Description:FIELD OF THE INVENTION

[0001] The present invention relates to a system for processing diabetic patient data processing system that enables structured acquisition, refinement, and analysis of patient-specific health indicators facilitating early diagnosis and treatment planning of diabetes through predictive health assessment.

BACKGROUND OF THE INVENTION

[0002] Diabetes mellitus is a chronic condition that requires continuous monitoring and analysis of various medical and lifestyle parameters. Accurate and timely evaluation of patient-specific data such as blood glucose levels, blood pressure, insulin, age, and body mass index (BMI) plays a critical role in early diagnosis and treatment planning.

[0003] Traditionally, medical professionals often rely on manual methods or isolated tools to collect, process, and analyze diabetic patient data. These methods include standalone glucose meters, handwritten records, or disjointed protocols that fails to provide overall analysis. Such approaches are prone to human error, delay in decision-making, and inconsistency in monitoring outcomes. Also, managing large volumes of diabetic patient data becomes challenging without structured data processing steps like cleaning, feature selection, and prediction modeling.

[0004] CN115985449A discloses a medication safety evaluation system for diabetic patients. The evaluation system comprises an information acquisition module, a data construction module, a model comparison module, a statistical summary module, an information storage module and an evaluation display module. Data processing and data statistics are carried out through big data collection information, a model is established and related influence factors are determined according to the corresponding relation of patient information, medication index data and feedback information, and the treatment efficiency is improved while medication safety and treatment effectiveness are guaranteed. Information such as patient age segmentation, sensitive medical history and medication charge is used as key classification information to consider medication cost and benefit evaluation economy, or suitability is evaluated according to body tolerance and cell self-rehabilitation ability of patients of different age groups, and the method adapts to early-age sensitization of current diabetic patients; the result of the safety evaluation system can be used as an effective reference for the medication safety of diabetic patients.

[0005] CN114521893A discloses a blood glucose data monitoring system comprises a matching module, a detection module and a data interaction module, the detection module comprises a supporting plate, a placement plate and a placement barrel, a limiting groove is formed in the middle of the supporting plate, the placement plate is installed in the middle of the limiting groove, a tray is installed at the bottom of the placement plate, and the placement barrel is installed at the bottom of the tray; the matching module is used for matching bed body parts in a use scene of a patient, the use scene where the patient is located is better facilitated, and the detection module can detect the current state of the patient; the detection module is matched with the matching module to detect the specific state of the patient and the action behavior of the patient at a specific time point and a non-specific time point, and the data interaction module can match and integrate the state data detected by the detection module and the detection data of the diabetic patient. And real-time treatment guidance adjustment can be conveniently carried out according to the current state of the patient.

[0006] Conventionally, many systems are present which focus solely on data collection and diagnosis, without a seamless transition from data acquisition to final predictive output. Furthermore, these conventional tools lack to cover handle missing values, identify critical health indicators, and offer meaningful predictions based on optimized features from complex datasets.

[0007] In order to overcome the aforementioned drawbacks, there exists a need in the art to develop a system that requires to be capable of gathering diabetic patient data from multiple sources, to produce actionable health status predictions, thereby assisting healthcare providers with early diagnosis, personalized treatment plans and better patient outcomes.

OBJECTS OF THE INVENTION

[0008] The principal object of the present invention is to overcome the disadvantages of the prior art.

[0009] An object of the present invention is to develop a device that is capable of automatically collecting and processing medical and demographic data of diabetic patients, to assist in health monitoring and management.

[0010] Another object of the present invention is to develop a device that is capable of preprocessing patient data for accurate diabetic diagnosis.

[0011] Another object of the present invention is to develop a device that is capable of accurately predicting diabetic or non-diabetic status to support healthcare providers in making timely diagnostic and treatment decisions.

[0012] Another object of the present invention is to develop a device that is capable of early detection of deteriorating conditions and prevent complications through timely intervention.

[0013] Yet another object of the present invention is to develop a device that is capable of supporting real-time monitoring and remote assessment of diabetic patients.

[0014] The foregoing and other objects, features, and advantages of the present invention will become readily apparent upon further review of the following detailed description of the preferred embodiment as illustrated in the accompanying drawings.

SUMMARY OF THE INVENTION

[0015] The present invention relates to a system for processing diabetic patient data that automatically analyzes medical and demographic data of a patient to predict diabetic health status, assisting in early diagnosis, and supporting in planning effective treatments, thereby enabling proactive healthcare management and improving patient outcomes.

[0016] According to an embodiment of the present invention, a system for processing diabetic patient data comprises a data collection module associated with the system to gather medical and demographic data from computing unit for diabetic patient analysis and gathers insulin levels and other health indicators from the computing unit to support diabetic patient monitoring, a data preprocessing module that fills missing data, removes incorrect data points, and scales features to ensure clean and uniform data for accurate diabetic analysis and uses imputation to fill missing blood glucose values and removes outliers to improve diabetic data quality.

