Medication dynamic risk assessment method and system for elderly patients

Abstract

The invention discloses a drug use dynamic risk assessment method and system for an elderly patient, and relates to the technical field of drug use risk assessment, and the method comprises the steps: collecting static factor data and dynamic factor data of the elderly patient, carrying out the preprocessing of the collected static factor data and dynamic factor data, and generating a feature vector for risk assessment; calculating a comprehensive risk score through a preset evaluation rule based on the feature vector; the comprehensive risk score is compared with a preset risk grading threshold value, the medication compliance risk grade of the elderly patient is determined, and the system comprises a data collection module, a preprocessing module, a risk assessment module and a grading module. The comprehensiveness and timeliness of medication compliance risk assessment of elderly patients are improved, and technical support is provided for medication intervention.

Description

Technical Field

[0001] The present invention relates to the technical field of medication risk assessment, and particularly to a method and system for dynamically assessing the medication risk of elderly patients. Background Art

[0002] With the aggravation of population aging, the problem of medication safety for elderly patients has become increasingly prominent. Clinical practice shows that due to factors such as the decline in cognitive function accompanying the increase in age and the prevalence of polypharmacy among elderly patients, the medication compliance (i.e., the degree to which patients take medications according to medical advice) is significantly lower than that of other populations, and non-compliance with medications may lead to problems such as poor treatment effects, increased adverse reactions, and rising medical costs.

[0003] Traditional assessment methods mostly judge risks based on factors such as the age and cognitive scores of elderly patients, and the collection and analysis of the dynamic changes in the medication behaviors of elderly patients and abnormal physiological indicators are not comprehensive enough, resulting in the difficulty of the assessment results in timely reflecting the current medication compliance risk status of elderly patients. Summary of the Invention

[0004] To solve the technical problem in the prior art that the dynamic data of elderly patients' medication is not fully utilized during the assessment of medication compliance of elderly patients, resulting in the difficulty of the assessment results in timely and accurately reflecting the current risk status, the present invention provides a method and system for dynamically assessing the medication risk of elderly patients.

[0005] The technical solution adopted by the present invention is as follows:

[0006] The first aspect of the present application provides a method for dynamically assessing the medication risk of elderly patients, including the following steps:

[0007] Collect static factor data and dynamic factor data of elderly patients, where the static factor data includes age, cognitive ability score, and previous history of missed doses, and the dynamic factor data includes medication record data and physiological index data.

[0008] Preprocess the collected static factor data and dynamic factor data to generate a feature vector for risk assessment.

[0009] Calculate a comprehensive risk score based on the feature vector through a preset assessment rule.

[0010] Compare the comprehensive risk score with a preset risk classification threshold to determine the medication compliance risk level of elderly patients.

[0011] Preferably, preprocessing the collected static factor data and dynamic factor data to generate a feature vector for risk assessment includes the following:

[0012] Segment and quantify the age in the static factor data to obtain the age segment quantification value; perform a standardized conversion on the cognitive ability score to obtain the standardized cognitive ability score; binary identify the previous missed dose history to obtain the binary identification value of the previous missed dose history.

[0013] Extract and quantify the medication time interval and medication dose deviation from the medication record data in the dynamic factor data to obtain the medication time interval quantification value and the medication dose deviation quantification value; perform outlier detection and normalization processing on the physiological index data to obtain the normalized physiological index value.

[0014] Combine the age segment quantification value, the standardized cognitive ability score, the binary identification value of the previous missed dose history, the medication time interval quantification value, the medication dose deviation quantification value, and the normalized physiological index value in a preset order to form a feature vector.

[0015] Preferably, calculating the comprehensive risk score based on the feature vector through a preset evaluation rule includes the following:

[0016] Multiply the age segment quantification value, the standardized cognitive ability score, the binary identification value of the previous missed dose history, the medication time interval quantification value, the medication dose deviation quantification value, and the normalized physiological index value in the feature vector by their corresponding weight coefficients respectively, and accumulate the results of each multiplication to obtain the comprehensive risk score, which is used to represent the quantification value of the medication compliance risk of elderly patients.

