celsius, from 0 to 15 degrees Celsius, from 0 to 14 degrees Celsius, from 0 to 13 degrees Celsius, from 0 to 12 degrees Celsius, from 0 to 11 degrees Celsius, from 0 to 10 degrees Celsius, from 0 to 9 degrees Celsius, from 0 to 8 degrees Celsius, from 0 to 7 degrees Celsius, from 0 to 6 degrees Celsius, from 0 to 5 degrees Celsius, from 0 to 4 degrees Celsius, from 0 to 3 degrees Celsius, and from 0 to 2 degrees Celsius. In various other aspects, the test object is maintained at a temperature ranging from 0 to 2 degrees Celsius, from 1 to 3 degrees Celsius, from 2 to 4 degrees Celsius, from 3 to 5 degrees Celsius, from 4 to 6 degrees Celsius, from 5 to 7 degrees Celsius, from 6 to 8 degrees Celsius, from 7 to 9 degrees Celsius, from 8 to 10 degrees Celsius, from 9 to 11 degrees Celsius, from 10 to 12 degrees Celsius, from 11 to 13 degrees Celsius, from 12 to 14 degrees Celsius, and from 13 to 15 degrees Celsius.

[0049] The patient holds 110 the test object 105 for a pre-determinedperiod of time including, but not limited to, 10 seconds or a count of ten. In the exemplary embodiment, test object 105 is designed so that it can be held by an individual in such a way that all of their fingers and a portion of the palm of one hand can be in contact with test object 105 simultaneously. The test object 105 is adjusted to fit a particular patient or their particular situation. After the patient has held the chilled test object 105 for the predetermined period of time, the patient records 115 their experience holding 110 the test object 105.

[0050] In the exemplary embodiment, the patient records 115 their experience using a user device 120. The user device 120 may display a user interface that facilitates the patient recording 115 their experience. The user interface may allow the patient to enter information about their completion 125 as well as rate 130 their pain and / or unpleasantness when holding the test object 105. Unpleasantness, for example, can include stinging and / or pricking feelings. In the illustrated embodiment, the patient enters the rating 130 on a scale of 1 to 10. In other embodiments, the rating 130 could be a pull-down menu of words associated with different feelings and / or levels of pain or any other rating method that allows the system 100 to work as described herein.

[0051] In some aspects, the rating comprises a pain score comprising a numerical score reported by a subject in response to contacting the cold test object. In various aspects, the pain score ranges from a minimum pain score through a maximum pain score. The minimum pain score corresponds to the subject experiencing no pain and the maximum pain score corresponds to the subject experiencing extremely high pain. In various aspects, the minimum pain score is selected from zero or one. In various other aspects, the maximum pain score is selected from one, two, three, four, five, six, seven, eight, nine, ten, twenty, thirty, forty, fifty, and one hundred.

[0052] In other aspects, the rating comprises a discomfort score comprising a numerical score reported by a subject in response to contacting the cold test object. In various aspects, the discomfort score ranges from a minimum discomfort score through a maximum discomfort score. The minimum discomfort score corresponds to the subject experiencing no discomfort and the maximum score corresponds to the subject experiencing extremely high discomfort. Invarious aspects, the minimum discomfort score is selected from zero or one. In various other aspects, the maximum discomfort score is selected from one, two, three, four, five, six, seven, eight, nine, ten, twenty, thirty, forty, fifty, and one hundred.

[0053] In some further embodiments, the user interface has a timer that displays the elapsed time that the patient 110 holds the test object 105. In still additional embodiments, the test object 105 includes a thermometer or thermocouple that allows it to send the current temperature of the surface of the test object 105 to the user device 120. In other embodiments, the test object 105 includes an active cooling system that allows the surface of the test object 105 to be cooled to the desired temperature.

[0054] The user device 120 transmits the ratings 130 to the patient neuropathy analysis (PNA) computer device 310 (shown in FIG. 3). The PNA computer device 310 performs analysis 135 on the ratings 130. In the exemplary embodiment, the PNA computer device 310 receives ratings 130 for a plurality of days, where the patient may hold 110 the test object 105 once a day and record 115 ratings 130 of their experience. The PNA computer device 310 analyzes 135 the plurality of ratings 130 received from the patient to detect any patterns. In some embodiments, the PNA computer device 310 includes a trained machine learning model, such as a neural network, which is trained to detect potential warning signs of neuropathy based on the analysis 135 of the ratings 130 over time.

[0055] In still further embodiments, the PNA computer device 310 receives and analyzes 135 a plurality of ratings 130 over a plurality of time from a plurality of patients. In some aspects, the PNA computer device 310 may compare the ratings 130 of different patients to look for warning signs of neuropathy. In other aspects, the PNA computer device 310 may analyze the plurality of ratings over a plurality of times to generate at least one summary parameter. In still further embodiments, the PNA computer device 310 may receive additional information about the patient, their conditions, and medications, such as, but not limited to, height, weight, age group, gender, and / or other information that allows the PNA computer device 310 to compare and contrast different patients when looking forpatterns.

[0056] By way of non-limiting example, FIGS. 6A and 6B are graphs summarizing patient-reported pain and unpleasantness ratings over seven courses of oxaliplatin chemotherapy treatment administered every 14 days. FIGS. 7A and 7B are graphs summarizing the patient-reported pain and unpleasantness ratings over seven courses of oxaliplatin chemotherapy treatment administered every 14 days, in which a portion of the patients were also administered lidocaine.

[0057] In various aspects, the summary parameter may include any suitable numerical value derived from at least a portion of the plurality of ratings over the plurality of times. In some aspects, a summary parameter is defined with respect to a single cycle of chemotherapy. Non-limiting examples of suitable summary parameters include an area under the curve for each chemotherapy treatment cycle, a maximum rating within each chemotherapy treatment cycle, a range between minimum and maximum ratings within each chemotherapy treatment cycle, a maximum rate of increase of ratings within each chemotherapy treatment cycle, and any other suitable summary parameter without limitation.

