Inpatient falling risk assessment method, apparatus and device, and storage medium

Abstract

The embodiment of the invention provides a hospitalized patient falling risk assessment method, device and equipment and a storage medium, the method is applied to the technical field of hospitalized patient management, and the method comprises the steps: obtaining multi-dimensional assessment information corresponding to a target patient; the multi-dimensional evaluation information comprises evaluation information corresponding to basic daily life activity information, evaluation information corresponding to fall risk evaluation scale information and evaluation information corresponding to a medical advice medication list; inputting the multi-dimensional assessment information into a risk assessment model for risk prediction, and obtaining a target risk prediction result; generating a target nursing scheme based on the target risk prediction result and the multi-dimensional evaluation information; and managing the target patient based on the target nursing scheme. According to the embodiment of the invention, the falling risk assessment efficiency of the inpatient can be improved, and the falling occurrence rate of the inpatient is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of inpatient management, and in particular to an inpatient fall risk assessment method, device, equipment and storage medium. BACKGROUND

[0002] For inpatient management, fall risk assessment is a crucial link. Effective fall risk assessment can not only help medical staff understand the patient's physical condition in a timely manner, but also predict potential fall risks.

[0003] Currently, there are various assessment tools for predicting fall risks, for example, BADL mainly assesses the patient's ability to perform activities of daily living, without fully considering drug factors (such as sedatives, antihypertensive drugs, etc.) and other potential risk factors; and only focusing on the impact of drugs on falls cannot comprehensively measure the overall physical function and living state of patients, and cannot obtain timely information on changes in patient drug-related risk values, resulting in a high risk of missed evaluation. In addition, manual assessment is time-consuming and labor-intensive, lacks a dynamic tracking mechanism, and cannot respond to changes in patient status in a timely manner.

[0004] Traditional single assessment methods are time-consuming and labor-intensive, lack a dynamic tracking mechanism, and cannot respond to changes in patient status in a timely manner, reducing the efficiency of inpatient fall risk assessment. SUMMARY

[0005] The embodiments of the present application provide an inpatient fall risk assessment method, device, equipment and storage medium, which can solve the problem of low inpatient fall risk assessment efficiency caused by single assessment method in the prior art.

[0006] In one aspect, the embodiments of the present application disclose an inpatient fall risk assessment method, which comprises:

[0007] Obtaining multi-dimensional assessment information corresponding to a target patient; the multi-dimensional assessment information includes assessment information corresponding to basic activities of daily living information, assessment information corresponding to fall risk assessment scale information, and assessment information corresponding to a medication list;

[0008] Inputting the multi-dimensional assessment information into a risk assessment model for risk prediction to obtain a target risk prediction result;

[0009] Generating a target care plan based on the target risk prediction result and the multi-dimensional assessment information;

[0010] Managing the target patient based on the target care plan.

[0011] Optionally, the multi-dimensional assessment information corresponding to the target patient is obtained, comprising:

[0012] Based on the drug knowledge base, the drugs related to falls in the prescription medication list are classified to obtain different drug categories, and the corresponding scores for each drug category are determined.

[0013] The first assessment information corresponding to the medication order list is obtained by multiplying each drug category by its corresponding score.

[0014] Optionally, obtaining the multi-dimensional assessment information corresponding to the target patient includes:

[0015] Determine the second assessment information corresponding to each of the multiple scale information contained in the fall risk assessment scale information;

[0016] Determine the third assessment information corresponding to each of the multiple pieces of information contained in the basic daily living activities information;

[0017] The second evaluation information is correlated with the third evaluation information to obtain the fourth evaluation information.

[0018] Optionally, generating a target care plan based on the target risk prediction results and the multi-dimensional assessment information includes:

[0019] If the target risk prediction result is high risk, an initial care plan is generated based on the target risk prediction result and the multi-dimensional assessment information.

[0020] Based on the initial nursing plan, the medication orders for the target patient were adjusted;

[0021] The medication is evaluated based on the adjusted prescription, and the fifth evaluation information corresponding to the adjusted prescription is obtained.

[0022] Based on the fifth assessment information and the fourth assessment information, the initial nursing plan is updated to obtain the target nursing plan.

[0023] Optionally, the method further includes:

[0024] Obtain the fourth assessment information of the target patient after the first time period following the initial nursing care provided according to the initial nursing plan;

[0025] Based on the first assessment information and the fourth assessment information after the first time period, the initial nursing plan is updated to obtain the target nursing plan.

[0026] Optionally, inputting the multi-dimensional assessment information into a risk assessment model for risk prediction to obtain a target risk prediction result includes:

[0027] The first assessment information is input into the risk assessment model to predict the risk and obtain the first risk prediction result.

[0028] The fourth assessment information is input into the risk assessment model to perform risk prediction, and a second risk prediction result is obtained.

[0029] Based on the first risk prediction result and the second risk prediction result, the target risk prediction result is determined.

[0030] Optionally, determining the target risk prediction result based on the first risk prediction result and the second risk prediction result includes:

[0031] If either the first risk prediction result or the second risk prediction result indicates a high risk, then the target risk prediction result is determined to be a high risk.

[0032] If both the first risk prediction result and the second risk prediction result are low risk, the target risk prediction result is determined to be low risk.

[0033] On the other hand, embodiments of the present invention disclose a fall risk assessment device for hospitalized patients, the device comprising:

[0034] The acquisition unit is used to acquire multi-dimensional assessment information corresponding to the target patient; the multi-dimensional assessment information includes assessment information corresponding to basic daily living activities, assessment information corresponding to fall risk assessment scale information, and assessment information corresponding to medication order list.

[0035] The obtaining unit is used to input the multi-dimensional assessment information into the risk assessment model to perform risk prediction and obtain the target risk prediction result.

[0036] The generation unit is used to generate a target care plan based on the target risk prediction results and the multi-dimensional assessment information;

[0037] A management unit for managing the target patient based on the target care plan.

[0038] Optionally, the acquisition unit includes:

[0039] The classification unit is used to classify the fall-related medications in the prescribed medication list according to the drug knowledge base;

[0040] The determination unit is used to obtain the different drug categories after classification and to determine the corresponding scores for each of the multiple drug categories;

[0041] A sub-unit is obtained, which is used to multiply each drug category with its corresponding score to obtain the first assessment information corresponding to the medication order list.

[0042] Optionally, the acquisition unit further includes:

[0043] The first determining unit is used to determine the second assessment information corresponding to each of the multiple scale information contained in the fall risk assessment scale information; and to determine the third assessment information corresponding to each of the multiple information contained in the basic daily living activities information.

[0044] The first obtaining unit is used to associate the second evaluation information with the third evaluation information to obtain the fourth evaluation information.

[0045] Optionally, the generation unit includes:

[0046] A generation subunit is used to generate an initial care plan based on the target risk prediction result and the multi-dimensional assessment information when the target risk prediction result is high risk.

[0047] An adjustment unit is used to adjust the medication orders for the target patient based on the initial nursing plan;

[0048] The second obtaining unit is used to evaluate the medication according to the adjusted prescription and obtain the fifth evaluation information corresponding to the adjusted prescription.

[0049] A subunit is obtained, which is used to update the initial nursing plan based on the fifth assessment information and the fourth assessment information to obtain the target nursing plan.