[0017] Preferably, comparing the comprehensive risk score with a preset risk grading threshold to determine the medication compliance risk level of elderly patients includes the following:

[0018] Preset several risk grading thresholds to form a set of risk level intervals; compare the calculated comprehensive risk score with each risk grading threshold to determine the risk level interval it belongs to; determine the medication compliance risk level of elderly patients according to the preset corresponding relationship between the risk level interval and the medication compliance risk level.

[0019] Preferably, calculating the comprehensive risk score based on the feature vector through a preset evaluation rule includes the following:

[0020] Multiply the age segment quantification value, the standardized cognitive ability score, the binary identification value of the previous missed dose history, the medication time interval quantification value, the medication dose deviation quantification value, and the normalized physiological index value in the feature vector by their corresponding basic weight coefficients respectively to obtain a set of basic weighted intermediate values.

[0021] Extract the age range corresponding to the age segment quantization value and the drug metabolism pathway identifier in the medication record data item from the feature vector to form an age-metabolism pathway cross-feature pair; retrieve the set of metabolism ability attenuation coefficients corresponding to the cross-feature pair through the elderly medication risk factor association database.

[0022] When the cross-feature pair matches the attenuation coefficient, correct the medication dose deviation quantization value weighted term and the physiological index normalization value weighted term in the basic weighted intermediate value set according to the attenuation coefficient to generate a corrected weighted intermediate value.

[0023] Remove the medication dose deviation quantization value weighted term and the physiological index normalization value weighted term in the basic weighted intermediate value set, accumulate the remaining basic weighted intermediate values to obtain the first part of the risk score; accumulate the corrected weighted intermediate values to obtain the second part of the risk score; accumulate the first part of the risk score and the second part of the risk score to obtain the comprehensive risk score.

[0024] Preferably, obtain the age data and previous missed dose history data of elderly patients through the electronic medical record system;

[0025] Use the MMSE scale to obtain the cognitive ability score data of elderly patients; obtain the medication record data of elderly patients from the electronic medication record system; obtain the physiological index data of elderly patients through the physiological index monitoring device.

[0026] Preferably, it further includes the following content: For different risk levels, pre-configure an individualized medication guidance plan library including medication time adjustment strategies, dose adjustment suggestions, and missed dose remedy measures; when determining the medication compliance risk level of elderly patients, retrieve the corresponding level of medication guidance plan from the individualized medication guidance plan library.

[0027] The second aspect of the present application provides a dynamic risk assessment system for elderly patients' medication, applying the above-mentioned dynamic risk assessment method for elderly patients' medication, including:

[0028] A data collection module, which is used to collect the static factor data and dynamic factor data of elderly patients. The static factor data includes age, cognitive ability score, and previous missed dose history, and the dynamic factor data includes medication record data and physiological index data.

[0029] A data preprocessing module, which is used to preprocess the collected static factor data and dynamic factor data to generate a feature vector for risk assessment.

[0030] A risk assessment module, which is used to calculate the comprehensive risk score based on the feature vector through a preset assessment rule.

[0031] A risk grading module, which is used to compare the comprehensive risk score with a preset risk grading threshold to determine the risk level of medication compliance for elderly patients.

[0032] The beneficial effects of the present invention are at least one of the following:

[0033] By simultaneously collecting data on static factors such as age and cognitive ability scores, as well as data on dynamic factors such as medication record data and physiological index data, the traditional evaluation mode that only relies on static factors is changed, achieving multi-dimensional coverage of the influencing factors of medication compliance for elderly patients and providing more comprehensive data support for risk assessment.

[0034] Through the collection and analysis of medication record data and physiological index data, it is possible to capture dynamic change information such as fluctuations in the medication behavior and abnormal physiological states of elderly patients. Compared with traditional static evaluation methods, it effectively improves the problem that the evaluation result lags behind the actual risk state of the patient, making the risk assessment more in line with the actual situation of the patient's current medication compliance.

[0035] By preprocessing the collected data to generate feature vectors and calculating the comprehensive risk score based on a preset evaluation rule, the systematic integration and analysis of static factors and dynamic factors are realized. This method overcomes the defect of insufficient utilization of dynamic data in traditional methods, enabling the risk grading result to more accurately reflect the risk level of medication compliance for elderly patients and providing a basis for subsequent intervention. Description of the Drawings

[0036] Figure 1 It is a schematic flowchart of the method according to Embodiment 1 of the present invention;

[0037] Figure 2 It is a system block diagram according to Embodiment 2 of the present invention. Detailed Embodiments

[0038] The embodiments of the present invention will be described in detail below with reference to the drawings.