[0058] In at least one embodiment, the PNA computer device 310 calculates an area 138 under the curve for each cycle between treatments, such as chemotherapy treatments. For example, the treatment interval may be once every two weeks. The PNA computer device 310 calculates the area 138 under the curve for the patient for the two weeks between treatments and then compares that area 138 to the area 138 from other intervals. The PNA computer device 310 can compare the rate of change of the area between each of the intervals or cycles. The PNA computer device 310 can compare the difference in change between the intervals or cycles. In one embodiment, the PNA computer device 310 compares the area 138 under the curve for the first cycle and the fourth cycle to determine how to categorize 140 the patient. While the cycle time of two weeks is described above, the cycle time could be more or less time depending on the treatment that the patient is undergoing.

[0059] In various aspect, the cycle time is 2 days, three days, four days, five days, six days, seven days, 10 days, 12 days, 15 days, 20 days, three weeks, four weeks, five weeks, 2 months, and 3 months.

[0060] In the exemplary embodiment, the PNA computer device 310 categorizes 140 the patient based on their likelihood of having developed CIPN, or to their likelihood to develop CIPN over time in subsequent courses of treatment. In the illustrated embodiment, the categories 140 include low, medium, and high likelihoods. In some embodiments, the categories 140 may be provided as a percentile estimate of risk for developing CIPN. Non-limiting examples include categories such as 25% risk or 10% higher risk from baseline. In various aspects, the percentile estimate of risk includes 5% risk, 10% risk, 15% risk, 20% risk, 25% risk, 30% risk, 35% risk, 40% risk, 45% risk, 50% risk, 55% risk, 60% risk, 65% risk, 70% risk, 75% risk, 80% risk, 85% risk, 90% risk, 95% risk, and 100% risk from baseline. The PNA computer device 310 transmits 145 the category 140 to one or more computer devices, such as healthcare provider devices 305 (shown in FIG. 3).

[0061] The healthcare provider can determine how to proceed with the patient’s treatment based on their risk category 140 for developing CIPN. In some embodiments, the healthcare provider may increase the interval between treatments, change the treatment dose or other treatment parameters. In still further embodiments, the healthcare provider can change the patient to a different treatment, such as a different chemo treatment. The healthcare provider could also begin to treat the neuropathy before the symptoms become severe, such as by using one or more drugs or other neuropathy treatment regimes.

[0062] In some embodiments, the PNA computer device 310 transmits 145 the category 140 to the healthcare provider via a notification, such as a text message or email. In other embodiments, the PNA computer device 310 is integrated with or in communication with the patient’s electronic health records (EHR). In these embodiments, the PNA computer device 310 is capable of updating the patient’s EHR. The PNA computer device 310 may format the category 140 for integration with digital health records.

[0063] In at least one embodiment, the PNA computer device 310 categorizes 140 the patient in comparison to historical analysis of other patients. The PNA computer device 310 determines the level of pain and unpleasantness over a period of time between treatments. For example, the period betweentreatments could be two weeks. During each two-week period, the PNA computer device 310 maps the pain and unpleasantness ratings 130 provided by the patient. The PNA computer device 310 determines the curve based on the ratings and calculates the area 138 under the curve. The PNA computer device 310 compares the areas 138 under the curves to each interval to the areas 138 for the different intervals of previous patients that did develop CIPN. In some further embodiments, the PNA computer device 310 uses areas 138 under the curves for a plurality of historical patients to determine one or more indicators of the potential to develop CIPN based on cold hypersensitivity. In various embodiments, these indicators may be used by healthcare providers to monitor and adjust a course of treatment or by clinical researchers to assess the potential to develop CIPN in the context of a clinical trial or other clinical research context.Peripheral Neuropathy Monitoring Method

[0064] FIG. 2 is a flowchart illustrating an example process 200 of monitoring a patient to detect peripheral neuropathy using the system 100 (shown in FIG. 1 ). In the exemplary embodiment, one or more steps of process 200 are performed by the PNA computer device 310 (shown in FIG. 3).

[0065] In the exemplary embodiment, the patient is provided at 205 with a cold test object 105 (shown in FIG. 1 ). The cold test object 105 is kept chilled so that the surface area is cool to the touch. For example, the surface of the cold test object 105 can range from 0 to 16 degrees Celsius as described above.

[0066] In the exemplary embodiment, the patient is in contact with the cold test object 105 for a predetermined period of time at 210. In some embodiments, the patient 110 holds (as shown in FIG. 1 ) the cold test object 105 in their hand. In other embodiments, the cold test object 105 is placed against a portion of the patient’s anatomy, such as the patient’s shoulder or outer leg. In one example, the predetermined period of time may range from 5 seconds to 30 seconds or longer. In the exemplary embodiment, the period of time remains constant for every time the patient is in contact with the cold test object 105 at 210.

[0067] In the exemplary embodiment, the PNA computer device 310 receives at 215 patient pain ratings 130 (shown in FIG. 1 ) quantifying the pain experienced by the patient over the period of time that the patient was in contactwith the cold test object 105 at 210. In the exemplary embodiment, the pain ratings 103 include the pain level and unpleasantness level that the patient experienced while in contact with the cold test object 105 at 210. In some further embodiments, there may be additional ratings 130, such as, but not limited to, initial pain, initial unpleasantness, final pain, final unpleasantness, highest pain, and highest unpleasantness, for example. In the exemplary embodiment, the ratings 130 are defined on a scale of one to ten. In other embodiments, the ratings 130 can be any other rating system that allows the systems and methods to work as described herein.