[0050] Optionally, the device further includes:

[0051] The first acquisition unit is used to acquire the fourth assessment information of the target patient after the first time period corresponding to the initial nursing period following the initial nursing care according to the initial nursing plan.

[0052] The first obtaining unit is used to update the initial nursing plan based on the first assessment information and the fourth assessment information after the first time period to obtain the target nursing plan.

[0053] Optionally, the obtaining unit includes:

[0054] The third obtaining unit is used to input the first assessment information into the risk assessment model to perform risk prediction and obtain a first risk prediction result; and to input the fourth assessment information into the risk assessment model to perform risk prediction and obtain a second risk prediction result.

[0055] The second determining unit is used to determine the target risk prediction result based on the first risk prediction result and the second risk prediction result.

[0056] Optionally, the second determining unit includes:

[0057] The second determining subunit is used to determine the target risk prediction result as high risk when the first risk prediction result or the second risk prediction result is high risk; and to determine the target risk prediction result as low risk when both the first risk prediction result and the second risk prediction result are low risk.

[0058] In another aspect, embodiments of the present invention also disclose an electronic device, the electronic device including a memory and one or more programs, wherein one or more programs are stored in the memory and configured to be executed by one or more processors of the aforementioned method for assessing the risk of fall in hospitalized patients.

[0059] This invention also discloses a readable storage medium, which, when the instructions in the storage medium are executed by the processor of an electronic device, enables the electronic device to perform the aforementioned method for assessing the risk of falls in hospitalized patients.

[0060] The embodiments of the present invention have the following advantages:

[0061] In this embodiment of the invention, during the fall risk assessment of hospitalized patients, multi-dimensional assessment information corresponding to the target patient is first obtained. This multi-dimensional assessment information includes assessment information corresponding to basic daily living activities, fall risk assessment scale information, and medication order list information. The multi-dimensional assessment information is then input into a risk assessment model for risk prediction, obtaining the target risk prediction result. Based on the target risk prediction result and the multi-dimensional assessment information, a target nursing plan is generated. The target patient is then managed based on this target nursing plan. This embodiment of the invention improves the efficiency of fall risk assessment for hospitalized patients by integrating multi-dimensional assessment information to formulate a target nursing plan, and then dynamically adjusts the nursing plan through real-time monitoring of the multi-dimensional assessment information, thereby reducing the incidence of falls among hospitalized patients. Attached Figure Description

[0062] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0063] Figure 1 This is a flowchart illustrating the steps of an embodiment of a fall risk assessment method for hospitalized patients according to the present invention;

[0064] Figure 2This is a schematic diagram of a multi-dimensional intelligent comprehensive assessment system for fall risk in adult hospitalized patients according to the present invention;

[0065] Figure 3 This is a structural block diagram of a fall risk assessment device for hospitalized patients according to the present invention;

[0066] Figure 4 This is a structural block diagram of an electronic device according to the present invention. Detailed Implementation

[0067] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0068] Statistics show that the incidence of falls among inpatients in general hospitals in my country ranges from 0.5‰ to 10‰, varying across different departments. For example, the incidence is relatively higher in departments such as neurology, neurosurgery, and geriatrics. Falls can lead to serious physical injuries, such as fractures and traumatic brain injuries, significantly impacting patients' quality of life and increasing the burden on healthcare providers.

[0069] Method Implementation Examples

[0070] Reference Figure 1 The diagram illustrates a step-by-step flowchart of an embodiment of a fall risk assessment method for hospitalized patients according to the present invention. The method may specifically include the following steps:

[0071] Step S101: Obtain multi-dimensional assessment information corresponding to the target patient; the multi-dimensional assessment information includes assessment information corresponding to basic daily living activities, assessment information corresponding to fall risk assessment scale information, and assessment information corresponding to medication order list.

[0072] Step S102: Input the multi-dimensional assessment information into the risk assessment model to predict the risk and obtain the target risk prediction result;

[0073] Step S103: Based on the target risk prediction results and multi-dimensional assessment information, generate a target care plan;

[0074] Step S104: Manage the target patients based on the target care plan.

[0075] Obtain multi-dimensional assessment information corresponding to the target patient; the multi-dimensional assessment information includes assessment information corresponding to basic daily living activities, assessment information corresponding to fall risk assessment scale information, and assessment information corresponding to medication prescription list.

[0076] Among them, the multi-dimensional assessment information corresponding to the target patient is an important tool for assessing an individual's ability to independently complete basic life skills. It is often used in fields such as medicine and rehabilitation, especially for assessing the functional status of the elderly, patients with chronic diseases, or people with disabilities.

[0077] For example, the Basic Activities of Daily Living (BADL) score mainly covers the following six most basic daily activities, each assigned a different score based on completion (usually using a 0-5 or 0-10 scale, which may vary slightly between different scales):

[0078] 1. Dressing: This includes putting on and taking off clothes, shoes and socks, buttoning buttons, tying shoelaces, etc.

[0079] 2. Eating: The ability to independently pick up, chew, and swallow food (excluding food preparation).

[0080] 3. Washing and grooming: personal hygiene behaviors such as washing face, brushing teeth, washing hands, combing hair, shaving (or applying makeup).

[0081] 4. Toileting: The ability to independently perform urination and defecation, wipe, tidy clothes, and use toilet aids (such as handrails).

[0082] 5. Bathing: Independently complete a shower or bath, including adjusting the water temperature and wiping the body.

[0083] 6. Mobility: Basic mobility skills such as moving from bed to chair, walking indoors, and going up and down stairs.

[0084] For example, the specific content of the assessment information corresponding to the fall risk assessment scale includes the following:

[0085] 1. Fall History: Determine if the patient has fallen during previous hospitalizations or before admission. Scoring: Yes = 1 point; No = 0 points;

[0086] 2. Restlessness: Determine if the patient exhibits restlessness, fidgeting, constant movement, or pulling on the catheter.

[0087] Rating: Yes = 1 point; No = 0 points;

[0088] 3. Visual impairment: Assess whether the patient has vision problems that affect daily activities (e.g., needing assistance to walk safely); Scoring: Yes = 1 point; No = 0 points;

[0089] 3. Frequent urination needs: Determine if the patient needs to urinate frequently (e.g., urinary frequency, urgency, diarrhea); Scoring: Yes = 1 point; No = 0 points;

[0090] 4. Transfer and mobility: Assess the patient's balance during transfers (e.g., from bed to chair) and walking;

[0091] The scoring criteria are as follows:

[0092] 0 points: Able to move and walk independently and safely (with good balance).

[0093] 1 point: Needs help or supervision from others when moving or walking (unsteady balance).

[0094] 3 points: Unable to walk independently (e.g., requires a wheelchair or is bedridden), or unable to walk safely even with assistive devices (poor balance).

[0095] For example, the drug knowledge base is invoked to identify fall-related drug categories (such as analgesics, hypnotics, antihypertensive drugs, diuretics, etc.) based on pharmacology and assign different scores (1 point, 2 points, 3 points) to obtain the assessment information corresponding to the prescription medication list.

[0096] Multi-dimensional assessment information is input into the risk assessment model to predict risk and obtain the target risk prediction result.

[0097] The risk assessment model, built upon machine learning or deep learning algorithms, comprehensively analyzes multi-dimensional assessment information to predict the fall risk of hospitalized patients. During training, the model learns from a large amount of historical data, identifying key factors related to fall risk and providing accurate predictions. In practice, healthcare professionals simply input the patient's relevant assessment information into the model to quickly obtain fall risk predictions, providing strong support for subsequent nursing care and interventions.