[0017] According to another embodiment of the present invention, the system further comprises a data splitting module that divides data into training and testing sets to train a model and using 70% of data for training and 30% for testing, a feature selection module using a particle swarm optimization protocols to pick the most important data features and reduces data dimensions by eliminating irrelevant features like redundant blood pressure readings for efficient diabetic modeling, a prediction module that uses a trained model to predict diabetic health status and outputs a diabetic or normal classification to assist healthcare providers in planning patient treatment.

[0018] While the invention has been described and shown with particular reference to the preferred embodiment, it will be apparent that variations might be possible that would fall within the scope of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS

[0019] These and other features, aspects, and advantages of the present invention will become better understood with regard to the following description, appended claims, and accompanying drawings where:
Figure 1 illustrates a flowchart of a system for processing diabetic patient data.

DETAILED DESCRIPTION OF THE INVENTION

[0020] The following description includes the preferred best mode of one embodiment of the present invention. It will be clear from this description of the invention that the invention is not limited to these illustrated embodiments but that the invention also includes a variety of modifications and embodiments thereto. Therefore, the present description should be seen as illustrative and not limiting. While the invention is susceptible to various modifications and alternative constructions, it should be understood, that there is no intention to limit the invention to the specific form disclosed, but, on the contrary, the invention is to cover all modifications, alternative constructions, and equivalents falling within the spirit and scope of the invention as defined in the claims.

[0021] In any embodiment described herein, the open-ended terms "comprising," "comprises,” and the like (which are synonymous with "including," "having” and "characterized by") may be replaced by the respective partially closed phrases "consisting essentially of," consists essentially of," and the like or the respective closed phrases "consisting of," "consists of, the like.

[0022] As used herein, the singular forms “a,” “an,” and “the” designate both the singular and the plural, unless expressly stated to designate the singular only.

[0023] The present invention relates to a system for processing diabetic patient data processing device that evaluates patterns in patient health indicators and filters out noisy or irrelevant data, thereby enhancing diagnostic accuracy, minimizing diagnostic errors, and enabling healthcare professionals to receive timely and relevant alerts for effective diabetic care intervention.

[0024] Referring to Figure 1, a flow chart of a system for processing diabetic patient data is illustrated. The system disclosed herein comprises a data collection module is to retrieve and compile essential medical and demographic information related to diabetic patients to enable accurate monitoring and analysis. The data collection module is designed to receive inputs such as blood glucose levels, patient age, body mass index (BMI), and blood pressure readings. These data points are gathered from a computing unit or handheld tablet that maintains regular health records for the patient.

[0025] The data collection module is wirelessly linked with the computing device to facilitate uninterrupted data flow and ensure that no manual transfer of health information is required. In addition to standard parameters, the data collection module also acquires insulin levels and various supplementary health indicators including cholesterol levels, heart rate, and historical diabetic trends logged by the user or healthcare professionals.

[0026] Upon receiving the data, the data collection module compiles it into a structured format suitable for further preprocessing, ensuring that the data is complete and free from errors. The data collection module initiates its function by examining the incoming dataset for missing values. In cases where patient records lack entries such as blood glucose readings, BMI, or blood pressure, the data collection module applies imputation methods. These imputation methods rely on available historical values to estimate and replace the missing entries.

[0027] For instance, if a patient’s blood glucose reading is missing on a given date, the data collection module estimates the value based on trends in previous records or corresponding biometric data. Following imputation, the data collection module continues by identifying and eliminating erroneous and inconsistent data entries. These outliers are detected using predefined medical thresholds and statistical features designed to preserve the diabetic data.

[0028] Once the dataset is cleaned, a preprocessing module proceeds to feature scaling, adjusting the range of different data features, such as blood pressure and glucose levels, to bring them to a uniform scale. The scaling is necessary to ensure that no single feature disproportionately influences the prediction results during analysis.

[0029] A data splitting module designed for the purpose of dividing the cleaned and preprocessed diabetic dataset into distinct subsets for model development and performance evaluation. The data splitting module receives the structured dataset from the data preprocessing module and performs a separation process to allocate a portion of the data for model training while reserving the remaining portion for performance testing.

[0030] The data splitting module operates by initiating a segmentation procedure where approximately 70% of the total dataset is designated for model training. This training portion is utilized to expose the model to a wide range of input conditions, and health indicators, allowing the model to identify patterns and correlations relevant to diabetic status prediction.

