Children traditional Chinese medicine nursing intelligent decision support system

Abstract

The invention belongs to the field of traditional Chinese medicine nursing, and particularly relates to a child traditional Chinese medicine nursing intelligent decision support system comprising a data acquisition module used for acquiring basic information, traditional Chinese medicine four diagnosis data and western medicine examination data of a child patient; the data preprocessing module is connected with the data acquisition module and is used for processing the acquired data; the feature extraction module is connected with the data preprocessing module and is used for performing feature extraction on the preprocessed data; the growth and development evaluation module is connected with the feature extraction module and is used for evaluating the growth and development of the children according to the extracted features; the dialectical analysis module is connected with the feature extraction module and comprises a traditional Chinese medicine pediatrics dialectical model, a multi-modal data fusion analysis unit and an intelligent dialectical unit, the problems of experience dependence, scheme stiffness and tracking deficiency in traditional Chinese medicine nursing of children are solved, and clinical practicability and parent satisfaction are remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of traditional Chinese medicine nursing, and particularly relates to a child traditional Chinese medicine nursing intelligent decision support system. BACKGROUND

[0002] In recent years, with the in-depth application of traditional Chinese medicine in the field of pediatrics, child traditional Chinese medicine nursing has made remarkable progress in disease prevention and treatment, rehabilitation and health care, and the popularization of characteristic technologies, but still faces challenges such as lack of standardization, shortage of talents, and need to improve the combination of traditional Chinese and western medicine modes; In the prior art, child traditional Chinese medicine nursing mostly relies on the experience of medical staff, cannot match the treatment plan according to the child plan, and cannot effectively track after treatment, so the present application provides a child traditional Chinese medicine nursing intelligent decision support system to solve the above problems. SUMMARY

[0003] The present application aims to solve the problem in the prior art that child traditional Chinese medicine nursing mostly relies on the experience of medical staff, cannot match the treatment plan according to the child plan, and cannot effectively track after treatment, and provides a child traditional Chinese medicine nursing intelligent decision support system.

[0004] In order to achieve the above-mentioned purpose, the present application adopts the following technical scheme: A child traditional Chinese medicine nursing intelligent decision support system, comprising: A data acquisition module for acquiring basic information of a child patient, traditional Chinese medicine four-examination data and western medicine examination data; A data preprocessing module connected with the data acquisition module for processing the collected data; A feature extraction module connected with the data preprocessing module for extracting features from the preprocessed data; A growth and development evaluation module connected with the feature extraction module for evaluating the growth and development of the child according to the extracted features; A dialectical analysis module connected with the feature extraction module, comprising a traditional Chinese pediatric syndrome differentiation model, a multi-modal data fusion analysis unit and an intelligent dialectical unit; An intelligent decision module connected with the dialectical analysis module, comprising a nursing measure knowledge base, a personalized plan generation unit and a decision unit; A plan output module connected with the intelligent decision module, comprising a visual interface, an early warning unit and a parent feedback unit; A feedback module connected with the plan output module for feeding back the treatment effect of the plan; A personalized file module connected with the feedback module for recording changes in the child's constitution, medication history, massage / food therapy effect, and forming long-term health tracking; A treatment effect evaluation module connected with the feedback module for evaluating the treatment effect. The scheme optimization module is connected with the treatment effect evaluation module, and selects whether to optimize the treatment scheme according to the evaluation result.

[0005] Preferably, the basic information of the child includes age, gender, weight, height, growth and development stage, past medical history, allergy history, family genetic history, and the four diagnostic data of traditional Chinese medicine include the following aspects: inspection: complexion, tongue appearance, mental state, and skin condition; auscultation: voice, smell; interrogation: parent's complaint, symptom duration, bowel movement, and sleep quality; palpation: pulse condition.

[0006] Preferably, the data processing module converts the traditional Chinese medicine terms into structured data, normalizes the continuous variables and classification variables, the continuous variables include body temperature, and the classification variables include cough type, the feature extraction module extracts key traditional Chinese medicine syndrome features, and combines the physiological characteristics of children to weight the related features.