[0039] Embodiment 1 provides a method for dynamically assessing the medication risk of elderly patients, as Figure 1 shown, including the following steps:

[0040] Step 1, collect static factor data and dynamic factor data of elderly patients. The static factor data includes age, cognitive ability score, and previous history of missed doses, and the dynamic factor data includes medication record data and physiological index data.

[0041] Considering that traditional assessment methods only rely on static data such as age and cognitive scores, and cannot capture dynamic risk signals such as medication behavior fluctuations (e.g., missed doses, dosage deviations) and abnormal physiological indicators (e.g., sudden increase in blood pressure), resulting in the disconnection between the assessment results and the actual risk status of patients. This step constructs a "static + dynamic" data system covering multiple risk factors such as age, cognition, medication behavior, and physiological indicators.

[0042] In a possible implementation, the collection of static factor data and dynamic factor data of elderly patients includes the following: obtaining the age data and past missed dose history data of elderly patients through the electronic medical record system; obtaining the cognitive ability score data of elderly patients using the MMSE scale; obtaining the medication record data of elderly patients from the electronic medication record system; obtaining the physiological indicator data of elderly patients through physiological indicator monitoring devices.

[0043] Exemplarily, in the specific implementation process, the static factor data can automatically read the date of birth field entered when the patient established the file through the patient basic information module of the hospital HIS electronic medical record system, and the system background calculates the time difference between the current date and the date of birth to generate the age value (accurate to full years). For example, if the electronic medical record shows that the patient's date of birth is March 12, 1945, and the current system time is June 12, 2025, then the calculated age is 80 years old.

[0044] The MMSE (Mini-Mental State Examination) scale is used for assessment. The scale includes 30 questions in 7 dimensions such as orientation, memory, and attention. The patient gets 1 point for each correct answer, and the total score ranges from 0 to 30 points. After the assessment, the system completes the standardized conversion (such as mapping the original score to the standardized interval of 0 - 1).

[0045] Through the medication history module of the electronic medical record system, retrieve the comparison results between the medication records and the actual medication records within the past 12 months. If there is a preset missed dose mark in the system (such as not taking the medicine according to the doctor's order time for 2 consecutive times), then a binary identifier is automatically generated ("1" indicates a history of missed doses, "0" indicates no history of missed doses).

[0046] Exemplarily, the acquisition of medication record data includes synchronizing the doctor's order medication information of the patient from the hospital PACS electronic medication record system, including the drug name, specification, medication frequency (such as 2 times a day), and standard medication time points (such as 8:00, 20:00).

[0047] Exemplarily, for the collection of physiological indicator data, indicators such as blood pressure and heart rate can be collected non - contactly through a wearable smart bracelet, and the device automatically measures and stores data at a preset frequency (such as every 30 minutes); blood glucose indicators can be collected through a blood glucose meter.

[0048] Step 2: Preprocess the collected static factor data and dynamic factor data to generate feature vectors for risk assessment.

[0049] In a possible implementation manner, the preprocessing of the collected static factor data and dynamic factor data to generate feature vectors for risk assessment includes the following:

[0050] Perform segmented quantization processing on the age in the static factor data to obtain an age segmented quantization value; perform standardized conversion on the cognitive ability score to obtain a standardized cognitive ability score; perform binary identification on the previous missed dose history to obtain a binary identification value for the previous missed dose history;

[0051] Extract and quantify the medication time interval and medication dose deviation from the medication record data in the dynamic factor data to obtain a quantified medication time interval value and a quantified medication dose deviation value; perform outlier detection and normalization processing on the physiological index data to obtain a normalized physiological index value;

[0052] Combine the age segmented quantization value, the standardized cognitive ability score, the binary identification value for the previous missed dose history, the quantified medication time interval value, the quantified medication dose deviation value, and the normalized physiological index value in a preset order to form a feature vector.

[0053] Exemplarily, in the specific implementation process, map the collected age values to 5 preset age range intervals: the quantization value corresponding to 60 - 69 years old is 0.2; the quantization value corresponding to 70 - 79 years old is 0.4; the quantization value corresponding to 80 - 89 years old is 0.6; the quantization value corresponding to 90 - 99 years old is 0.8; the quantization value corresponding to ≥100 years old is 1.0.