[0098] For example, risk prediction refers to the analysis of a patient's physical condition, past fall history, and other factors using a similar risk assessment model to predict the risk of a patient falling during hospitalization. Such predictions help healthcare professionals take timely preventative measures, such as providing assistive devices or accompanying the patient during bathing, to ensure patient safety.

[0099] Risk prediction results refer to the conclusions drawn from a comprehensive analysis of the potential fall risk of hospitalized patients based on a risk assessment model. These results quantify the degree of fall risk, providing clear reference information for healthcare professionals. If the prediction results indicate a high risk, healthcare professionals can take necessary intervention measures in advance, such as advising patients to stay near their beds to ensure their safety.

[0100] Based on the target risk prediction results and multi-dimensional assessment information, a target care plan is generated.

[0101] For example, the target care plan includes adding a yellow wristband buckle to the patient's wrist and highlighting this during shift handover; performing all procedures at the bedside as much as possible to reduce patient movement; and conducting medication education.

[0102] For example, for the daily activity of bathing, if the predicted risk of a patient's fall is high, the target care plan might include installing anti-slip facilities in the bathroom, providing a bath chair or stool, and arranging for a caregiver to accompany the patient during bathing to ensure the patient's safety. Additionally, the care plan might include providing the patient with safety education before bathing, reminding them of the slippery conditions in the bathroom and the appropriate range of motion during bathing, to further reduce the risk of falls.

[0103] Targeted care protocols are used to manage target patients.

[0104] For example, a target care plan might involve attaching a yellow wristband to the inpatient's wrist and highlighting this during shift handover. All procedures should be performed at the bedside as much as possible to minimize patient movement. Based on this plan, healthcare staff must closely monitor the patient's daily activities. Based on the patient's fall risk assessment, healthcare staff must ensure a safe environment for daily activities, such as having sufficient nursing staff present. Simultaneously, healthcare staff must provide medication education and adjust the care plan according to the actual situation to minimize the risk of falls.

[0105] In embodiments of the present invention, risk prediction is performed based on multi-dimensional assessment information to obtain risk prediction results; and a target care plan is generated based on the target risk prediction results and multi-dimensional assessment information; finally, the target patient is managed based on the target care plan. In the specific scenario of patient hospitalization, by comprehensively considering multiple dimensions such as the patient's age, physical condition, and history of falls, and using advanced algorithm models for risk prediction, a relatively accurate risk prediction result can be obtained. Based on this risk prediction result and multi-dimensional assessment information, medical staff can tailor the most suitable care plan for the patient.

[0106] In an optional embodiment of the present invention, obtaining the multi-dimensional assessment information corresponding to the target patient may specifically include the following steps:

[0107] Step S1011: Based on the drug knowledge base, classify the drugs related to falls in the prescription medication list, obtain the different drug categories after classification, and determine the corresponding scores for each of the multiple drug categories.

[0108] Step S1012: Multiply each drug category by its corresponding score to obtain the first assessment information corresponding to the prescription medication list.

[0109] Based on the drug knowledge base, the drugs related to falls in the prescription medication list are classified to obtain different drug categories, and the corresponding scores for each drug category are determined.

[0110] The drug knowledge base is a database containing detailed information on various medications. It records not only basic information such as drug name, usage, and dosage, but also specifically notes potential side effects and high-risk events, such as falls. As a crucial information source, the drug knowledge base provides a scientific basis for classifying and assigning scores to fall-related medications in prescriptions. Through precise matching and classification, healthcare professionals can quickly identify which medications may increase a patient's fall risk and adjust nursing care accordingly to ensure patient safety.

[0111] Medications associated with falls may include, but are not limited to, those with sedative, hypnotic, anti-anxiety, antidepressant, antipsychotic, antihypertensive, and hypoglycemic effects. These medications may increase the risk of falls during daily activities such as bathing by affecting the patient's nervous, cardiovascular, or metabolic systems. Therefore, when assessing the fall risk of hospitalized patients, it is essential to fully consider fall-related medications on the prescribed medication list to ensure patient safety.

[0112] Categorizing fall-related medications on the prescription list involves analyzing each drug and classifying them based on their potential fall risk. This categorization requires comprehensive consideration of the medication's side effects, mechanism of action, and impact on the patient's daily activities. This step provides a clearer understanding of which medications may increase the fall risk for hospitalized patients, thus providing strong support for subsequent fall risk assessments and the development of preventative measures.

[0113] For example, medications associated with falls can be categorized into high-risk, medium-risk, and low-risk groups based on their potential fall risk. High-risk medications typically have significant sedative, hypnotic, or antipsychotic effects, potentially leading to marked cognitive impairment or decreased balance during daily activities, thus significantly increasing the risk of falls. Medium-risk medications may indirectly increase the likelihood of falls by affecting a patient's blood pressure, blood sugar, or mental state, but their effects are relatively mild. Low-risk medications generally pose a lower risk of falls, but individual differences and potential side effects still require careful consideration during use. This classification helps healthcare professionals more accurately assess a patient's fall risk and implement appropriate preventative measures.

[0114] For example, in fall risk assessment, different scores can be assigned to different medication categories for hospitalized patients' daily activities. High-risk medications, due to their potential to cause significant cognitive impairment or decreased balance, receive the highest scores, indicating a significantly increased risk of falls during daily access when using these medications. Medium-risk medications, while having relatively milder effects, may still indirectly increase fall risk by affecting the patient's physiological state, thus receiving moderate scores. Low-risk medications, due to their lower fall risk, receive correspondingly lower scores. By assigning scores to different medication categories and combining this with other fall risk factors, a more comprehensive assessment of hospitalized patients' fall risk in daily life can be achieved, leading to the development of more precise preventative measures.

[0115] The first assessment information corresponding to the prescription medication list is obtained by multiplying each drug category by its corresponding score.

[0116] For example, the first assessment information refers to assigning a pre-set score to each drug category based on the medication order list. These scores are typically derived by comprehensively considering factors such as the drug's potential risks, side effects, and frequency of use. Subsequently, the number or frequency of each drug category appearing in the medication order is multiplied by its corresponding score, and the total score of the medication order list is obtained by summing these scores; this is the first assessment information.

[0117] For example, in determining the initial assessment information, a drug knowledge base can be accessed to identify fall-related drug categories (such as analgesics, hypnotics, antihypertensive drugs, diuretics, etc.) based on pharmacology and assign different scores (1, 2, or 3 points). A total score of ≥6 points on the drug-related fall risk assessment table indicates high risk of fall, while <6 points indicates low risk. Then, according to the drug risk score calculation method, the drug-related fall risk score is obtained, i.e., drug 1 * corresponding score + drug 2 * corresponding score + ...

[0118] For example, the system automatically identifies medications with a high risk of falls and marks them with the word "fall" before their names; it also automatically identifies changes in medication orders, displaying a corresponding identifier on the nursing documentation system's interface if such changes occur. The responsible nurse, based on the timing of the fall risk assessment, conducts a comprehensive fall risk assessment using the "Drug-Related Fall Risk Assessment Form" after daily review of medication orders, taking into account any changes in medication orders.