[0007] Preferably, the traditional Chinese medicine pediatric syndrome differentiation model includes a traditional Chinese medicine pediatric syndrome differentiation model, which includes the following aspects: basic theoretical framework: based on the classical theory of traditional Chinese medicine pediatrics, combined with the physiological characteristics of children, pediatric syndrome type library: wind-cold cold, wind-heat cold, spleen deficiency and accumulation, and heart and spleen accumulation; syndrome-symptom association rule: mapping relationship between symptoms and syndrome types is constructed through knowledge graph.

[0008] Preferably, the multi-modal data fusion analysis unit includes the following aspects: symptom weight distribution: the weight of core symptoms is high, and the core symptoms include fever and tongue appearance; secondary symptom weight is low, and the secondary symptom includes sleep disturbance; child-specific adjustment: such as infant pulse diagnosis reference value is low, and needs to rely on inspection and interrogation; dynamic differentiation: considering the course stage, including the initial stage of cold and the heat period, and the influence on syndrome type; seasonal and regional factors: summer dampness syndrome is high, and the differentiation parameters need to be adjusted.

[0009] Preferably, the intelligent differentiation unit includes a machine learning model, the machine learning model uses labeled pediatric cases to train a classification model, including SVM and random forest, processes the symptom time series data through LSTM, constructs a knowledge graph based on traditional Chinese medicine classics and expert experience, and realizes syndrome type reasoning through a graph neural network.

[0010] Preferably, the nursing measure knowledge base includes a traditional Chinese medicine nursing method library and contraindication and risk control, and the traditional Chinese medicine nursing method library includes the following aspects: Massage: acupoint-syndrome type matching; Diet therapy: medicinal diet formula; External treatment: moxibustion and application; The contraindication and risk control includes child contraindicated acupoints and allergy prompt.

[0011] Preferably, the personalized treatment plan generation unit includes multi-objective optimization and synergy between traditional Chinese and Western medicine to balance efficacy, safety, and operability. If bacterial infection is detected, "antibiotics need to be combined" is marked in the massage plan. The "IF-THEN" rule is implemented using the Drools tool, and the recommendation priority is dynamically adjusted based on historical nursing effect feedback.

[0012] Preferably, the visual interface pushes illustrated nursing steps and dietary recipes, provides explanations of traditional Chinese medicine theory, and the early warning unit prompts medical attention when symptoms exceed the scope of traditional Chinese medicine nursing. The parent feedback unit is used by parents to input nursing effects for system optimization.

[0013] Preferably, the growth and development assessment module analyzes whether the growth rate is too slow, whether the neural development is delayed, and the correlation between TCM syndrome type and developmental delay based on a machine learning model. The machine learning model includes random forest and XGBoost.

[0014] The beneficial effects of the intelligent decision support system for pediatric TCM nursing described in this invention are as follows: Multimodal data fusion and dynamic syndrome differentiation improve diagnostic accuracy: Compared with existing technologies, traditional Chinese medicine pediatrics relies on the experience of a single physician and is easily influenced by subjectivity; existing electronic systems mostly only record symptoms without combining Western medical examination data. This solution reduces missed diagnoses / misdiagnoses by combining the four diagnostic methods of traditional Chinese medicine with Western medical indicators through a multimodal data fusion analysis unit; the dynamic syndrome differentiation function adjusts the syndrome judgment according to the stage of disease, adapting to the characteristics of rapid changes in children's conditions; machine learning models assist in syndrome differentiation, improving the accuracy rate by about 25% compared with traditional methods.

[0015] Personalized nursing care plans are generated, balancing safety and operability: Compared with existing technologies, existing systems mostly recommend general templates without considering individual differences among children; this plan's nursing care knowledge base intelligently matches massage acupoints and medicinal diets, and marks contraindications; a multi-objective optimization algorithm balances efficacy and ease of operation for parents; and integrated traditional Chinese and Western medicine prompts avoid delays in treatment caused by purely traditional Chinese medicine nursing. This invention addresses three major pain points in traditional Chinese medicine nursing for children: reliance on experience, rigid protocols, and lack of follow-up, significantly improving clinical applicability and parental satisfaction. Attached Figure Description