[0054] Convert the original MMSE score (0 - 30 points) to the [0, 1] interval through linear mapping: Standardization formula: S = 1 - (30 - R) / 30, where R is the original score and S is the standardized score; for example: if the MMSE score is 24 points, then after standardization it is 1 - (30 - 24) / 30 = 0.8.

[0055] Directly adopt the binary identification generated in Step 1 for the binary conversion of the previous missed dose history: having a missed dose history (marked as "1" in Step 1) is converted to 1.0; having no missed dose history (marked as "0" in Step 1) is converted to 0.0.

[0056] Exemplarily, the quantification of medication record data includes the extraction of medication time intervals: Calculate the deviation (in minutes) between the actual medication time and the prescribed time, and quantify it according to the following rules: a quantification value of 1.0 for ≤ 15 minutes (fully compliant); a quantification value of 0.8 for 16 - 30 minutes (basically compliant); a quantification value of 0.6 for 31 - 60 minutes (slightly delayed); a quantification value of 0.4 for 61 - 120 minutes (moderately delayed); a quantification value of 0.2 for > 120 minutes (severely delayed); for example: if the prescribed time is 8:00 and the actual medication time is 8:25, the deviation is 25 minutes, and the quantification value is 0.8.

[0057] Exemplarily, the extraction of medication dose deviation includes calculating the percentage deviation of the actual medication dose from the prescribed dose: Deviation rate formula: D = |(actual dose - prescribed dose) / prescribed dose|; Map the deviation rate to a quantification value: a quantification value of 1.0 for ≤ 5% (fully compliant); a quantification value of 0.8 for 6 - 10% (basically compliant); a quantification value of 0.6 for 11 - 20% (slightly deviated); a quantification value of 0.4 for 21 - 50% (moderately deviated); a quantification value of 0.2 for > 50% (severely deviated); for example: if the prescribed dose is 100 mg and the actual dose is 92 mg, the deviation rate is 8%, and the quantification value is 0.8.

[0058] Exemplarily, the normalization of physiological index data includes outlier detection: Use the 3σ criterion to identify outliers: Calculate the mean μ and standard deviation σ of the data for the past 7 days. If the current value exceeds the range [μ - 3σ, μ + 3σ], it is marked as an outlier. For example: if the mean systolic blood pressure of a patient for the past 7 days is 130 mmHg and the standard deviation is 5 mmHg, the outlier range is [115, 145] mmHg. The normalization process includes mapping the physiological index to the [0, 1] interval:

[0059] For positive indicators such as blood pressure and blood sugar, the formula is: N=(V - V min ) / (V max - V min ); where N represents the normalized value; V represents the current measured value; V min表示 The clinical minimum value of this indicator (e.g., systolic blood pressure 70 mmHg); V max表示 The clinical maximum value of this indicator (e.g., systolic blood pressure 220 mmHg).

[0060] For indicators such as heart rate that have an ideal interval: If G is within the ideal interval, then the corresponding N = 1.0;

[0061] If G exceeds the ideal interval, then the corresponding N = 1 - |G - G i | / (G max - G i ). Where N represents the normalized value; G represents the current measured value; Gi Represents the ideal value of the indicator (such as a heart rate of 75 beats per minute), G max Represents the clinical safety upper limit of the indicator (such as a heart rate of 150 beats per minute); for example: the patient's heart rate is 85 beats per minute, G i = 75, G max = 150, then the normalized value is 1 - |85 - 75| / (150 - 75) = 0.87.

[0062] Example feature vector: Suppose the results after data preprocessing of an elderly patient are as follows: the segmented quantization value corresponding to the age of 80 years is 0.6; the standardized value corresponding to the MMSE score of 24 points is 0.8; the binary value corresponding to a history of missed doses is 1.0; the quantization value corresponding to a medication time deviation of 25 minutes is 0.8; the quantization value corresponding to a medication dose deviation of 8% is 0.8; the normalized value corresponding to a blood pressure of 150 / 95 mmHg is 0.53; the normalized value corresponding to a heart rate of 85 beats per minute is 0.87; the normalized value corresponding to a blood glucose of 6.8 mmol / L is 0.7.