[0119] Refer to Table 1 for the drug-related fall risk assessment table, as shown in the table, which includes the score corresponding to the type of drug.

[0120] Table 1

[0121]

[0122] For example, a patient's medication-related fall risk score is equal to the sum of the existing fall-related medication scores. For instance, if a patient is taking three fall-related medications, then the medication-related fall risk score = medication 1 * corresponding score + medication 2 * corresponding score + medication 3 * corresponding score.

[0123] In an optional embodiment of the present invention, obtaining the multi-dimensional assessment information corresponding to the target patient may specifically include the following steps:

[0124] Step S1013: Determine the second assessment information corresponding to each of the multiple scale information contained in the fall risk assessment scale information;

[0125] Step S1014: Determine the third assessment information corresponding to each of the multiple pieces of information contained in the basic daily living activities information;

[0126] Step S1015: Associate the second evaluation information with the third evaluation information to obtain the fourth evaluation information.

[0127] Identify the secondary assessment information corresponding to each of the multiple scale information contained in the fall risk assessment scale.

[0128] In determining the secondary assessment information corresponding to each of the multiple scales in the fall risk assessment scale, each scale item is analyzed in depth to extract key data directly related to fall risk. This data may involve multiple aspects such as the patient's age, medical history, and medication use, and each item is assigned a specific weight to reflect its degree of influence on fall risk.

[0129] Identify the third assessment information corresponding to each of the multiple pieces of information contained in the basic daily living activities information.

[0130] The basic activities of daily living information includes various third-level assessments covering the patient's daily living abilities, such as walking, climbing stairs, dressing, and washing. The system will also perform detailed analysis and quantification of this information to assess the patient's activity levels and potential fall risk.

[0131] The second and third assessment information are correlated to obtain the fourth assessment information.

[0132] After obtaining the second and third assessment information, these two sets of information can be correlated and processed. This step aims to comprehensively consider the patient's physical condition and daily activity abilities, thereby more accurately predicting their fall risk. Through complex algorithms and logical operations, the system integrates the second and third assessment information into a fourth assessment information, which more comprehensively and deeply reflects the patient's fall risk status.

[0133] For example, based on the original STRATIFY assessment scale, the sum of the transfer and activity assessment scores equals 3 or 4 points. The sum of the scores for bed-chair transfer and walking on flat ground in the BADL assessment equals 15 or 20 points. The STRATIFY Fall Risk Assessment Scale automatically links to the BADL assessment and synchronizes the assessment results, generating a score equal to the sum of the patient's transfer and activity scores. A final STRATIFY assessment score of 2 indicates high risk, 1 indicates medium risk, and 0 indicates low risk.

[0134] In an optional embodiment of the present invention, generating a target care plan based on the target risk prediction results and multi-dimensional assessment information may specifically include the following steps:

[0135] Step S1031: If the target risk prediction result is high risk, generate an initial care plan based on the target risk prediction result and multi-dimensional assessment information.

[0136] Step S1032: Based on the initial nursing plan, adjust the medication orders for the target patient;

[0137] Step S1033: Evaluate the medication according to the adjusted medical order to obtain the fifth evaluation information corresponding to the adjusted medical order.

[0138] Step S1034: Based on the fifth assessment information and the fourth assessment information, update the initial nursing plan to obtain the target nursing plan.

[0139] If the target risk prediction result is high, an initial care plan is generated based on the target risk prediction result and multi-dimensional assessment information.

[0140] The initial nursing care plan refers to the preliminary nursing measures developed to prevent falls in patients based on their specific circumstances, such as age, physical condition, fall history, and other multi-dimensional assessment information, as well as the high-risk prediction result. These measures may include enhanced patient monitoring and providing assistive walking devices to reduce fall risk, aiming to lower the risk of falls for hospitalized patients during daily activities.

[0141] Based on the initial nursing plan, the medication orders for the target patients were adjusted.

[0142] Adjusting medication orders for target patients involves making necessary adjustments to the original medication prescriptions based on the patient's specific condition, fall risk assessment results, and other relevant medical information. This step aims to ensure that patients receiving medication treatment do not increase their risk of falls due to side effects or improper use. Adjustments may involve various aspects such as the type of medication, dosage, and timing of administration, ensuring that the medication effectively treats the patient's condition without unnecessarily interfering with or harming their daily activities. Through meticulous adjustments to medication orders, patients can be provided with safer and more effective treatment options, further reducing the probability of adverse events such as falls.

[0143] The medication was evaluated based on the adjusted prescription, and the fifth evaluation information corresponding to the adjusted prescription was obtained.

[0144] The fifth assessment information corresponding to the adjusted medication order refers to the assessment information obtained by reassessing the patient after the medication order has been adjusted as described above. This information aims to reflect whether the adjusted medication treatment plan poses a potential fall risk to the hospitalized patient's daily activities. By comparing the assessment results before and after the adjustment, healthcare professionals can gain a more comprehensive understanding of the patient's physical condition and fall risk, thereby providing more personalized care and rehabilitation recommendations.

[0145] Based on the information from the fifth and fourth assessments, the initial nursing plan was updated to obtain the target nursing plan.

[0146] For example, during the update of the care plan, healthcare professionals will comprehensively consider the patient's overall condition, especially changes in fall risk. If the fifth assessment indicates that the adjusted medication regimen effectively reduces the risk of falls, the care plan will emphasize continuing this medication regimen to ensure the patient's safety.

[0147] If the assessment indicates that the risk of falls remains or has increased, healthcare professionals may need to re-evaluate the effectiveness of the medication regimen and engage in in-depth communication with the patient and their family to understand the specific difficulties and needs the patient faces in daily life. Based on this, the care plan may be adjusted more meticulously, such as by adding companions, to reduce the risk of falls caused by the patient's physical limitations.

[0148] The development of a target care plan is a dynamic and comprehensive process that aims to provide patients with the most appropriate and effective nursing support and ensure their safety and comfort during hospitalization.

[0149] For example, when the target risk prediction result is high risk, the system automatically triggers an early warning, the nursing information system's simplified card interface displays the corresponding fall prevention warning sign, and automatically prompts the nurse to fasten the yellow wristband on the patient's wrist and to emphasize the handover, with all operations performed at the bedside as much as possible to reduce patient movement; and to carry out medication education.

[0150] If a change in medication orders is sent after the initial care is provided according to the initial care plan, a fall assessment alert will be automatically triggered.

[0151] STRATIFY scale (combining BADL assessment results):

[0152] Frequent toileting (1 point), transfer and activity (i.e., BADL bed-chair transfer (requires partial support, 10 points) and walking on flat ground (requires partial support, 10 points) are worth 15 or 20 points) (1 point), totaling 2 points, which is considered high risk.

[0153] Drug-related fall risk assessment form:

[0154] Estazolam (sedative-hypnotic drug, 3 points), total 3 points, low risk.

[0155] Overall assessment level:

[0156] The patient's fall risk level was high due to STRATIFY, and low due to medication-related falls. Ultimately, the patient's fall risk level remained high.

[0157] The system automatically triggers an early warning, and the nursing information system's simplified card interface displays the corresponding fall prevention warning sign. It also automatically prompts nurses to fasten the yellow wristband on the patient's wrist and to emphasize this during shift handover. All operations should be performed at the bedside as much as possible to reduce patient movement; medication education should also be conducted.