[0068] Referring again to FIG. 2, the computer device receives and stores the patient pain ratings at 215 over a predetermined number of days (N) prior to analyzing the patient ratings at 220. In the exemplary embodiment illustrated in FIG. 2, the PNA computer device 310 analyzes at 220 the patient ratings 130 over a selected number of episodes of patient contact with the chilled object and pain rating at 205-235. These episodes are counted using an index N at 250. In some embodiments, the patient pain ratings are received and stored at 235, and the number of cycles N is counted, and when N is determined to exceed a threshold number of cycles Nassess at 240, the PNA computer device 310 analyzes at 220 the patient ratings 130. In various embodiments, the threshold number of cycles Nassess may be any suitable number of days without limitation. In some aspects, the threshold number of cycles Nassess ranges from one day (corresponding to daily analysis and category determination) to a higher number of days equivalent to a duration of one or more chemotherapy treatment cycles. In at least one embodiment, Nassess is the number of days between treatments including, but not limited to, chemotherapy treatments, that the patient receives.

[0069] In the exemplary embodiment, the PNA computer device 310 analyzes at 220 the patient ratings 130 by generating a curve of ratings 130 for each cycle and comparing the area 138 (shown in FIG. 1 ) under each curve. In some embodiments, the PNA computer device 310 analyzes 220 the change in area 138 between individual cycles, a change in area 138 between each cycle, a rate of change, and / or any other combination of analysis as described herein.

[0070] By way of non-limiting example, FIGS. 8A and 8B are graphssummarizing the patient-reported pain and unpleasantness ratings over one course of oxaliplatin chemotherapy treatment administered every 14 days, in which a portion of the patients were also administered lidocaine.

[0071] Referring again to FIG. 2, in some embodiments, the PNA computer device 310 analyzes at 220 the patient ratings 130 over an assessment period A / assess corresponding to one or more chemotherapy treatment cycles to determine at 225 a category 140 for the patient, where the category 140 is indicative of the likelihood that the patient will develop neuropathy or another condition including, but not limited to, CIPN based on the patient’s indication of hypersensitivity to cold. In some embodiments, the categories 140 are low, medium, or high. In other embodiments, the categories 140 are numbers, such as on a scale from one to ten, a percentage chance, a combination of multiple types, and / or any other category system to allow a viewer to quickly understand the likelihood that the patient will develop neuropathy or any other analyzed condition. In the exemplary embodiment, the PNA computer device 310 compares the changes in cold hypersensitivity of the patient to historical changes in cold hypersensitivity based on whether or not those patients developed neuropathy.

[0072] In some aspects, the patient ratings at different time points over a chemotherapy treatment cycle are compared to threshold values defined empirically from ratings of populations of patients with and without chemotherapy induced peripheral neuropathy (CIPN). By way of non-limiting example, FIGS. 10A and 10B show the average pain and discomfort ratings of patients with and without CIPN, in which threshold values for medium and high risk of developing CIPN are defined. By way of another non-limiting example, FIGS. 9A and 9B are graphs summarizing the areas under the curve (AUCs) of patient-reported pain and unpleasantness ratings over seven courses of oxaliplatin chemotherapy treatment administered every 14 days, as compared to patients with other doselimiting toxicities and patients with no dose-limiting toxicities; the patients with CIPN had much higher AUCs than the other patient groups starting at the fourth chemotherapy treatment cycle.

[0073] Referring again to FIG. 2, the PNA computer device 310 transmitsat 230 the patient category 140 to one or more practitioners, via their practitioner devices 305 (shown in FIG. 3). In various embodiments, the practitioner may be any suitably qualified medical practitioner or researcher without limitation. Nonlimiting examples of suitable practitioners include healthcare providers and members of research teams in clinical trials or other research scenarios. In some embodiments, the PNA computer device 310 formats and transmits 230 the patient category 140 to be integrated with one or more electronic health records (EHR) of the patient. The patient category 140 allows the healthcare provider an advanced warning that the patient may develop neuropathy and provides information that may be used by a healthcare provider or clinical researcher to support a decision to modify their treatment of the patient based on the category 140 and associated likelihood of developing dose-limiting toxicities. This modification can include but is not limited to, increasing the interval between treatments, reducing treatment dosage, changing treatment medicines, treating the neuropathy, a combination of the above, and / or any other available treatment to potentially reduce the neuropathy or the changes of the patient developing neuropathy.

[0074] Referring again to FIG. 2, after the patient category 140 is transmitted to one or more practitioners at 230, the number of cycles N is reset at 245, and another set of patient pain ratings 130 are obtained and stored at 205-235 for another cycle of Nassess days.

[0075] In some embodiments, the PNA computer device 310 trains a model using machine learning to determine the odds of a patient developing neuropathy based on a plurality of historical ratings 130 and results. In some embodiments, the model is constantly being updated based on other results and how the model categorized 225 different patients. In some embodiments, the model also includes other patient information, such as, but not limited to, vital statistics (age, weight, gender), medical history (other conditions that the patient has developed), family history, and or any other medical or personal information. The PNA computer device 310 may then use that patient information to detect differences between patients that develop neuropathy and those that do not. In some embodiments, the model categorizes 225 patients into those with high, medium, and low risk of developing neuropathy.

[0076] In the exemplary embodiment, the test object 105 is chilled at 235 for the next day’s test. In some embodiments, the test object 105 is chilled in a refrigerator, such as the patient’s refrigerator if the patient is at home. In other embodiments, the test object 105 includes a chilling module that reduces the temperature of the surface of the test object to be used in the future.

[0077] FIG. 3 is a simplified block diagram of an example system 300 for monitoring a patient to detect peripheral neuropathy using a process 200 (shown in FIG. 2) in accordance with the system 100 (shown in FIG. 1 ). In the example embodiment, system 300 is used for monitoring a patient to detect peripheral neuropathy using cold hypersensitivity assessments. In addition, system 300 is a real-time data analyzing and classifying computer system that includes a patient neuropathy analysis (PNA) computer device 310 (also known as a PNA server) configured to analyze patient reactions to cold hypersensitivity assessments and detect potential warning signs of peripheral neuropathy.