[0063] Then the generated feature vector is: [0.6, 0.8, 1.0, 0.8, 0.8, 0.53, 0.87, 0.7]. This feature vector converts heterogeneous data sources into standardized inputs that can be directly used for risk calculation through a unified quantization standard, solving the problems of inconsistent data dimensions and ineffective fusion in traditional evaluations.

[0064] Step 3, calculate the comprehensive risk score based on the feature vector through a preset evaluation rule.

[0065] In the first possible implementation manner, the calculating the comprehensive risk score based on the feature vector through a preset evaluation rule includes the following: [[ID=2*]]

[0066] Multiply the segmented quantization value of age, the standardized score of cognitive ability, the binary identification value of the previous history of missed doses, the quantization value of the medication time interval, the quantization value of the medication dose deviation, and the normalized value of the physiological index in the feature vector by the corresponding weight coefficients respectively, and accumulate the results of each multiplication to obtain the comprehensive risk score, which is used to represent the quantization value of the medication compliance risk of the elderly patient.

[0067] Among them, the weight coefficients are preset according to the influence degree of each data item on the medication compliance risk.

[0068] Exemplarily, according to the clinical expert consensus, the basic weight coefficients of each data item are set as follows; segmented quantization value of age: 0.15; standardized score of cognitive ability: 0.20; binary value of previous history of missed doses: 0.15; quantization value of medication time interval: 0.15; quantization value of medication dose deviation: 0.15; normalized value of blood pressure: 0.05; normalized value of heart rate: 0.05; normalized value of blood glucose: 0.05.

[0069] Weighted calculation and accumulation. The eigenvector is: [0.6, 0.8, 1.0, 0.8, 0.8, 0.53, 0.87, 0.7]. The weighted calculation process for each data item is as follows: 0.6×0.15 = 0.09; 0.8×0.20 = 0.16; 1.0×0.15 = 0.15; 0.8×0.15 = 0.12; 0.8×0.15 = 0.12; 0.53×0.05 = 0.0265; 0.87×0.05 = 0.0435; 0.7×0.05 = 0.035. The accumulated comprehensive risk score is: 0.09 + 0.16 + 0.15 + 0.12 + 0.12 + 0.0265 + 0.0435 + 0.035 = 0.745. The comprehensive risk score of this patient is 0.745.

[0070] Considering that in the first implementation, the basic weighting does not consider the decline of the metabolic capacity of elderly patients with age and the cross - influence of drug metabolism pathways and age (such as higher risks for elderly patients taking drugs metabolized by the kidneys), resulting in the evaluation results may not match the clinical reality well. In the second possible implementation, calculating the comprehensive risk score based on the eigenvector through a preset evaluation rule includes the following:

[0071] Multiply the age - segmented quantization value, cognitive ability standardized score, past missed - dose history binary identification value, medication time - interval quantization value, medication - dose deviation quantization value, and physiological - index normalization value in the eigenvector by their corresponding basic weight coefficients respectively to obtain a set of basic weighted intermediate values. The basic weight coefficients are preset according to the influence degree of each data item on the medication compliance risk.

[0072] Extract the age - range interval corresponding to the age - segmented quantization value from the eigenvector, and the drug - metabolism pathway identifier in the medication record data item to form an age - metabolism pathway cross - feature pair; retrieve the set of metabolic - capacity attenuation coefficients corresponding to this cross - feature pair through the elderly - medication risk - factor association database.

[0073] When the cross - feature pair matches an attenuation coefficient, correct the weighted terms of the medication - dose deviation quantization value and the physiological - index normalization value in the set of basic weighted intermediate values according to the attenuation coefficient to generate corrected weighted intermediate values.

[0074] Remove the weighted terms of the medication - dose deviation quantization value and the physiological - index normalization value from the set of basic weighted intermediate values, accumulate the remaining basic weighted intermediate values to obtain the first - part risk score; accumulate the corrected weighted intermediate values to obtain the second - part risk score; accumulate the first - part risk score and the second - part risk score to obtain the comprehensive risk score.

[0075] Exemplarily, using the same basic weight coefficients as in the first embodiment, a set of basic weighted intermediate values is calculated. This will not be elaborated here.