[0158] In an optional embodiment of the present invention, the method for assessing the risk of falls in hospitalized patients may specifically include the following steps:

[0159] Step S105: Obtain the fourth assessment information of the target patient after the first time period following the initial nursing care according to the initial nursing plan;

[0160] Step S106: Based on the first assessment information and the fourth assessment information after the first time period, update the initial nursing plan to obtain the target nursing plan.

[0161] Obtain the fourth assessment information of the target patient after the first time period following the initial nursing care according to the initial nursing plan.

[0162] For example, the fourth assessment information after the first time period following initial care according to the initial care plan refers to the STRATIFY scale (comprehensive BADL assessment results) after the first time period. For example, frequent toileting (1 point), transfer and activity (i.e., BADL bed-chair transfer (requiring partial support, 10 points) and walking on flat ground (requiring partial support, 10 points) are scored out of 15 or 20 points) (1 point), totaling 2 points, indicating high risk. In addition, the fourth assessment information after the first time period may also cover changes in the patient's fall risk during that time period, as well as the emergence of any new conditions or symptoms that may affect their daily behavior and fall risk.

[0163] Based on the information from the first assessment and the fourth assessment after the first time period, the initial nursing plan is updated to obtain the target nursing plan.

[0164] In cases where the first assessment information corresponding to the medication order list remains unchanged, but the fourth assessment information corresponding to the target patient changes, the initial nursing plan is updated to obtain the target nursing plan.

[0165] For example, the target care plan may include nurses fastening yellow wristbands to patients' wristbands and highlighting key points during shift handover, performing all procedures at the bedside as much as possible to reduce patient movement, and conducting medication education, etc.

[0166] In an optional embodiment of the present invention, the step of inputting multi-dimensional assessment information into a risk assessment model for risk prediction to obtain a target risk prediction result may specifically include the following steps:

[0167] Step S1021: Input the first assessment information into the risk assessment model to perform risk prediction and obtain the first risk prediction result;

[0168] Step S1022: Input the fourth assessment information into the risk assessment model to perform risk prediction and obtain the second risk prediction result;

[0169] Step S1023: Determine the target risk prediction result based on the first risk prediction result and the second risk prediction result.

[0170] The first assessment information is input into the risk assessment model to predict the risk and obtain the first risk prediction result.

[0171] The risk assessment model uses complex algorithms and logic to perform in-depth analysis and calculation of the input assessment information, ultimately outputting a preliminary risk prediction result regarding medication use. This process considers not only the risk of a single drug but also the potential interactions and risk synergistic effects of combining multiple drugs, providing a more comprehensive and accurate reference for clinical decision-making.

[0172] The fourth assessment information is input into the risk assessment model to predict the risk and obtain the second risk prediction result.

[0173] The fourth assessment information is input into the risk assessment model for risk prediction, resulting in a second risk prediction result. This process is similar to inputting the first assessment information into the risk assessment model; both involve in-depth analysis and calculation of the input information to output a risk prediction result regarding fall risk. This result can provide important reference for medical staff, helping to develop more reasonable and effective fall prevention measures.

[0174] Based on the results of the first risk prediction and the second risk prediction, the target risk prediction result is determined.

[0175] This process involves comprehensively considering the results of two risk predictions, comparing, analyzing, and possibly weighting them to arrive at a more accurate and comprehensive target risk prediction. This process may involve assessing the reliability, relevance, and importance of the two predictions to ensure that the final target risk prediction accurately reflects the patient's risk status. Such comprehensive judgment provides healthcare professionals with more precise decision support, thereby better protecting patient safety.

[0176] In an optional embodiment of the present invention, determining the target risk prediction result based on the first risk prediction result and the second risk prediction result may specifically include the following steps:

[0177] Step S10231: If the first risk prediction result or the second risk prediction result is high risk, determine that the target risk prediction result is high risk;

[0178] Step S10232: If both the first risk prediction result and the second risk prediction result are low risk, determine the target risk prediction result as low risk.

[0179] If either the first or second risk prediction result is high risk, then the target risk prediction result is determined to be high risk.

[0180] For example, the comprehensive method for determining fall risk includes either the STRATIFY score or the drug-related fall risk assessment scale score, if either is high-risk, the patient is determined to be a high-risk patient for falls; if the STRATIFY fall risk level is high-risk and the drug-related fall risk level is high-risk, the patient's final fall risk level is high-risk.

[0181] For example, patients at high risk of falling are displayed with a fall risk icon in the patient risk warning bar on the nursing information system, nurse station whiteboard, bedside screen and PDA information system. The system can also perform statistics and screening of all patients at high risk of falling.

[0182] For example, basic measures to prevent falls include: ensuring the ward is well-lit and that bedside lamps and floor lamps are in working order; keeping the ward floor dry; removing all unstable tables, chairs, and other items and obstacles; ensuring the bed is in its lowest position and the bed brakes are locked; instructing patients to wear non-slip shoes and that clothing and shoes are the correct size; encouraging patients and their families to seek help and instructing them on how to use the bathroom emergency call bell; keeping patients' daily necessities (such as water cups, tissues, glasses, bedpans, walking aids, etc.) and call buttons within easy reach; locking the wheelchair wheels and using seat belts when using a wheelchair during patient movement; providing fall prevention health education to patients and their families; and confirming with the patient that they no longer need assistance before leaving the ward.

[0183] For example, general measures for patients at high risk of falls include: adding a yellow buckle to the patient's wristband, focusing on shift handover, and following up on the implementation of preventive measures each shift; avoiding sudden changes in body position, requiring the patient to rest for 30 seconds before sitting up in bed, getting out of bed, and walking; assisting the patient with daily activities, such as standing up, squatting, personal hygiene, and toileting; arranging the patient in a room near the nurses' station for easy observation; performing all procedures at the bedside as much as possible to reduce patient movement; allowing family members to accompany the patient 24 hours a day when necessary, informing the caregiver to properly settle the patient and inform the responsible nurse before leaving; and providing targeted and personalized fall prevention education to the patient and their family.

[0184] For example, patients with impaired consciousness or abnormal behavior need to be accompanied by a dedicated caregiver; agitated patients should be given appropriate sedation or restraint as prescribed by the doctor; patients should be placed in wards close to the nurses' station; and safety education on fall prevention should be provided to raise the safety awareness of patients and caregivers.

[0185] For example, for patients with visual impairments that affect their daily living functions, two or more pairs of glasses with different uses should be prepared in advance, labeled accordingly, and placed within easy reach. Patients should be encouraged to wear their glasses while active. When caring for hemianopic patients, it is advisable to stand on the blind side and enhance the patient's perception of space and location through sound or other means. Blind patients should be cared for by a dedicated person. Patient rounds should be increased.

[0186] For example, for patients who need to use the toilet frequently, the patient should be placed in a bed close to the toilet; a urinal, bedpan, or bedside commode should be provided to the patient and placed within the patient's reach; the patient should be trained to use the urinal, bedpan, or bedside commode in bed; the patient should be trained in bladder and bowel control; the patient should be instructed to reduce water intake before bedtime; the patient should be instructed to seek help when using the toilet; and the medical staff should actively treat the primary disease.