[0016] Figure 1 This is a block diagram of an intelligent decision support system for pediatric TCM nursing proposed in this invention; Figure 2 This is a block diagram of the dialectical analysis module of an intelligent decision support system for pediatric TCM nursing proposed in this invention. Figure 3 This is a block diagram of the intelligent decision-making module of an intelligent decision support system for pediatric TCM nursing proposed in this invention; Figure 4This is a block diagram of the data acquisition module of an intelligent decision support system for pediatric TCM nursing proposed in this invention; Figure 5 This is a block diagram of the solution output module of an intelligent decision support system for pediatric TCM nursing proposed in this invention. Detailed Implementation

[0017] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0018] Example 1 Reference Figures 1-5 A smart decision support system for pediatric TCM nursing, comprising: The data acquisition module is used to collect basic information about the children, data from the four diagnostic methods of traditional Chinese medicine, and data from Western medical examinations. The data preprocessing module, connected to the data acquisition module, is used to process the acquired data; The feature extraction module, connected to the data preprocessing module, is used to extract features from the preprocessed data. The growth and development assessment module, connected to the feature extraction module, is used to assess children's growth and development based on the extracted features. The dialectical analysis module, connected to the feature extraction module, includes a TCM pediatric dialectical model, a multimodal data fusion analysis unit, and an intelligent dialectical unit. The intelligent decision-making module, connected to the dialectical analysis module, includes a nursing intervention knowledge base, a personalized solution generation unit, and a decision-making unit; The solution output module, connected to the intelligent decision-making module, includes a visual interface, an early warning unit, and a parent feedback unit; The feedback module, connected to the treatment plan output module, is used to provide feedback on the treatment effect of the plan. The personalized profile module, connected to the feedback module, is used to record changes in a child's physical condition, medication history, and the effects of massage / dietary therapy, forming a long-term health tracking system. The treatment effectiveness evaluation module, connected to the feedback module, is used to evaluate the treatment effectiveness. The treatment plan optimization module is connected to the treatment effect evaluation module. Based on the evaluation results, it allows users to choose whether to optimize the treatment plan.

[0019] In this embodiment, the basic information of the child includes age, gender, weight, height, growth and development stage, past medical history, allergy history, and family history of genetic diseases. The data of the four diagnostic methods of traditional Chinese medicine include inspection: complexion, tongue appearance, mental state, and skin condition; auscultation: sound and odor; inquiry: parents' chief complaint, duration of symptoms, bowel and bladder function, and sleep quality; and palpation: pulse.

[0020] In this embodiment, the data processing module converts TCM terminology into structured data and normalizes continuous and categorical variables. Continuous variables include body temperature, and categorical variables include cough type. The feature extraction module extracts key TCM syndrome features and, combined with children's physiological characteristics, weights relevant features.

[0021] In this embodiment, the TCM pediatric syndrome differentiation model includes the construction of the TCM pediatric syndrome differentiation model, which includes: a basic theoretical framework based on the classic TCM pediatric theories and combined with the physiological characteristics of children; a pediatric syndrome database including: wind-cold common cold, wind-heat common cold, spleen deficiency and stagnation, and heart and spleen heat accumulation; and syndrome-symptom association rules: constructing a mapping relationship between symptoms and syndromes through a knowledge graph.

[0022] In this embodiment, the multimodal data fusion analysis unit includes symptom weight allocation: core symptoms have higher weights, including fever and tongue appearance; secondary symptoms have lower weights, including sleep disturbances; child-specific adjustments: for example, pulse diagnosis has lower reference value for infants and young children, requiring reliance on observation and questioning; dynamic syndrome differentiation: considering the stage of disease, including the initial stage of a cold and the heat-transforming stage, and its impact on syndrome type; seasonal and regional factors: summer heat-dampness syndrome is more common in summer, requiring adjustment of syndrome differentiation parameters.

[0023] In this embodiment, the intelligent dialectical unit includes a machine learning model. The machine learning model uses labeled pediatric cases to train a classification model, including SVM and random forest. It processes symptom time series data through LSTM, constructs a knowledge graph based on TCM classics and expert experience, and realizes syndrome type reasoning through graph neural network.

[0024] In this embodiment, the nursing intervention knowledge base includes a traditional Chinese medicine nursing method base and a contraindication and risk control base. The traditional Chinese medicine nursing method base includes: Massage: Acupoint-Syndrome Matching; Dietary therapy: medicinal diet recipes; External treatment methods: moxibustion, topical application; Contraindications and risk control include acupoints that are contraindicated for children and allergy warnings.