[0078] Practitioner devices 305 are configured to provide information to the practitioners (healthcare providers or clinical researchers), including whether or not the patient is developing early signs of peripheral neuropathy. The healthcare provider devices 305 connect to the PNA computer device 310 through various wired or wireless interfaces including without limitation a network, such as a local area network (LAN) or a wide area network (WAN), dial-in-connections, cable modems, Internet connections, wireless, and special high-speed Integrated Services Digital Network (ISDN) lines. Healthcare provider devices 305 can be any device capable of accessing a network, such as the Internet, including, but not limited to, a desktop computer, a laptop computer, a personal digital assistant (PDA), a cellular phone, a smartphone, a tablet, a phablet, or other web-based connectable equipment.

[0079] As described above in more detail, the PNA server 310 is programmed to analyze patient ratings 130 of pain and unpleasantness to detect signs of peripheral neuropathy and to warn one or more healthcare providers. The PNA server 310 is programmed to (1 ) determine the current conditions of a patient; (2) compare the patient's ratings over time to a model; and (3) determine if the patient is showing early signs of peripheral neuropathy. In otherembodiments, the PNA server 310 is in communication with one or more user devices 120, and the user devices 120 route the measurement data to the PNA computer device 310 in real-time or near real-time.

[0080] User devices 120 are computers that include a web browser or a software application, which enables User devices 120 to communicate with the PNA server 310 using the Internet, a local area network (LAN), or a wide area network (WAN). In some embodiments, user devices 120 are communicatively coupled to the Internet through many interfaces including, but not limited to, at least one of a network, such as the Internet, a LAN, a WAN, or an integrated services digital network (ISDN), a dial-up-connection, a digital subscriber line (DSL), a cellular phone connection, a satellite connection, and a cable modem. User devices 120 can be any device capable of accessing a network, such as the Internet, including, but not limited to, a desktop computer, a laptop computer, a personal digital assistant (PDA), a cellular phone, a smartphone, a tablet, a phablet, or other web-based connectable equipment.

[0081] A database server 315 is communicatively coupled to a database 320 that stores data. In one embodiment, database 320 is a database that includes historical rating data and the model. In some embodiments, database 320 is stored remotely from PNA server 310. In some embodiments, database 320 is decentralized. In the example embodiment, a person can access database 320 via healthcare provider devices 305 by logging onto PNA server 310.

[0082] FIG. 4 illustrates an example configuration of a client system 400. User computer device 402 is operated by a user 401 . User computer device 402 may include but is not limited to, user device 120 (shown in FIG. 1 ) and healthcare provider device 305 (shown in FIG. 3). User computer device 402 includes a processor 405 for executing instructions. In some embodiments, executable instructions are stored in a memory area 410. Processor 405 may include one or more processing units (e.g., in a multi-core configuration). Memory area 410 is any device allowing information such as executable instructions and / or transaction data to be stored and retrieved. Memory area 410 may include one or more computer-readable media.

[0083] User computer device 402 also includes at least one media outputcomponent 415 for presenting information to user 401 . Media output component 415 is any component capable of conveying information to user 401. In some embodiments, media output component 415 includes an output adapter (not shown) such as a video adapter and / or an audio adapter. An output adapter is operatively coupled to processor 405 and operatively coupleable to an output device such as a display device (e.g., a cathode ray tube (CRT), liquid crystal display (LCD), light emitting diode (LED) display, or “electronic ink” display) or an audio output device (e.g., a speaker or headphones). In some embodiments, media output component 415 is configured to present a graphical user interface (e.g., a web browser and / or a client application) to user 401. A graphical user interface may include, for example, an interface for adding ratings 130 (shown in FIG. 1 ). In some embodiments, user computer device 402 includes an input device 420 for receiving input from user 401 . User 401 may use input device 420 to, without limitation, select a rating 130. Input device 420 may include, for example, a keyboard, a pointing device, a mouse, a stylus, a touch-sensitive panel (e.g., a touchpad or a touch screen), a gyroscope, an accelerometer, a position detector, a biometric input device, and / or an audio input device. A single component such as a touch screen may function as both an output device of media output component 415 and input device 420.

[0084] User computer device 402 may also include a communication interface 425, communicatively coupled to a remote device such as PNA server 310 (shown in FIG. 3). Communication interface 425 may include, for example, a wired or wireless network adapter and / or a wireless data transceiver for use with a mobile telecommunications network.

[0085] Stored in memory area 410 are, for example, computer-readable instructions for providing a user interface to user 401 via media output component 415 and, optionally, receiving and processing input from input device 420. A user interface may include, among other possibilities, a web browser and / or a client application. Web browsers enable users, such as user 401 , to display and interact with media and other information typically embedded on a web page or a website from PNA server 310. A client application allows user 401 to interact with, for example, PNA server 310. For example, instructions may be stored by a cloud service, and the output of the execution of the instructions may be sent to themedia output component 415.

[0086] Processor 405 executes computer-executable instructions for implementing aspects of the disclosure. In some embodiments, the processor 405 is transformed into a special-purpose microprocessor by executing computer-executable instructions or by otherwise being programmed.

[0087] FIG. 5 illustrates an example configuration of the server system 310 (shown in FIG. 3). Server computer device 501 may include but is not limited to, PNA computer device 310 and database server 315 (both shown in FIG. 3). Server computer device 501 also includes a processor 505 for executing instructions. Instructions may be stored in a memory area 510. Processor 505 may include one or more processing units (e.g., in a multi-core configuration).

[0088] Processor 505 is operatively coupled to a communication interface 515 such that server computer device 501 is capable of communicating with a remote device such as another server computer device 501 , another PNA server 310, user device 120 (shown in FIG. 1 ), or healthcare provider device 305 (shown in FIG. 3). For example, communication interface 515 may receive requests from healthcare provider devices 305 via the Internet, as illustrated in FIG. 3.

[0089] Processor 505 may also be operatively coupled to a storage device 534. Storage device 534 is any computer-operated hardware suitable for storing and / or retrieving data, such as, but not limited to, data associated with database 320 (shown in FIG. 3). In some embodiments, storage device 534 is integrated in the server computer device 501. For example, server computer device 501 may include one or more hard disk drives as storage device 534. In other embodiments, storage device 534 is external to server computer device 501 and may be accessed by a plurality of server computer devices 501. For example, storage device 534 may include a storage area network (SAN), a network attached storage (NAS) system, and / or multiple storage units such as hard disks and / or solid-state disks in a redundant array of inexpensive disks (RAID) configuration.