[0187] For example, if the sum of the patient's transfer and activity scores is 3 or 4 (i.e., the sum of the scores for bed-chair transfer and walking on flat ground in the BADL assessment is 15 or 20), it is necessary to guide and assist the patient in doing rehabilitation exercises; develop a regular, personalized activity plan with the patient; keep the patient's walking aids within the patient's reach; consider using necessary protective equipment; provide necessary aids during transport; guide the patient to move slowly and provide necessary assistance.

[0188] For example, for patients using medications that increase the risk of falls, it is necessary to identify and clearly inform patients and / or caregivers about medications that may increase the risk of falls; for patients using opioid analgesics, minimize activity, such as getting out of bed, and have someone with them whenever possible; for patients using sedative-hypnotic drugs, inform them to take the medication before bedtime, and to rest in bed after taking it, and not to sit on the edge of the bed after getting up; for patients using anticonvulsants, inform them that they may experience dizziness, drowsiness, and weakness after taking the medication, and to rest in bed as much as possible. When getting out of bed, they should be accompanied by someone and follow the "three-step procedure," namely, lying down for 30 seconds, sitting up for 30 seconds, and standing for 30 seconds before taking steps to prevent falls; for patients using antihypertensive drugs, pay attention to orthostatic hypotension and blood pressure fluctuations after taking the medication, and instruct patients to follow the "three-step procedure" when getting out of bed; for patients using diuretics, inform them that they may experience frequent urination, dizziness, and weakness after taking the medication, and to follow the "three-step procedure" when getting out of bed or changing position.

[0189] If both the first and second risk prediction results are low risk, the target risk prediction result is determined to be low risk.

[0190] For example, STRATIFY's fall risk level is low, the drug-related fall risk level is low, and the patient's final fall risk level is low.

[0191] In the embodiments of the present invention, a dynamic risk assessment model is constructed by integrating BADL (Basic Activities of Daily Living) assessment, drug-induced fall risk factors, and STRATIFY scale multidimensional data to achieve closed-loop management of "assessment-early warning-intervention" and fill the gap in domestic multidimensional intelligent assessment systems.

[0192] It is applied to hospital inpatient nursing management systems, covering departments such as internal medicine, surgery, and geriatrics; it is compatible with nurse station terminals, mobile nursing apps, and hospital cloud platforms. The technology is applied to the entire process of patient admission assessment, dynamic monitoring during hospitalization, and pre-discharge risk review, enabling quantitative assessment and real-time early warning of fall risk.

[0193] Currently, the mainstream approach is to use a single scale assessment (such as the Morse scale or the STRATIFY scale) or manual judgment based on experience. Some systems integrate basic data entry functions but do not achieve multi-source data fusion analysis. For example, nursing systems used in a few hospitals in China only support the completion of the STRATIFY scale and the MORSE assessment scale used by most hospitals, but they do not link patient medication lists and BADL score data, and cannot dynamically update risk levels. Another example is the group standard "Assessment and Prevention of Fall Risk in Adult Inpatients" published by the Chinese Nursing Association. Although it mentions that taking two or more high-risk medications (such as opioid analgesics, anticonvulsants, antihypertensive diuretics, sedative-hypnotics, laxatives, and psychotropic drugs) determines a patient to be at medium risk of falling, or that using sedative-analgesics or hypnotics within 6 hours determines a patient to be at high risk of falling, it does not combine the patient's BADL assessment results. However, the risk level of each type of medication is different, thus compromising data accuracy and assessment rigor.

[0194] Existing assessment methods rely on a single scale, resulting in a missed assessment rate as high as 43.87% (data source: 2023 survey in Chinese Journal of Nursing); they also require weekly manual assessments, which cannot capture risk fluctuations caused by changes in patient medication or condition; in addition, the lack of algorithmic models leads to delayed risk warnings and reliance on nurses' proactive rounds, resulting in low efficiency.

[0195] To address the shortcomings of existing single-scale assessments, such as high missed rates and inefficient manual processes, a multi-dimensional data fusion intelligent assessment system is designed. This system can automatically integrate BADL, STRATIFY scale data, and drug risk data to improve assessment accuracy. Furthermore, it can build a dynamic risk model based on machine learning to update risk levels in real time and automatically generate intervention recommendations, thereby reducing nursing labor costs.

[0196] Refer to Table 2 for the fall risk assessment content, as shown in the table, which includes the corresponding scores for each assessment item.

[0197] Table 2

[0198]

[0199] Reference Figure 2 The figure shows a schematic diagram of a multi-dimensional intelligent comprehensive assessment system for fall risk in adult hospitalized patients according to the present invention. As shown in the figure, it includes a display layer, a business layer, cloud services, a nursing whiteboard, and a patient bedside screen. The business layer includes STRATIFY assessment and medication-related fall risk assessment, and the fall risk level is assessed based on the STRATIFY assessment and medication-related fall risk assessment.

[0200] The data acquisition layer includes inputting BADL scores (10 indicators, such as eating, dressing, walking on flat ground, bed-chair transfer, etc.) and STRATIFY scale scores (7 indicators, such as age and fall history) via PC, and automatically capturing the list of medication orders (extracting the types and dosages of drugs that caused the fall).

[0201] The algorithm layer includes data preprocessing, which involves normalizing unstructured data (such as medication texts) to generate standardized feature vectors.

[0202] By using a risk assessment model and a comprehensive judgment method (if either the STRATIFY score or the drug-related fall risk assessment scale score is determined to be of high risk, the patient is ultimately classified as having a high risk of fall), the risk level (low / medium / high) is output.

[0203] The application layer includes real-time display of risk levels on the nursing information system (PC terminal), nursing whiteboard at the nurse station, and patient bedside screen, and automatic push of intervention plans (such as fall prevention education, environmental modification suggestions, etc.).

[0204] The data flow diagram shows that nurses can synchronize patient basic information, BADL scores, medication details, and STRATIFY scale results to the hospital cloud server with one click.

[0205] The system utilizes a drug knowledge base and pharmacological analysis to identify fall-related drug categories (such as analgesics, hypnotics, antihypertensives, and diuretics) and assigns them different scores (1, 2, or 3 points). A total score of ≥6 on the drug-related fall risk assessment scale indicates high risk of falling, while <6 indicates low risk. Based on the drug risk score calculation method, the drug-related fall risk score is obtained: Drug 1 * corresponding score + Drug 2 * corresponding score + ...

[0206] The STRATIFY+BADL assessment module is based on the original STRATIFY assessment scale. The sum of the transfer and activity assessment scores equals 3 or 4 points. The sum of the scores for bed-chair transfer and walking on level ground in the BADL assessment equals 15 or 20 points. The STRATIFY Fall Risk Assessment Scale automatically links to the BADL assessment and synchronizes the results, generating a score equal to the sum of the patient's transfer and activity scores. The final total STRATIFY assessment score is 2 points, indicating high risk; 1 point indicates medium risk; and 0 points indicates low risk.

[0207] Output the risk level and nursing plan (including nursing problems and nursing intervention plans, such as adding a yellow wristband buckle to the patient's wristband, key shift handover, and follow up on the implementation of preventive measures each shift), and synchronize them to the nursing record.

[0208] For example, a 74-year-old female oncology patient was admitted on May 14 due to nausea and vomiting after chemotherapy for pancreatic malignancy. Upon admission, she was given fentanyl transdermal patch for pain relief (high-risk drug, assigned a score of 3) and estazolam (high-risk drug, assigned a score of 3). On May 17, the pain was relieved, and the fentanyl transdermal patch was discontinued, while the other medications continued.