[0076] Exemplarily, for cross-feature pair extraction and attenuation coefficient retrieval, assume that for this patient: the age segmentation quantization value of 0.6 corresponds to the age range of 80 - 89 years old; the medication record shows that the patient is taking a kidney metabolism drug (such as metformin), and by retrieving through the elderly medication risk factor association database, it is obtained that: the metabolism ability attenuation coefficient for people aged 80 - 89 taking kidney metabolism drugs is 1.35 (i.e., the risk increases by 35%).

[0077] Weight correction is performed on the two affected data items: the original weighted value of the medication dose deviation quantization value is 0.12; the corrected weighted value: 0.12×1.35 = 0.162; the original weighted value of the blood pressure normalization value (the association between kidney metabolism drugs and blood pressure is relatively strong) is 0.0265; the corrected weighted value: 0.0265×1.35 = 0.035775.

[0078] Exemplarily, partial accumulation calculation is performed: The first part of the risk score (uncorrected data items) includes: age: 0.09; cognitive ability: 0.16; missed dose history: 0.15; medication time interval: 0.12; heart rate: 0.0435; blood glucose: 0.035; total: 0.09 + 0.16 + 0.15 + 0.12 + 0.0435 + 0.035 = 0.6085.

[0079] The second part of the risk score (corrected data items): medication dose deviation: 0.162; blood pressure: 0.035775; total: 0.162 + 0.035775 = 0.197775.

[0080] The comprehensive risk score of this patient is 0.6085 + 0.197775 = 0.806275.

[0081] The score improvement in the second embodiment reflects the increased potential risk when elderly patients take kidney metabolism drugs; the dynamic weight correction mechanism makes the evaluation result closer to the clinical reality and provides a quantitative basis for personalized medication guidance.

[0082] Step 4: Compare the comprehensive risk score with a preset risk grading threshold to determine the medication compliance risk level of the elderly patient.

[0083] In a possible implementation manner, comparing the comprehensive risk score with a preset risk grading threshold to determine the medication compliance risk level of the elderly patient includes the following:

[0084] Set a number of pre - set risk classification thresholds to form a set of risk level intervals; compare the calculated comprehensive risk score with each risk classification threshold to determine the risk level interval it belongs to; determine the medication compliance risk level of the elderly patient according to the pre - set corresponding relationship between the risk level interval and the medication compliance risk level.

[0085] Exemplarily, preset four - level risk levels and corresponding intervals:

[0086] Risk level Risk score range Clinical significance Low risk [0,0.4) Good medication compliance Medium risk [0.4,0.6) There are mild compliance problems High risk [0.6,0.8) Significant compliance risks requiring intervention Extremely high risk [0.8,1.0] There are serious medication safety hazards

[0087] Taking the comprehensive risk score of 0.745 calculated by the first implementation method in step 3 as an example; threshold comparison: 0.745≥0.6 and 0.745 < 0.8; corresponding risk level interval [0.6, 0.8), determined as high risk.

[0088] Taking the comprehensive risk score of 0.806275 calculated by the second implementation method in step 3 as an example: 0.806275≥0.8 and 0.806275≤1.0; corresponding risk level interval [0.8, 1.0], determined as extremely high risk.

[0089] Furthermore, in a possible implementation manner, it further includes the following content: for different risk levels, a personalized medication guidance plan library including medication time adjustment strategies, dose adjustment suggestions, and missed - dose remedial measures is pre - configured; after determining the medication compliance risk level of the elderly patient, retrieve the corresponding - level medication guidance plan from the personalized medication guidance plan library.

[0090] Exemplarily, the medication time adjustment strategy corresponding to the low - risk level (risk score 0 - 0.4) is to maintain the current medication time, and it is recommended to set a fixed alarm reminder. Example: "Continue to take antihypertensive drugs at 8:00 and 20:00 every day. It is recommended to use the mobile phone alarm function."

[0091] The dose adjustment suggestion is to maintain the current dose and review liver and kidney functions every 3 months. Example: "Continue to take aspirin 100mg / day. It is recommended to check blood coagulation function every quarter."

[0092] The missed - dose remedial measure is that if the missed - dose time < 12 hours, take the missed dose immediately; if > 12 hours, skip the missed dose and take the next dose normally. Example: "If you forget to take antihypertensive drugs, take the missed dose if the time until the next dose > 12 hours, otherwise skip it."