[0090] Processor 505 may be operatively coupled to storage device 534 via a storage interface 520. Storage interface 520 is any component capable of providing processor 505 with access to storage device 534. Storage interface520 may include, for example, an Advanced Technology Attachment (ATA) adapter, a Serial ATA (SATA) adapter, a Small Computer System Interface (SCSI) adapter, a RAID controller, a SAN adapter, a network adapter, and / or any component providing processor 505 with access to storage device 534.

[0091] Processor 505 executes computer-executable instructions for implementing aspects of the disclosure. In some embodiments, the processor 505 is transformed into a special-purpose microprocessor by executing computer-executable instructions or by otherwise being programmed. For example, the processor 505 is programmed with instructions as illustrated in FIG. 2.

[0092] The computer-implemented methods and processes described herein may include additional, fewer, or alternate actions, including those discussed elsewhere herein. The present systems and methods may be implemented using one or more local or remote processors, transceivers, and / or sensors (such as processors, transceivers, and / or sensors mounted on vehicles, stations, nodes, or mobile devices, or associated with smart infrastructures and / or remote servers), and / or through the implementation of computer-executable instructions stored on non-transitory computer-readable media or medium. Unless described herein to the contrary, the various steps of the several processes may be performed in a different order, or simultaneously in some instances.

[0093] Additionally, the computer systems discussed herein may include additional, fewer, or alternative elements and respective functionalities, including those discussed elsewhere herein, which themselves may include or be implemented according to computer-executable instructions stored on non- transitory computer-readable media or medium.

[0094] The methods and algorithms of the invention may be enclosed in a controller or processor. Furthermore, methods and algorithms of the present invention can be embodied as a computer-implemented method or methods for performing such computer-implemented method or methods, and can also be embodied in the form of a tangible or non-transitory computer-readable storage medium containing a computer program or other machine-readable instructions(herein “computer program”), wherein when the computer program is loaded into a computer or other processor (herein “computer”) and / or is executed by the computer, the computer becomes an apparatus for practicing the method or methods. Storage media for containing such computer programs include, for example, floppy disks and diskettes, compact disk (CD)-ROMs (whether or not writeable), DVD digital disks, RAM and ROM memories, computer hard drives and back-up drives, external hard drives, “thumb” drives, and any other storage medium readable by a computer. The method or methods can also be embodied in the form of a computer program, for example, whether stored in a storage medium or transmitted over a transmission medium such as electrical conductors, fiber optics or other light conductors, or by electromagnetic radiation, wherein when the computer program is loaded into a computer and / or is executed by the computer, the computer becomes an apparatus for practicing the method or methods.

[0095] The methods and systems may be implemented using computer programming or engineering techniques including computer software, firmware, hardware, or any combination or subset. As disclosed above, at least one technical problem with prior systems is that there is a need for systems for a cost- effective and reliable manner for analyzing patient data to predict peripheral neuropathy. The system and methods described herein address that technical problem. Additionally, at least one of the technical solutions enabled by this system to overcome technical problems may include: (i) advanced warning that the patient may develop neuropathy; (ii) improved accuracy in detecting neuropathy; (iii) eliminating the need for invasive tests for initial neuropathy testing; and (iv) providing up to date monitoring of a patient’s condition to a remote healthcare provider.

[0096] The methods and systems described may be implemented using computer programming or engineering techniques including computer software, firmware, hardware, or any combination or subset thereof, wherein the technical effects may be achieved by performing at least one of the following steps: a) storing a plurality of cold ratings from a patient; b) providing the patient with a cold test object; c) applying cold test object to patient for a period of time; d) receiving one or more ranking from the patient based on the application of thecold test object to the patient; e) analyzing the one or more rankings and the plurality of cold ranking; f) determining a category of the patient developing a condition based on the analysis; and g) transmitting the category to a healthcare provider computer device.

[0097] In some aspects, a computing device is configured to implement machine learning, such that the computing device “learns” to analyze, organize, and / or process data without being explicitly programmed. Machine learning may be implemented through machine learning (ML) methods and algorithms. In one aspect, a machine learning (ML) module is configured to implement ML methods and algorithms. In some aspects, ML methods and algorithms are applied to data inputs and generate machine learning (ML) outputs. Data inputs may further include sequencing data, sensor data, image data, video data, telematics data, authentication data, authorization data, security data, mobile device data, geolocation information, transaction data, personal identification data, financial data, usage data, weather pattern data, “big data” sets, and / or user preference data. In some aspects, data inputs may include certain ML outputs.

[0098] In some aspects, at least one of a plurality of ML methods and algorithms may be applied, which may include but are not limited to linear or logistic regression, instance-based algorithms, regularization algorithms, decision trees, Bayesian networks, cluster analysis, association rule learning, artificial neural networks, deep learning, dimensionality reduction, and support vector machines. In various aspects, the implemented ML methods and algorithms are directed toward at least one of a plurality of categorizations of machine learning, such as supervised learning, unsupervised learning, and reinforcement learning.

[0099] In one aspect, ML methods and algorithms are directed toward supervised learning, which involves identifying patterns in existing data to make predictions about subsequently received data. Specifically, ML methods and algorithms directed toward supervised learning are “trained” through training data, which includes example inputs and associated example outputs. Based on the training data, the ML methods and algorithms may generate a predictive function that maps outputs to inputs and utilize the predictive function to generateML outputs based on data inputs. The example inputs and example outputs of the training data may include any of the data inputs or ML outputs described above.

[0100] In another aspect, ML methods and algorithms are directed toward unsupervised learning, which involves finding meaningful relationships in unorganized data. Unlike supervised learning, unsupervised learning does not involve user-initiated training based on example inputs with associated outputs. Rather, in unsupervised learning, unlabeled data, which may be any combination of data inputs and / or ML outputs as described above, is organized according to an algorithm-determined relationship.