[0025] In this embodiment, the personalized treatment plan generation unit includes multi-objective optimization and synergy between traditional Chinese and Western medicine, balancing efficacy, safety, and operability. If bacterial infection is detected, "antibiotics need to be combined" is marked in the massage plan. The Drools tool is used to implement the "IF-THEN" rule, and the recommendation priority is dynamically adjusted based on historical nursing effect feedback.

[0026] In this embodiment, the visual interface pushes out nursing steps and dietary recipes with illustrations and text, and provides explanations of traditional Chinese medicine theory. The early warning unit prompts medical attention when symptoms exceed the scope of traditional Chinese medicine nursing. The parent feedback unit is used by parents to input the nursing effect for system optimization.

[0027] In this embodiment, the growth and development assessment module analyzes whether the growth rate is too slow, whether the neural development is delayed, and the correlation between TCM syndrome type and developmental delay based on machine learning models. The machine learning models include random forest and XGBoost.

[0028] Example 2 The difference between this embodiment and Embodiment 1 is that: a children's TCM nursing intelligent decision support system includes: The data acquisition module is used to collect basic information about the children, data from the four diagnostic methods of traditional Chinese medicine, and data from Western medical examinations. The data preprocessing module, connected to the data acquisition module, is used to process the acquired data; The feature extraction module, connected to the data preprocessing module, is used to extract features from the preprocessed data. The growth and development assessment module, connected to the feature extraction module, is used to assess children's growth and development based on the extracted features. The dialectical analysis module, connected to the feature extraction module, includes a TCM pediatric dialectical model, a multimodal data fusion analysis unit, and an intelligent dialectical unit. The intelligent decision-making module, connected to the dialectical analysis module, includes a nursing intervention knowledge base, a personalized solution generation unit, and a decision-making unit; The solution output module, connected to the intelligent decision-making module, includes a visual interface, an early warning unit, and a parent feedback unit; The feedback module, connected to the treatment plan output module, is used to provide feedback on the treatment effect of the plan. The personalized profile module, connected to the feedback module, is used to record changes in a child's physical condition, medication history, and the effects of massage / dietary therapy, forming a long-term health tracking system. The treatment effectiveness evaluation module, connected to the feedback module, is used to evaluate the treatment effectiveness. The treatment plan optimization module is connected to the treatment effect evaluation module. Based on the evaluation results, it allows users to choose whether to optimize the treatment plan. The home environment assessment module monitors and analyzes room temperature and humidity through IoT devices.

[0029] Example 3 The difference between this embodiment and Embodiment 1 is that: a children's TCM nursing intelligent decision support system includes: The data acquisition module is used to collect basic information about the children, data from the four diagnostic methods of traditional Chinese medicine, and data from Western medical examinations. The data preprocessing module, connected to the data acquisition module, is used to process the acquired data; The feature extraction module, connected to the data preprocessing module, is used to extract features from the preprocessed data. The growth and development assessment module, connected to the feature extraction module, is used to assess children's growth and development based on the extracted features. The dialectical analysis module, connected to the feature extraction module, includes a TCM pediatric dialectical model, a multimodal data fusion analysis unit, and an intelligent dialectical unit. The intelligent decision-making module, connected to the dialectical analysis module, includes a nursing intervention knowledge base, a personalized solution generation unit, and a decision-making unit; The solution output module, connected to the intelligent decision-making module, includes a visual interface, an early warning unit, and a parent feedback unit; The feedback module, connected to the treatment plan output module, is used to provide feedback on the treatment effect of the plan. The personalized profile module, connected to the feedback module, is used to record changes in a child's physical condition, medication history, and the effects of massage / dietary therapy, forming a long-term health tracking system. The treatment effectiveness evaluation module, connected to the feedback module, is used to evaluate the treatment effectiveness. The treatment plan optimization module is connected to the treatment effect evaluation module. Based on the evaluation results, it allows users to choose whether to optimize the treatment plan. The seasonal health maintenance module generates a dynamic health log based on the theory of Five Elements and Six Qi.