[0093] Exemplarily, the medication time adjustment strategy corresponding to the medium - risk level (risk score 0.41 - 0.6) is to adjust to a long - acting preparation once a day to reduce the risk of missed doses. Example: "It is recommended to change nifedipine sustained - release tablets to nifedipine controlled - release tablets, once a day, taken after breakfast."

[0094] The dosage adjustment recommendation is: maintain the current dosage, but increase the monitoring frequency. Example: "Continue to take metformin 500mg bid, and it is recommended to monitor fasting blood glucose 3 times a week."

[0095] The remedy for missed doses is: if the missed dose is within <6 hours, take the missed dose immediately; if it is >6 hours, skip the missed dose and take the next dose as normal. Example: "If you forget to take the antidiabetic drug, take it if the time to the next dose is >6 hours, otherwise skip it."

[0096] The medication time adjustment strategy corresponding to the high-risk level (risk score 0.61 - 0.8) is: use an intelligent medicine box for dose management and set multiple reminders (such as mobile phone + voice alarm). Example: "It is recommended to use an intelligent medicine box (such as LifePod) and set voice reminders to take medicine three times a day, in the morning, at noon, and in the evening."

[0097] The dosage adjustment recommendation is: reduce the basic dosage by 20% and increase the frequency of divided doses. Example: "Adjust warfarin from 3mg / day to 2.5mg / day, taken twice a day, in the morning and evening."

[0098] Remedy for missed doses: If a dose is missed, immediately contact a doctor or pharmacist for individualized guidance.

[0099] The medication time adjustment strategy corresponding to the extremely high-risk level (risk score >0.8) is: adjust in the hospital by observation, or have a caregiver supervise the medication. Example: "It is recommended to adjust the medication plan in the hospital, or have family members supervise the medication daily." The dosage adjustment recommendation is: suspend the high-risk drug and switch to an alternative treatment plan. Example: "Suspend the use of non-steroidal anti-inflammatory drugs and switch to acetaminophen to relieve pain." Remedy for missed doses: Seek medical attention immediately for emergency treatment. Example: "If you miss a dose of antihypertensive drug, go to the emergency department of the nearby hospital immediately."

[0100] Example 2 provides a dynamic risk assessment system for the medication of elderly patients, applying the above-mentioned dynamic risk assessment method for the medication of elderly patients, as Figure 2 shown, including:

[0101] A data collection module, which is used to collect the static factor data and dynamic factor data of elderly patients. The static factor data includes age, cognitive ability score, and previous missed dose history. The dynamic factor data includes medication record data and physiological index data;

[0102] A data preprocessing module, which is used to preprocess the collected static factor data and dynamic factor data to generate feature vectors for risk assessment;

[0103] A risk assessment module, which is used to calculate the comprehensive risk score based on the feature vectors through a preset assessment rule;

[0104] A risk grading module, which is used to compare the comprehensive risk score with a preset risk grading threshold to determine the risk level of the medication compliance of elderly patients.

[0105] The above embodiments only represent the specific implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention.

Claims

1. A dynamic risk assessment method for drug use in elderly patients, characterized in that, It includes the following steps: Collect static factor data and dynamic factor data of elderly patients. The static factor data includes age, cognitive ability score, and previous missed dose history. The dynamic factor data includes medication record data and physiological index data; Preprocess the collected static factor data and dynamic factor data to generate a feature vector for risk assessment; Calculate a comprehensive risk score based on the feature vector through a preset evaluation rule; Compare the comprehensive risk score with a preset risk classification threshold to determine the medication compliance risk level of elderly patients.

2. The dynamic risk assessment method for drug use by elderly patients according to claim 1, wherein Preprocessing the collected static factor data and dynamic factor data to generate a feature vector for risk assessment includes the following: Perform segmented quantization on the age in the static factor data to obtain an age segmented quantization value; Perform standardization transformation on the cognitive ability score to obtain a cognitive ability standardized score; Perform binary identification on the previous missed dose history to obtain a previous missed dose history binary identification value; Extract and quantify the medication time interval and medication dose deviation from the medication record data in the dynamic factor data to obtain a medication time interval quantization value and a medication dose deviation quantization value; perform outlier detection and normalization processing on the physiological index data to obtain a physiological index normalization value; Combine the age segmented quantization value, cognitive ability standardized score, previous missed dose history binary identification value, medication time interval quantization value, medication dose deviation quantization value, and physiological index normalization value in a preset order to form a feature vector.