[0101] In yet another aspect, ML methods and algorithms are directed toward reinforcement learning, which involves optimizing outputs based on feedback from a reward signal. Specifically ML methods and algorithms directed toward reinforcement learning may receive a user-defined reward signal definition, receive a data input, utilize a decision-making model to generate an ML output based on the data input, receive a reward signal based on the reward signal definition and the ML output, and alter the decision-making model so as to receive a stronger reward signal for subsequently generated ML outputs. The reward signal definition may be based on any of the data inputs or ML outputs described above. In one aspect, an ML module implements reinforcement learning in a user recommendation application. The ML module may utilize a decision-making model to generate a ranked list of options based on user information received from the user and may further receive selection data based on a user selection of one of the ranked options. A reward signal may be generated based on comparing the selection data to the ranking of the selected option. The ML module may update the decision-making model such that subsequently generated rankings more accurately predict a user selection.

[0102] A control sample or a reference sample as described herein can be a sample from a healthy subject. A reference value can be used in place of a control or reference sample, which was previously obtained from a healthy subject or a group of healthy subjects. A control sample or a reference sample can also be a sample with a known amount of a detectable compound or a spikedsample.

[0103] Definitions and methods described herein are provided to better define the present disclosure and to guide those of ordinary skill in the art in the practice of the present disclosure. Unless otherwise noted, terms are to be understood according to conventional usage by those of ordinary skill in the relevant art.

[0104] In some embodiments, numbers expressing quantities of ingredients, properties such as molecular weight, reaction conditions, and so forth, used to describe and claim certain embodiments of the present disclosure are to be understood as being modified in some instances by the term “about.” In some embodiments, the term “about” is used to indicate that a value includes the standard deviation of the mean for the device or method being employed to determine the value. In some embodiments, the numerical parameters set forth in the written description and attached claims are approximations that can vary depending upon the desired properties sought to be obtained by a particular embodiment. In some embodiments, the numerical parameters should be construed in light of the number of reported significant digits and by applying ordinary rounding techniques. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of some embodiments of the present disclosure are approximations, the numerical values set forth in the specific examples are reported as precisely as practicable. The numerical values presented in some embodiments of the present disclosure may contain certain errors necessarily resulting from the standard deviation found in their respective testing measurements. The recitation of ranges of values herein is merely intended to serve as a shorthand method of referring individually to each separate value falling within the range. Unless otherwise indicated herein, each individual value is incorporated into the specification as if it were individually recited herein. The recitation of discrete values is understood to include ranges between each value.

[0105] In some embodiments, the terms “a” and “an” and “the” and similar references used in the context of describing a particular embodiment (especially in the context of certain of the following claims) can be construed to cover boththe singular and the plural, unless specifically noted otherwise. In some embodiments, the term “or” as used herein, including the claims, is used to mean “and / or” unless explicitly indicated to refer to alternatives only or the alternatives are mutually exclusive.

[0106] The terms “comprise,” “have” and “include” are open-ended linking verbs. Any forms or tenses of one or more of these verbs, such as “comprises,” “comprising,” “has,” “having,” “includes” and “including,” are also open-ended. For example, any method that “comprises,” “has” or “includes” one or more steps is not limited to possessing only those one or more steps and can also cover other unlisted steps. Similarly, any composition or device that “comprises,” “has” or “includes” one or more features is not limited to possessing only those one or more features and can cover other unlisted features.

[0107] All methods described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context.

[0108] The use of any and all examples, or exemplary language (e.g., “such as”) provided with respect to certain embodiments herein is intended merely to better illuminate the present disclosure and does not pose a limitation on the scope of the present disclosure otherwise claimed. No language in the specification should be construed as indicating any non-claimed element essential to the practice of the present disclosure.

[0109] Groupings of alternative elements or embodiments of the present disclosure disclosed herein are not to be construed as limitations. Each group member can be referred to and claimed individually or in any combination with other members of the group or other elements found herein. One or more members of a group can be included in, or deleted from, a group for reasons of convenience or patentability. When any such inclusion or deletion occurs, the specification is herein deemed to contain the group as modified thus fulfilling the written description of all Markush groups used in the appended claims.

[0110] All publications, patents, patent applications, and other references cited in this application are incorporated herein by reference in their entirety for all purposes to the same extent as if each individual publication, patent, patent application, or other reference was specifically and individually indicated to beincorporated by reference in its entirety for all purposes. Citation of a reference herein shall not be construed as an admission that such is prior art to the present disclosure.

[0111] Having described the present disclosure in detail, it will be apparent that modifications, variations, and equivalent embodiments are possible without departing from the scope of the present disclosure defined in the appended claims. Furthermore, it should be appreciated that all examples in the present disclosure are provided as non-limiting examples.EXAMPLES

[0112] The following non-limiting examples are provided to further illustrate the present disclosure.EXAMPLE 1 - DEVELOPMENT THE ALLO-COLD MOBILE HEALTH TECHNOLOGY PROTOTYPE USING A USER-CENTERED DESIGN APPROACH

[0113] To develop the disclosed systems and methods of predicting CIPN in a subject as disclosed herein, the following experiments were conducted. A user-centered mobile app with a three-tier architecture was developed to facilitate the collection, processing, storing, and aggregation of palmar cold sensitivity data with a pre-refrigerated Allo-Cold rod. The presentation tier (user interface and data entry) allowed the patient to easily enter cold pain, cold unpleasantness, and rod surface temperature information. This tier included a timer to facilitate accurate measurement of a 10-second contact time with the rod. The application tier (data management and storage) enabled the aggregation and storage of the entered data. The data process / logic tier enabled the calculation of AUC pain and AUC unpleasantness between treatment cycles and enabled data access by the research team to monitor adherence and identify problems with data entry and application use. The application prototype was designed to be simple and convenient for prompting and capturing daily patient testing and self-reporting of cold pain and unpleasantness, and for depositing responses securely in the database through the cloud. The prototype was iteratively tested and refined to address any usability issues (i.e. , issues that would hinder the user from using the technology or issues that are critical and persistent across users). The prototype met acceptability criteria as described in Example 2.