[0209] Data collection:

[0210] May 14

[0211] STRATIFY scale (combining BADL assessment results):

[0212] Frequent toileting (1 point), transfer and activity (i.e., BADL bed-chair transfer (requires partial support, 10 points) and walking on flat ground (requires partial support, 10 points) are worth 15 or 20 points) (1 point), totaling 2 points, which is considered high risk.

[0213] Drug-related fall risk assessment form:

[0214] Fentanyl transdermal patch (opioid analgesic, 3 points) and estazolam (sedative-hypnotic drug, 3 points), totaling 6 points, are considered high-risk.

[0215] Overall assessment level:

[0216] The patient's fall risk level is high, the drug-related fall risk level is high, and the patient's ultimate fall risk level is high.

[0217] The system automatically triggers an early warning, and the nursing information system's simplified card interface displays the corresponding fall prevention warning sign. It also automatically prompts nurses to fasten the yellow wristband on the patient's wrist and to emphasize this during shift handover. All operations should be performed at the bedside as much as possible to reduce patient movement; medication education should also be conducted.

[0218] On May 17th, a change in medication orders triggered an automatic fall assessment alert in the system.

[0219] STRATIFY scale (combining BADL assessment results):

[0220] Frequent toileting (1 point), transfer and activity (i.e., BADL bed-chair transfer (requires partial support, 10 points) and walking on flat ground (requires partial support, 10 points) are worth 15 or 20 points) (1 point), totaling 2 points, which is considered high risk.

[0221] Drug-related fall risk assessment form:

[0222] Estazolam (sedative-hypnotic drug, 3 points), total 3 points, low risk.

[0223] Overall assessment level:

[0224] The patient's fall risk level was high due to STRATIFY, and low due to medication-related falls. Ultimately, the patient's fall risk level remained high.

[0225] The system automatically triggers an early warning, and the nursing information system's simplified card interface displays the corresponding fall prevention warning sign. It also automatically prompts nurses to fasten the yellow wristband on the patient's wrist and to emphasize this during shift handover. All operations should be performed at the bedside as much as possible to reduce patient movement; medication education should also be conducted.

[0226] Using the above methods, the accuracy of assessments can be improved by 70% (compared to the single STRATIFY scale); in terms of operational effectiveness, nurses' assessment time is reduced by 50%; and the incidence of falls among hospitalized patients is reduced from 0.52‰ to 0.11‰.

[0227] For example, a rule engine is used instead of a machine learning model to determine risk levels through a combination of preset thresholds. However, this approach cannot adapt to the differences in patient characteristics across different departments (e.g., different weights of risk factors between surgery and geriatrics), resulting in weak generalization ability. Alternatively, only the BADL and STRATIFY scales are integrated, ignoring medication risks. This leads to underestimation of the risk of falls due to medication side effects, particularly ineffective for elderly patients.

[0228] In embodiments of the present invention, a multi-dimensional data fusion algorithm (BADL, drug, STRATIFY weight allocation mechanism) is used; a dynamic risk update mechanism (real-time reassessment based on medication adjustments and changes in condition) is implemented; and intervention plans are automatically generated using rules (mapping relationship between risk level and nursing measures).

[0229] For example, in an embodiment of the present invention, the method for assessing the risk of falls in hospitalized patients includes steps of data collection, weighted fusion, and risk classification; the architecture of the assessment system includes the interaction logic of the data collection layer, the algorithm layer, and the application layer; and it also includes an intelligent assessment module with a knowledge base of drugs that cause falls.

[0230] In summary, this invention, in the process of assessing the fall risk of hospitalized patients, first obtains multi-dimensional assessment information corresponding to the target patient. This multi-dimensional assessment information includes assessment information corresponding to basic daily living activities, fall risk assessment scale information, and medication order list information. The multi-dimensional assessment information is then input into a risk assessment model for risk prediction, obtaining the target risk prediction result. Based on the target risk prediction result and the multi-dimensional assessment information, a target nursing plan is generated. The target patient is then managed based on this target nursing plan. This invention can improve the efficiency of fall risk assessment for hospitalized patients by integrating multi-dimensional assessment information to formulate a target nursing plan, and then dynamically adjust the nursing plan through real-time monitoring of the multi-dimensional assessment information, thereby reducing the incidence of falls among hospitalized patients.

[0231] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0232] Device Examples

[0233] Reference Figure 3 The diagram shows a structural block diagram of a fall risk assessment device for hospitalized patients according to the present invention. The fall risk assessment device 60 for hospitalized patients may specifically include:

[0234] The acquisition unit 601 is used to acquire multi-dimensional assessment information corresponding to the target patient; the multi-dimensional assessment information includes assessment information corresponding to basic daily living activities, assessment information corresponding to fall risk assessment scale information, and assessment information corresponding to medication order list.

[0235] The obtaining unit 602 is used to input the multi-dimensional assessment information into the risk assessment model to perform risk prediction and obtain the target risk prediction result;

[0236] The generation unit 603 is used to generate a target care plan based on the target risk prediction results and the multi-dimensional assessment information;

[0237] Management unit 604 is used to manage the target patient based on the target care plan.

[0238] Optionally, the acquisition unit includes:

[0239] The classification unit is used to classify the fall-related medications in the prescribed medication list according to the drug knowledge base;

[0240] The determination unit is used to obtain the different drug categories after classification and to determine the corresponding scores for each of the multiple drug categories;

[0241] A sub-unit is obtained, which is used to multiply each drug category with its corresponding score to obtain the first assessment information corresponding to the medication order list.

[0242] Optionally, the acquisition unit further includes:

[0243] The first determining unit is used to determine the second assessment information corresponding to each of the multiple scale information contained in the fall risk assessment scale information; and to determine the third assessment information corresponding to each of the multiple information contained in the basic daily living activities information.

[0244] The first obtaining unit is used to associate the second evaluation information with the third evaluation information to obtain the fourth evaluation information.

[0245] Optionally, the generation unit includes:

[0246] A generation subunit is used to generate an initial care plan based on the target risk prediction result and the multi-dimensional assessment information when the target risk prediction result is high risk.

[0247] An adjustment unit is used to adjust the medication orders for the target patient based on the initial nursing plan;

[0248] The second obtaining unit is used to evaluate the medication according to the adjusted prescription and obtain the fifth evaluation information corresponding to the adjusted prescription.

[0249] A subunit is obtained, which is used to update the initial nursing plan based on the fifth assessment information and the fourth assessment information to obtain the target nursing plan.

[0250] Optionally, the device further includes:

[0251] The first acquisition unit is used to acquire the fourth assessment information of the target patient after the first time period corresponding to the initial nursing period following the initial nursing care according to the initial nursing plan.

[0252] The first obtaining unit is used to update the initial nursing plan based on the first assessment information and the fourth assessment information after the first time period to obtain the target nursing plan.

[0253] Optionally, the obtaining unit includes:

[0254] The third obtaining unit is used to input the first assessment information into the risk assessment model to perform risk prediction and obtain a first risk prediction result; and to input the fourth assessment information into the risk assessment model to perform risk prediction and obtain a second risk prediction result.

[0255] The second determining unit is used to determine the target risk prediction result based on the first risk prediction result and the second risk prediction result.