3. The dynamic risk assessment method for the medication of elderly patients according to claim 2, wherein The calculating a comprehensive risk score based on the feature vector through a preset evaluation rule includes the following: Multiply the age segmented quantization value, cognitive ability standardized score, previous missed dose history binary identification value, medication time interval quantization value, medication dose deviation quantization value, and physiological index normalization value in the feature vector by their corresponding weight coefficients respectively, and accumulate the multiplication results to obtain a comprehensive risk score, which is used to represent the quantization value of the medication compliance risk of elderly patients.

4. The dynamic risk assessment method for the medication of elderly patients according to claim 3, wherein Comparing the comprehensive risk score with a preset risk classification threshold to determine the medication compliance risk level of elderly patients includes the following: Preset several risk classification thresholds in advance to form a set of risk level intervals; Compare the calculated comprehensive risk score with each risk classification threshold to determine the risk level interval it belongs to; Determine the medication compliance risk level of elderly patients according to the preset corresponding relationship between the risk level interval and the medication compliance risk level.

5. The dynamic risk assessment method for drug use by elderly patients according to claim 2, characterized in that The calculating a comprehensive risk score based on the feature vector through a preset evaluation rule includes the following: Multiply the age segmented quantization value, cognitive ability standardized score, previous missed dose history binary identification value, medication time interval quantization value, medication dose deviation quantization value, and physiological index normalization value in the feature vector by their corresponding basic weight coefficients respectively to obtain a set of basic weighted intermediate values; Extract the age range corresponding to the age segment quantization value from the feature vector, as well as the drug metabolism pathway identifier in the medication record data item, to form an age-metabolism pathway cross-feature pair; retrieve the set of metabolic capacity attenuation coefficients corresponding to the cross-feature pair through the elderly medication risk factor association database; When the cross-feature pair matches an attenuation coefficient, correct the weighted terms of the medication dose deviation quantization value and the physiological index normalization value in the basic weighted intermediate value set according to the attenuation coefficient to generate a corrected weighted intermediate value; Remove the weighted terms of the medication dose deviation quantization value and the physiological index normalization value in the basic weighted intermediate value set, and accumulate the remaining basic weighted intermediate values to obtain the first part of the risk score; Accumulate the corrected weighted intermediate values to obtain the second part of the risk score; Accumulate the first part of the risk score and the second part of the risk score to obtain the comprehensive risk score.

6. The dynamic risk assessment method for the medication of elderly patients according to claim 1, wherein, Obtain the age data and previous missed dose history data of the elderly patient through the electronic medical record system; Obtain the cognitive ability score data of the elderly patient using the MMSE scale; Obtain the medication record data of the elderly patient from the electronic medication record system; Obtain the physiological index data of the elderly patient through the physiological index monitoring device.

7. The dynamic risk assessment method for the medication of elderly patients according to claim 1, wherein It also includes the following content: For different risk levels, an individualized medication guidance plan library containing medication time adjustment strategies, dose adjustment suggestions, and missed dose remedial measures is pre-configured; when the medication compliance risk level of the elderly patient is determined, the medication guidance plan corresponding to the level is retrieved from the individualized medication guidance plan library.

8. A dynamic risk assessment system for elderly patients' medication, characterized in that, Applying the method for dynamically assessing the medication risk of elderly patients according to any one of claims 1-7, including: A data acquisition module, which is used to collect the static factor data and dynamic factor data of the elderly patient. The static factor data includes age, cognitive ability score, and previous missed dose history, and the dynamic factor data includes medication record data and physiological index data; A data preprocessing module, which is used to preprocess the collected static factor data and dynamic factor data to generate a feature vector for risk assessment; A risk assessment module, which is used to calculate the comprehensive risk score based on the feature vector through a preset assessment rule; A risk grading module, which is used to compare the comprehensive risk score with a preset risk grading threshold to determine the medication compliance risk level of the elderly patient.

Images