[0114] A three-tier web application was developed as the Allo-Cold prototype. This application enabled users to access the daily data collection interface using their phone's web browser, where the user is prompted to enter the relevant responses on their daily cold unpleasantness and cold pain. In addition, the surface temperature of the rod was continuously measured via a commercially available TC-SA type K / T surface thermocouple and presented on a display mounted on the rod's case. The rod temperature (as shown on the device's display) was also be entered into the app by the user at the time of measurement. The data was aggregated, stored, and processed using Amazon Web Services cloud computing. The study team accessed patient responses through the administrative function of the app.

[0115] Semi-structured qualitative interviews with 6-8 patients were conducted to attain a user-centered design, who were either currently undergoing oxaliplatin-based therapy, or have developed CIPN. The interviews were geared toward the usability of the Allo-Cold system prototype for cold sensitivity assessment. In addition, similar interviews were conducted with 4-6 clinicians (nurses, physicians) who treated patients with CRC to determine the barriers and facilitators for implementing Allo-Cold technology as a risk prediction biomarker to support clinical decision-making. The number of interviewees (10-14) was selected to attain data saturation. Some of the key features assessed for iterative optimization included a) Reminders and instructions for daily testing of cold sensitivity; b) Data entry: cold pain and unpleasantness, time of contact with rod, surface temperature; c) Update options: treatment dates, treatment regimen changes; d) Data processing: access, missing data, calculation and communication of risk prediction; and e) Protection of information and data safety.

[0116] After each interview (corresponding to a prototype version), the Acceptability of Intervention Measure (AIM) was administered; AIM is a validated measure to determine the acceptability of decision support tools, including mHealth products. AIM scores >3 (agree and completely agree) on its 4 domains indicated acceptability. The elements of Allo-Cold rod packaging design, thermocouple and temperature display, patient instructions, training materials, and optimal user support approaches for the experiments of Example 2 will be finalized.

[0117] During the software development, technical experts, patients, and clinicians viewed the system prototype and provide feedback to enable iterative, user-centered design. Acceptance Criteria for the Allo-Cold system prototype included functional interfaces, data processing, and data management, and an Acceptability of Intervention Measure (AIM) score >3 on its 4.

[0118] The results of these experiments defined the characteristics of a user-centered design of the Allo-Cold clinical biomarker, resulting in a functional and acceptable prototype tested in Example 2.EXAMPLE 2 - DEMONSTRATION ADHERENCE AND PREDICTIVE PERFORMANCE OF ALLO-COLD SYSTEM IN PATIENTS UNDERGOING OXALIPLATIN-BASED CHEMOTHERAPY

[0119] To demonstrate the predictive performance of the systems and methods of predicting CIPN disclosed herein, the following experiments will be conducted. A prototype system will be tested in the context of oxaliplatin-based chemotherapy. Twenty-four patients with stage lll / IV colorectal cancer will use the Allo-Cold system and self-report cold pain and cold unpleasantness daily for 10 weeks (5 cycles) of oxaliplatin-based chemotherapy. Patients will be monitored for the occurrence of CIPN over 24 weeks from the beginning of chemotherapy. Adherence will be recorded, and bi-weekly feedback will be collected from patients.

[0120] The Allo-Cold system will be evaluated in cancer patients using the app during their oxaliplatin-based chemotherapy. Main inclusion criteria: (i) adults > 18 years old, (ii) diagnosed with Stage III or IV CRC, (iii) planned to undergo oxaliplatin-based chemotherapy (any regimen with >8 planned cycles of biweekly oxaliplatin), and (iv) have a smartphone or are willing to use a smartphone provided by the study team. Main exclusion criteria: (i) pre-existing painful symmetric peripheral neuropathy, and (ii) prior treatment with neurotoxic chemotherapy within 12 months of oxaliplatin initiation.

[0121] Enrolled patients will receive an Allo-Cold metal rod, detailed instruction, and initial training. The application will be available via web access on a mobile device (compatible with iOS and Android). At baseline, the patients will assess cold hypersensitivity upon a 10-second contact with the metal rod inthe presence of a study team member to ensure appropriate use. Participants will be given the Allo-Cold metal rod (with its case, thermocouple, and temperature display, with appropriate instructions) to take home and perform daily cold sensitivity measurements at home, beginning on the first day of chemotherapy. Participants will continue this assessment for 10 weeks, i.e. completing 14-day measurements after each of the first five chemotherapy treatment cycles. At baseline, comprehensive demographic information will be collected, as well as measures related to CIPN and pain, including the Brief Pain Inventory (BPI), EORTC QLQ-CIPN20 questionnaire, and Total Neuropathy Score-Clinical (TNSc) assessment. At each clinic visit (on the day of the treatment cycle) for the study duration, peripheral neuropathy will be graded using CTCAE v5.0 criteria, the BPI, TNSc, and QLQ-CIPN20 will be administered, and patient-reported open feedback on usability will be collected. CIPN will be diagnosed clinically, without quantitative sensory testing or invasive methods such as nerve conduction studies or skin biopsies, due to their limited diagnostic value in CIPN.

[0122] The predictive performance of the algorithm in assigning CIPN risk will be confirmed in a total of 48 patients with CRC receiving oxaliplatin treatment — the target population of the proposed technology (24 patients with existing data and 24 patients from the proposed study). The sample size is not intended for full clinical validation of the biomarker. This pilot aims to independently confirm our preliminary findings in a similarly sized cohort and finetune the CIPN prediction algorithm. Given that, 96% of patients are exhibiting some cold hypersensitivity with the Allo-Cold method and — 25% dose-limiting CIPN rate, this sample size will allow us to determine the AUROC>0.75 cut-off for accurate CIPN classification, with 85% power and a=0.05. AUROC for predicting dose-limiting CIPN will be calculated while combining two independent cohorts with the same patient criteria (preliminary and current) to determine the sensitivity and specificity of CIPN prediction. The interviews with the 24 study participants will also be conducted to collect further usability data on Allo-Cold. In example 2, a feasible working prototype of the Allo-Cold system will be developed, with appropriate usability and patient-centered design elements.