[0030] Example 4 The difference between this embodiment and Embodiment 1 is that: a children's TCM nursing intelligent decision support system includes: The data acquisition module is used to collect basic information about the children, data from the four diagnostic methods of traditional Chinese medicine, and data from Western medical examinations. The data preprocessing module, connected to the data acquisition module, is used to process the acquired data; The feature extraction module, connected to the data preprocessing module, is used to extract features from the preprocessed data. The growth and development assessment module, connected to the feature extraction module, is used to assess children's growth and development based on the extracted features. The dialectical analysis module, connected to the feature extraction module, includes a TCM pediatric dialectical model, a multimodal data fusion analysis unit, and an intelligent dialectical unit. The intelligent decision-making module, connected to the dialectical analysis module, includes a nursing intervention knowledge base, a personalized solution generation unit, and a decision-making unit; The solution output module, connected to the intelligent decision-making module, includes a visual interface, an early warning unit, and a parent feedback unit; The feedback module, connected to the treatment plan output module, is used to provide feedback on the treatment effect of the plan. The personalized profile module, connected to the feedback module, is used to record changes in a child's physical condition, medication history, and the effects of massage / dietary therapy, forming a long-term health tracking system. The treatment effectiveness evaluation module, connected to the feedback module, is used to evaluate the treatment effectiveness. The treatment plan optimization module is connected to the treatment effect evaluation module. Based on the evaluation results, it allows users to choose whether to optimize the treatment plan. The abnormal behavior recognition module uses LSTM to analyze time-series data such as crying and sleeping.

[0031] Example 5 The difference between this embodiment and Embodiment 1 is that: a children's TCM nursing intelligent decision support system includes: The data acquisition module is used to collect basic information about the children, data from the four diagnostic methods of traditional Chinese medicine, and data from Western medical examinations. The data preprocessing module, connected to the data acquisition module, is used to process the acquired data; The feature extraction module, connected to the data preprocessing module, is used to extract features from the preprocessed data. The growth and development assessment module, connected to the feature extraction module, is used to assess children's growth and development based on the extracted features. The dialectical analysis module, connected to the feature extraction module, includes a TCM pediatric dialectical model, a multimodal data fusion analysis unit, and an intelligent dialectical unit. The intelligent decision-making module, connected to the dialectical analysis module, includes a nursing intervention knowledge base, a personalized solution generation unit, and a decision-making unit; The solution output module, connected to the intelligent decision-making module, includes a visual interface, an early warning unit, and a parent feedback unit; The feedback module, connected to the treatment plan output module, is used to provide feedback on the treatment effect of the plan. The personalized profile module, connected to the feedback module, is used to record changes in a child's physical condition, medication history, and the effects of massage / dietary therapy, forming a long-term health tracking system. The treatment effectiveness evaluation module, connected to the feedback module, is used to evaluate the treatment effectiveness. The treatment plan optimization module is connected to the treatment effect evaluation module. Based on the evaluation results, it allows users to choose whether to optimize the treatment plan. The nursing operation guidance module uses AR technology to display the trajectory of pediatric massage techniques.

[0032] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A smart decision support system for pediatric traditional Chinese medicine nursing, characterized in that, include: The data acquisition module is used to collect basic information about the children, data from the four diagnostic methods of traditional Chinese medicine, and data from Western medical examinations. The data preprocessing module, connected to the data acquisition module, is used to process the acquired data; The feature extraction module, connected to the data preprocessing module, is used to extract features from the preprocessed data. The growth and development assessment module, connected to the feature extraction module, is used to assess children's growth and development based on the extracted features. The dialectical analysis module, connected to the feature extraction module, includes a TCM pediatric dialectical model, a multimodal data fusion analysis unit, and an intelligent dialectical unit. The intelligent decision-making module, connected to the dialectical analysis module, includes a nursing intervention knowledge base, a personalized solution generation unit, and a decision-making unit; The solution output module, connected to the intelligent decision-making module, includes a visual interface, an early warning unit, and a parent feedback unit; The feedback module, connected to the treatment plan output module, is used to provide feedback on the treatment effect of the plan. The personalized profile module, connected to the feedback module, is used to record changes in a child's physical condition, medication history, and the effects of massage / dietary therapy, forming a long-term health tracking system. The treatment effectiveness evaluation module, connected to the feedback module, is used to evaluate the treatment effectiveness. The treatment plan optimization module is connected to the treatment effect evaluation module. Based on the evaluation results, it allows users to choose whether to optimize the treatment plan.

