CN116759094A - Evaluation system and method for senile community acquired pneumonia death risk - Google Patents

Evaluation system and method for senile community acquired pneumonia death risk Download PDF

Info

Publication number
CN116759094A
CN116759094A CN202310831340.8A CN202310831340A CN116759094A CN 116759094 A CN116759094 A CN 116759094A CN 202310831340 A CN202310831340 A CN 202310831340A CN 116759094 A CN116759094 A CN 116759094A
Authority
CN
China
Prior art keywords
death
indexes
risk
curb
elderly
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310831340.8A
Other languages
Chinese (zh)
Inventor
戈艳蕾
刘聪辉
崔俊昌
王景梅
高珊
刘靖轩
白静
张嘉宾
付爱双
陈前程
范竹
董爱英
陈伟彬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Affiliated Hospital Of North China University Of Science And Technology
Original Assignee
Affiliated Hospital Of North China University Of Science And Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Affiliated Hospital Of North China University Of Science And Technology filed Critical Affiliated Hospital Of North China University Of Science And Technology
Priority to CN202310831340.8A priority Critical patent/CN116759094A/en
Publication of CN116759094A publication Critical patent/CN116759094A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Public Health (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Physics & Mathematics (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Pathology (AREA)
  • Mathematical Optimization (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Biomedical Technology (AREA)
  • Computational Mathematics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Operations Research (AREA)
  • Probability & Statistics with Applications (AREA)
  • Evolutionary Biology (AREA)
  • Algebra (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

The application discloses an evaluation system and method for the death risk of senile community acquired pneumonia, wherein the evaluation system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring clinical data and clinical detection indexes of elderly patients suffering from senile community acquired pneumonia and carrying out reinforced CURB scoring and PSI scoring on each of the elderly patients; the data preprocessing module is used for processing clinical data and clinical detection indexes; the statistical analysis module is used for carrying out statistical analysis on clinical data and clinical detection indexes, selecting indexes with statistical significance as independent variables by taking the survival of the elderly patients as the dependent variables, and carrying out multi-factor analysis to obtain evaluation indexes; the risk assessment module is used for constructing a death risk assessment model based on the reinforced CURB-PCT combination, and inputting assessment indexes into the death risk assessment model to assess the death risk of the elderly patient. The evaluation system has higher accuracy of the evaluation result and simpler and more convenient operation.