Claims

ClaimsWhat is claimed is:1 . A computer-implemented method for predicting a chemotherapy- induced neuropathy (CIPN) condition in a subject undergoing a chemotherapy treatment, the method comprising: receiving, at a computing device, one or more cold rankings from a subject, wherein the one or more cold rankings quantify the subject’s reaction to applying a cold test object to the subject; storing, using the computing device, the one or more cold rankings into a cold ranking database, the cold ranking database comprising the one or more cold rankings and a plurality of previously obtained cold rankings; transforming, using the computing device, at least a portion of the cold ranking database into at least one summary parameter; transforming, using the computing device, the at least one summary parameter into a prediction category selected from subject not likely to develop the CIPN condition and subject likely to develop the CIPN condition; and transmitting, using the computing device, the prediction category to a practitioner device.

2. The method of claim 1 , further comprising: transforming, using the computing device, the prediction category into a recommendation for treatment; and transmitting, using the computing device, the recommendation for treatment to the practitioner device;wherein the recommendation is selected from: maintaining a dosage of the chemotherapy treatment if the classification comprises low risk of the CIPN condition; and reducing the treatment dosage or changing the treatment composition if the classification comprises low risk of the CIPN condition.

3. The method of claim 1 , further comprising applying the cold test object to the subject for a predetermined duration.

4. The method of claim 3, wherein the predetermined duration comprises about ten seconds.

5. The method of claim 3, wherein the cold test object is a stainless-steel cylinder configured to be gripped in a hand of the subject.

6. The method of claim 3, wherein the cold test object is maintained at a temperature ranging from 0 degrees C to 16 degrees C.

7. The method of claim 1 , wherein the cold rankings are selected from a pain score, an unpleasantness score, and any combination thereof.

8. The method of with claim 1 , wherein transforming the at least a portion of the cold ranking database into at least one summary parameter further comprises: dividing, using the computing device, at least a portion of the cold ranking database into at least one group, each group comprising one portion of the cold rankings obtained during one recurring interval of a chemotherapy treatment cycle of the subject; andtransforming, using the computing device, each group of the at least one group of cold rankings into one portion of the at least one summary parameters.

9. The method of claim 8, wherein the at least one summary parameter is selected from at least one of: an area under the curve for each chemotherapy treatment cycle, a maximum rating within each chemotherapy treatment cycle, a range between minimum and maximum ratings within each chemotherapy treatment cycle, and a maximum rate of increase of ratings within each chemotherapy treatment cycle.

10. The method of claim 9, wherein the at least one summary parameter is the area under the curve for each of the chemotherapy treatment cycles.11 . The method of claim 10, further comprising comparing the areas under the curve for each of the chemotherapy treatment cycles.

12. The method in accordance with Claim 11 , wherein transforming the at least one summary parameter into a prediction category further comprises comparing the areas under the curve for each of the chemotherapy treatment cycles to at least one threshold value comprising a high-risk threshold value, wherein the subject is assigned a prediction category of high risk of the CIPN condition if the AUC exceeds the high-risk threshold value or assigned a prediction category of low risk of the CIPN condition if the AUC falls below the high-risk threshold value.

13. The method of claim 1 , further comprising executing, using the computing device, a trained machine learning model to determine the prediction category based on the cold ranking database.

14. A system for predicting a chemotherapy-induced neuropathy (CIPN) condition in a subject undergoing a chemotherapy treatment, the system comprising: a cold test object comprising a stainless-steel cylinder configured to be gripped in a hand of the subject for a predetermined duration of about ten seconds, wherein the cold test object is maintained at a temperature ranging from 0 degrees C to 16 degrees C; and a computing device comprising at least one processor, wherein the at least one processor is configured to: receive one or more cold rankings from a subject, the one or more cold rankings quantifying the subject’s reaction to applying the cold test object, wherein the one or more cold rankings are selected from a pain score, an unpleasantness score, and any combination thereof; store the one or more cold rankings into a cold ranking database, the cold ranking database comprising the one or more cold rankings and a plurality of previously obtained cold rankings; transform at least a portion of the cold ranking database into at least one summary parameter;transform the at least one summary parameter into a prediction category selected from subject not likely to develop the CIPN condition and subject likely to develop the CIPN condition; transform the prediction category into a recommendation for treatment; and transmit the recommendation for treatment to a practitioner device.

15. The system of claim 14, wherein recommendation for treatment is selected from: maintaining a dosage of the chemotherapy treatment if the classification comprises low risk of the CIPN condition; and reducing the treatment dosage or changing the treatment composition if the classification comprises low risk of the CIPN condition.

16. The system of Claim 14 wherein the at least one processor is further configured to: divide at least a portion of the cold ranking database into at least one group, each group comprising one portion of the cold rankings obtained during one recurring interval of a chemotherapy treatment cycle of the subject; and transform each group of the at least one group of cold rankings into one portion of the at least one summary parameters.

17. The method in accordance with Claim 10, wherein determining the prediction category of the subject developing the CIPN conditionbased on the at least one summary parameter further comprises comparing the summary parameter for each of the chemotherapy treatment cycles to at least one threshold value comprising a high-risk threshold value, wherein the subject is assigned a prediction category of high risk of developing the CIPN condition if the summary parameter exceeds the high-risk threshold value and a prediction category of low risk of developing the CIPN condition if the summary parameter is below the high-risk threshold value.

18. The system of claim 19, wherein the at least one summary parameter is selected from at least one of: an area under the curve for each chemotherapy treatment cycle, a maximum rating within each chemotherapy treatment cycle, a range between minimum and maximum ratings within each chemotherapy treatment cycle, and a maximum rate of increase of ratings within each chemotherapy treatment cycle.

Images