2. The intelligent decision support system for pediatric TCM nursing according to claim 1, characterized in that, The basic information of the child includes age, gender, weight, height, growth and development stage, past medical history, allergy history, and family history of genetic diseases. The data from the four diagnostic methods of traditional Chinese medicine include inspection: complexion, tongue appearance, mental state, and skin condition; and auscultation: sound and odor. Medical history taking: Parent's chief complaint, duration of symptoms, bowel and bladder function, sleep quality; Palpation: Pulse.

3. The intelligent decision support system for pediatric TCM nursing according to claim 2, characterized in that, The data processing module transforms TCM terminology into structured data and normalizes continuous and categorical variables. Continuous variables include body temperature, and categorical variables include cough type. The feature extraction module extracts key TCM syndrome features and, combined with children's physiological characteristics, weights relevant features.

4. The intelligent decision support system for pediatric TCM nursing according to claim 3, characterized in that, The TCM pediatric syndrome differentiation model includes the construction of a TCM pediatric syndrome differentiation model, which includes: a basic theoretical framework based on classical TCM pediatric theories and combined with the physiological characteristics of children; a pediatric syndrome database including: wind-cold common cold, wind-heat common cold, spleen deficiency and stagnation, and heart and spleen heat accumulation; and syndrome-symptom association rules, which construct the mapping relationship between symptoms and syndromes through a knowledge graph.

5. The intelligent decision support system for pediatric TCM nursing according to claim 4, characterized in that, The multimodal data fusion analysis unit includes symptom weight allocation: core symptoms have higher weights, including fever and tongue appearance; secondary symptoms have lower weights, including sleep disturbances. Child-specific adjustments: Pulse diagnosis has low reference value for infants and young children, and observation and questioning are necessary; Dynamic differentiation: Consider the stage of disease, including the initial stage of a cold and the stage of heat transformation, and its impact on the syndrome type; Seasonal and regional factors: Summer heat and dampness syndrome is more common in summer, so the differentiation parameters need to be adjusted.

6. The intelligent decision support system for pediatric TCM nursing according to claim 5, characterized in that, The intelligent dialectical unit includes a machine learning model, which trains a classification model using labeled pediatric cases, including SVM and random forest, processes symptom time series data through LSTM, constructs a knowledge graph based on TCM classics and expert experience, and realizes syndrome type reasoning through graph neural network.

7. The intelligent decision support system for pediatric TCM nursing according to claim 6, characterized in that, The nursing intervention knowledge base includes a traditional Chinese medicine nursing method base and a contraindication and risk control section. The traditional Chinese medicine nursing method base includes: Massage: Acupoint-Syndrome Matching; Dietary therapy: medicinal diet recipes; External treatment methods: moxibustion, topical application; Contraindications and risk control include acupoints that are contraindicated for children and allergy warnings.

8. The intelligent decision support system for pediatric TCM nursing according to claim 7, characterized in that, The personalized treatment plan generation unit includes multi-objective optimization and the integration of traditional Chinese and Western medicine, balancing efficacy, safety, and operability. If bacterial infection is detected, "antibiotics need to be combined" is marked in the massage plan. The Drools tool is used to implement the "IF-THEN" rule, and the recommendation priority is dynamically adjusted based on historical nursing effect feedback.

9. The intelligent decision support system for pediatric TCM nursing according to claim 8, characterized in that, The visual interface displays illustrated nursing steps and dietary recipes, provides explanations based on traditional Chinese medicine theory, and includes an early warning unit that prompts medical attention if symptoms exceed the scope of traditional Chinese medicine nursing care. The parent feedback unit allows parents to input nursing effectiveness for system optimization.

10. The intelligent decision support system for pediatric TCM nursing according to claim 9, characterized in that, The growth and development assessment module analyzes whether the growth rate is too slow, whether the neural development is delayed, and the correlation between TCM syndrome types and developmental delay based on machine learning models. The machine learning models include random forest and XGBoost.

Images