[0031] The remaining 30% of the data is retained for testing purposes. The testing subset is not involved during the training phase. Instead, it is later introduced to the trained model to evaluate how effectively the model apply learned patterns to new, previously unseen patient data. The result of the testing phase helps determine whether the model is capable of accurately predicting diabetic conditions in real-world applications beyond the training data.

[0032] The data splitting module ensures that the division of data maintains a balanced distribution of diabetic and non-diabetic cases across both training and testing sets. Further the system incorporates a feature selection module aimed at identifying and retaining relevant medical and demographic attributes for diabetic prediction, while discarding redundant information.

[0033] The feature selection module receives the divided training and testing data sets from the data splitting module. To perform its intended function, the feature selection module applies a particle swarm optimization-based approach to examine combinations of features such as blood glucose, BMI, age, blood pressure, insulin levels, and others.

[0034] The system also incorporates a prediction module designed to evaluate processed patient data and generate a classification result indicating the diabetic health status of the individual. The obtained classification assists healthcare providers in conducting early diagnosis and formulating appropriate treatment strategies.

[0035] The prediction module disclosed herein receives the output from the feature selection module, which includes only the relevant attributes for accurate diabetic prediction. These selected features such as blood glucose levels, BMI, blood pressure, insulin levels, and age are input into a model previously trained using the designated training dataset.

[0036] Once the selected features are input into the trained model, the prediction module calculates the probability of the individual being diabetic or non-diabetic. Based on this probability, the prediction module generates a binary classification output either “diabetic” or “normal.” The obtained result is then made available for clinical interpretation.

[0037] The classification output serves as a supportive reference for medical professionals, enabling them to identify high-risk individuals promptly and plan timely medical interventions. In cases where the prediction indicates a diabetic status, doctors initiate further diagnostic procedures or recommend lifestyle and pharmacological measures to manage the patient’s condition effectively.

[0038] The present invention works best in the following manner, where the data collection module receives patient-specific medical and demographic information such as blood glucose readings, blood pressure, body mass index (BMI), age, and insulin levels. The data collection module functions through wireless connectivity established with a computing unit or tablet associated with diabetic patient monitoring and ensuring timely acquisition of relevant health indicators. Once the data is collected, the collected data is transferred to the data preprocessing module. The data preprocessing module operates to clean the gathered information by filling missing values using imputation techniques, and by removing outlier entries that misrepresent the patient’s true condition. After preprocessing, the clean dataset is routed to the data splitting module. The data splitting module divides the dataset into two portions, one for training and the other for testing.

[0039] In continuation, the conventional split of 70% training data and 30% testing data is applied, which ensures the model learns effectively from past records while also being validated on unseen data to verify its reliability. The training dataset is then passed to the feature selection module, to identify the influential features affecting diabetic prediction. The selection process is guided by the particle swarm optimization protocols, which evaluates combinations of attributes and retains those contributing most strongly to accurate classification. With the selected features, the trained model within the prediction module processes incoming patient data to deliver classification result. The prediction module compares the new input with the patterns learned during training and produces an output that indicates whether the patient’s health status is diabetic or normal. This result is then presented to healthcare professionals to assist in diagnostic and treatment decisions.

[0040] Although the field of the invention has been described herein with limited reference to specific embodiments, this description is not meant to be construed in a limiting sense. Various modifications of the disclosed embodiments, as well as alternate embodiments of the invention, will become apparent to persons skilled in the art upon reference to the description of the invention. , Claims:1) A system for processing diabetic patient data, comprising:

i) a data collection module associated with the system to gather medical and demographic data like blood glucose, age, BMI, and blood pressure from computing unit wirelessly associated with system or tablets for diabetic patient analysis;
ii) a data preprocessing module that fills missing data, removes incorrect data points, and scales features to ensure clean and uniform data for accurate diabetic analysis;
iii) a data splitting module that divides data into training and testing sets to train a model and check its performance on new, unseen diabetic data;
iv) a feature selection module using a particle swarm optimization protocols to pick the most important data features, reducing unnecessary data for better diabetic model accuracy; and
v) a prediction module that uses a trained model to predict diabetic health status, helping doctors with early diagnosis and treatment planning for patients.

2) The system as claimed in claim 1, wherein the data collection module gathers insulin levels and other health indicators from the computing unit to support diabetic patient monitoring.

3) The system as claimed in claim 1, wherein the data pre-processing module uses imputation to fill missing blood glucose values and removes outliers to improve diabetic data quality.

4) The system as claimed in claim 1, wherein the data splitting module uses 70% of data for training and 30% for testing to ensure the diabetic model generalizes well.

5) The system as claimed in claim 1, wherein the feature selection module reduces data dimensions by eliminating irrelevant features like redundant blood pressure readings for efficient diabetic modeling.

6) The system as claimed in claim 1, wherein the prediction module outputs a diabetic or normal classification to assist healthcare providers in planning patient treatment.