[0256] Optionally, the second determining unit includes:

[0257] The second determining subunit is used to determine the target risk prediction result as high risk when the first risk prediction result or the second risk prediction result is high risk; and to determine the target risk prediction result as low risk when both the first risk prediction result and the second risk prediction result are low risk.

[0258] In summary, this invention provides a fall risk assessment device for hospitalized patients. This device first acquires multi-dimensional assessment information corresponding to the target patient during the fall risk assessment process. This multi-dimensional assessment information includes assessment information corresponding to basic daily living activities, fall risk assessment scale information, and medication order list information. The multi-dimensional assessment information is then input into a risk assessment model for risk prediction, obtaining a target risk prediction result. Based on the target risk prediction result and the multi-dimensional assessment information, a target nursing plan is generated. Finally, the target patient is managed based on the target nursing plan. This invention improves the efficiency of fall risk assessment for hospitalized patients by integrating multi-dimensional assessment information to formulate a target nursing plan, and then dynamically adjusts the nursing plan through real-time monitoring of the multi-dimensional assessment information, thereby reducing the incidence of falls among hospitalized patients.

[0259] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0260] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0261] This invention provides an electronic device for assessing the fall risk of hospitalized patients. The electronic device includes a memory and one or more programs, which are stored in the memory and configured to be executed by one or more processors. The programs contain instructions for performing the following operations: During the fall risk assessment of hospitalized patients, firstly, multi-dimensional assessment information corresponding to the target patient is acquired; the multi-dimensional assessment information includes assessment information corresponding to basic daily living activities, assessment information corresponding to fall risk assessment scale information, and assessment information corresponding to medication orders; the multi-dimensional assessment information is input into a risk assessment model for risk prediction to obtain a target risk prediction result; based on the target risk prediction result and the multi-dimensional assessment information, a target nursing plan is generated; and the target patient is managed based on the target nursing plan. This invention can improve the efficiency of fall risk assessment for hospitalized patients and reduce the incidence of falls by integrating multi-dimensional assessment information to formulate a target nursing plan and then dynamically adjusting the nursing plan through real-time monitoring of the multi-dimensional assessment information.

[0262] Reference Figure 4 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Figure 4 As shown, the electronic device includes a processor, a memory, a communication interface, and a communication bus. The processor, the memory, and the communication interface communicate with each other through the communication bus. The memory stores executable instructions, which cause the processor to execute the hospitalized patient fall risk assessment method of the aforementioned embodiment.

[0263] The processor can be a CPU, a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), a FPGA (Field Programmable Gate Array), or other programmable devices, transistor logic devices, hardware components, or any combination thereof. The processor can also be a combination that implements computational functions, such as a combination of one or more microprocessors, or a combination of a DSP and a microprocessor.

[0264] The communication bus may include a path for transmitting information between the memory and the communication interface. The communication bus may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by only one line, but this does not mean that there is only one bus or one type of bus.

[0265] The memory may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or it may be EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory), magnetic tape, floppy disk, and optical data storage devices, etc.

[0266] This invention also provides a non-transitory computer-readable storage medium that, when instructions in the storage medium are executed by a processor of an electronic device (server or terminal), enables the processor to perform... Figure 1 The method for assessing the risk of falls in hospitalized patients is shown.

[0267] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0268] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0269] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0270] These computer program instructions may also be stored in a computer-readable storage medium capable of directing a computer or other programmable data processing terminal device to operate in a predictive manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0271] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0272] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0273] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0274] The above provides a detailed description of the method, apparatus, equipment, and storage medium for assessing the fall risk of hospitalized patients provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for assessing the risk of falls in hospitalized patients, characterized in that, The method includes: Obtain multi-dimensional assessment information corresponding to the target patient; the multi-dimensional assessment information includes assessment information corresponding to basic daily living activities, assessment information corresponding to fall risk assessment scale information, and assessment information corresponding to medication order list; The multi-dimensional assessment information is input into the risk assessment model to predict the risk and obtain the target risk prediction result. Based on the target risk prediction results and the multi-dimensional assessment information, a target care plan is generated; The target patient is managed based on the target care plan.

2. The method according to claim 1, characterized in that, The acquisition of multi-dimensional assessment information corresponding to the target patient includes: Based on the drug knowledge base, the drugs related to falls in the prescription medication list are classified to obtain different drug categories, and the corresponding scores for each drug category are determined. The first assessment information corresponding to the medication order list is obtained by multiplying each drug category by its corresponding score.

3. The method according to claim 1, characterized in that, The acquisition of multi-dimensional assessment information corresponding to the target patient includes: Determine the second assessment information corresponding to each of the multiple scale information contained in the fall risk assessment scale information; Determine the third assessment information corresponding to each of the multiple pieces of information contained in the basic daily living activities information; The second evaluation information is correlated with the third evaluation information to obtain the fourth evaluation information.

4. The method according to claim 3, characterized in that, The process of generating a target care plan based on the target risk prediction results and the multi-dimensional assessment information includes: If the target risk prediction result is high risk, an initial care plan is generated based on the target risk prediction result and the multi-dimensional assessment information. Based on the initial nursing plan, the medication orders for the target patient were adjusted; The medication is evaluated based on the adjusted prescription, and the fifth evaluation information corresponding to the adjusted prescription is obtained. Based on the fifth assessment information and the fourth assessment information, the initial nursing plan is updated to obtain the target nursing plan.

5. The method according to any one of claims 2 to 4, characterized in that, The method further includes: Obtain the fourth assessment information of the target patient after the first time period following the initial nursing care provided according to the initial nursing plan; Based on the first assessment information and the fourth assessment information after the first time period, the initial nursing plan is updated to obtain the target nursing plan.

6. The method according to any one of claims 2 to 3, characterized in that, The step of inputting the multi-dimensional assessment information into the risk assessment model for risk prediction to obtain the target risk prediction result includes: The first assessment information is input into the risk assessment model to predict the risk and obtain the first risk prediction result. The fourth assessment information is input into the risk assessment model to perform risk prediction, and a second risk prediction result is obtained. Based on the first risk prediction result and the second risk prediction result, the target risk prediction result is determined.

7. The method according to claim 6, characterized in that, The step of determining the target risk prediction result based on the first risk prediction result and the second risk prediction result includes: If either the first risk prediction result or the second risk prediction result indicates a high risk, then the target risk prediction result is determined to be a high risk. If both the first risk prediction result and the second risk prediction result are low risk, the target risk prediction result is determined to be low risk.

8. A fall risk assessment device for hospitalized patients, characterized in that, The device includes: The acquisition unit is used to acquire multi-dimensional assessment information corresponding to the target patient; the multi-dimensional assessment information includes assessment information corresponding to basic daily living activities, assessment information corresponding to fall risk assessment scale information, and assessment information corresponding to medication order list. The obtaining unit is used to input the multi-dimensional assessment information into the risk assessment model to perform risk prediction and obtain the target risk prediction result. The generation unit is used to generate a target care plan based on the target risk prediction results and the multi-dimensional assessment information; A management unit for managing the target patient based on the target care plan.

9. An electronic device, characterized in that, The electronic device includes a memory and one or more programs, wherein one or more programs are stored in the memory and configured to be executed by one or more processors using the hospitalized patient fall risk assessment method as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the processor is able to perform the hospitalized patient fall risk assessment method as described in any one of claims 1 to 7.

Images