Description

Evaluation system and method for senile community acquired pneumonia death risk
Technical Field
The application belongs to the technical field of machine learning, and particularly relates to an evaluation system and method for the risk of acquired pneumonia death in an aged community.
Background
Community-acquired pneumonia (Community-acquired pneumonia, CAP) is the most common respiratory disease worldwide, and is also the most common infection among all age groups that can lead to hospitalization and death, with a fatal position in the third world. But the susceptibility and mortality rate are higher in the elderly, the people with serious basic diseases and immune function defects.
At present, various scoring systems are internationally applied to the evaluation of the severity and the prognosis prediction of CAP, such as CURB-65 scoring, are simple and easy to operate, are widely applied to clinic at present, and have the main functions of evaluating the severity of the illness at the initial diagnosis of patients, but do not consider the influence of the combined basic illness condition of CAP patients, other assay indexes except renal functions and pulmonary imaging examination results on the severity of the illness, and are insufficient in predicting short-term mortality and clinical outcome. The method is widely used for grading the severity index of the pneumonia, covers approximately 20 reference projects such as demographic indexes, mind, vital signs, arterial blood gas PH values, basic diseases and the like, can accurately layer and evaluate the diseases, but has complicated projects, relatively complex calculation and limitation of being widely popularized in emergency cases with a large number of patients and rapid change of the illness.
Therefore, it is highly desirable to provide a more accurate and effective evaluation system and method for risk of acquired pneumonia death in the elderly community.
Disclosure of Invention
The application aims to provide a system and a method for evaluating the risk of acquired pneumonia death of an elderly community, which are used for solving the problems in the prior art.
In order to achieve the above purpose, the application provides an evaluation system for the risk of acquired pneumonia death in an aged community, which comprises a data acquisition module, a data preprocessing module, a statistical analysis module and a risk evaluation module which are connected in sequence, wherein:
the data acquisition module is used for acquiring clinical data and clinical detection indexes of elderly patients suffering from senile community acquired pneumonia, and carrying out reinforced CURB scoring and PSI scoring on each of the elderly patients;
the data preprocessing module is used for cleaning and regulating the clinical data and clinical detection indexes;
the statistical analysis module is used for carrying out statistical analysis on the processed clinical data and clinical detection indexes, selecting indexes with statistical significance as independent variables by taking the survival or non-survival of the elderly patients as the dependent variables, and carrying out multi-factor analysis to obtain evaluation indexes of death risk of the elderly patients;
the risk assessment module is used for constructing a death risk assessment model based on the reinforced CURB-PCT combination, and inputting the death risk assessment index into the death risk assessment model to assess the death risk of the elderly patient.
Optionally, the clinical data of the elderly patient includes at least: name, gender, age, hospitalization time, whether to stay in the intensive care unit, 28-day return, history of illness, history of smoking, history of drinking; wherein the disease history comprises at least: hypertension, chronic obstructive pulmonary disease, congestive heart failure, coronary heart disease, diabetes, cerebral stroke, solid tumors without metastasis, kidney disease, history of surgery, history of trauma;
the clinical detection indexes at least comprise physical examination, assay indexes, blood gas analysis indexes and imaging examination; wherein the physical examination includes: body temperature, heart rate, respiratory rate, blood pressure, and disturbance of consciousness; the assay index comprises: white blood cells, lymphocytes, platelets, red blood cell volume distribution width, hematocrit, hemoglobin, albumin, total cholesterol, triglycerides, procalcitonin, sodium, blood glucose, and urea nitrogen; the blood gas analysis index comprises: PH value, oxygen partial pressure, carbon dioxide partial pressure, blood oxygen saturation and oxygenation index; the imaging examination includes: chest radiographs, chest CT with or without lung nodules, pleural effusion and multiple lobular infiltration.
Optionally, the statistical analysis module comprises a statistical unit and an analysis unit; the statistical unit is used for dividing the acquired elderly patients into a survival group and a death group, carrying out normal examination on the clinical indexes and clinical detection indexes after pretreatment, and carrying out t-test on the average number between the survival group and the death group based on independent samples for indexes meeting normal distribution; for indexes of the non-normal distribution, the median between the survival group and the death group is checked based on the rank sum, and then the statistical result of all indexes is obtained.
Optionally, the analysis unit is used for presetting a statistical threshold value, and comparing the statistical results of all indexes with the statistical threshold value to obtain the indexes with statistical significance; furthermore, whether the elderly patient survives or not is taken as a dependent variable, an index with statistical significance is taken as an independent variable, and a two-class Logistic regression is adopted to carry out multi-factor analysis, so as to obtain an evaluation index of death risk;
wherein the statistically significant indicators include: consciousness disturbance, check-in ICU, coronary heart disease, systolic pressure, diastolic pressure, platelet, neutrophil to lymphocyte count ratio, albumin, total cholesterol, procalcitonin, urea nitrogen, PSI score, enhanced CURB score, hypoxia, multiple lobe infiltration, pleural effusion; the evaluation index of the death risk comprises the following steps: diastolic pressure, neutrophil to lymphocyte count ratio, procalcitonin, PSI score, and boost CURB score.
Optionally, the risk assessment module comprises a model building unit and a risk assessment unit;
the model construction unit is used for discarding the PSI score after comparing and analyzing the corresponding prediction result with the real situation of the advanced patient based on the PSI score, the reinforced CURB score, the PCT and NLR death risks of the advanced patient; performing correlation analysis on the reinforced CURB score, the PCT and the NLR, constructing reinforced CURB-PCT combination and reinforced CURB-NLR combination, respectively predicting death risk of the elderly patient, comparing the corresponding prediction result with the real situation of the elderly patient again, and taking the reinforced CURB-PCT combination with highest sensitivity and specificity as a death risk assessment model;
the risk assessment unit is used for inputting the assessment index of the death risk into the death risk assessment model to assess the death risk of the elderly patient.
The application also provides an evaluation method of the senile community acquired pneumonia death risk, which comprises the following steps:
collecting clinical data and clinical detection indexes of elderly patients suffering from senile community acquired pneumonia, and carrying out reinforced CURB score and PSI score on each of the elderly patients;
cleaning and orderly preprocessing the clinical data and clinical detection indexes;
carrying out statistical analysis on the pretreated clinical data and clinical detection indexes, selecting indexes with statistical significance as independent variables by taking the survival of the elderly patients as dependent variables, and carrying out multi-factor analysis to obtain evaluation indexes of death risk of the elderly patients;
and constructing a death risk assessment model based on the reinforced CURB-PCT combination, and inputting the death risk assessment index into the death risk assessment model to assess the death risk of the elderly patient.
Optionally, the process of statistically analyzing the pre-processed clinical data and clinical test indicators includes: dividing the acquired elderly patients into a survival group and a death group, carrying out normal examination on the pretreated clinical indexes and clinical detection indexes, and carrying out t-test on the average number between the survival group and the death group based on independent samples for indexes meeting normal distribution; for indexes of the non-normal distribution, the median between the survival group and the death group is checked based on the rank sum, and then the statistical result of all indexes is obtained.
Optionally, the process of obtaining an assessment of mortality risk of an elderly patient comprises: presetting a statistical threshold, and comparing the statistical results of all indexes with the statistical threshold to obtain indexes with statistical significance; and then taking whether the elderly patient survives or not as a dependent variable, taking an index with statistical significance as an independent variable, and adopting two-class Logistic regression to carry out multi-factor analysis so as to obtain an evaluation index of death risk.
Optionally, the construction process of the death risk assessment model includes: based on PSI score, reinforced CURB score, PCT and NLR, comparing and analyzing the corresponding prediction result with the real situation of the advanced patient, and discarding the PSI score; and further carrying out correlation analysis on the reinforced CURB score, the PCT and the NLR, constructing reinforced CURB-PCT combination and reinforced CURB-NLR combination, respectively predicting death risk of the elderly patient, comparing the corresponding prediction result with the real situation of the elderly patient again, and taking the reinforced CURB-PCT combination with highest sensitivity and specificity as a death risk assessment model.
The application has the technical effects that:
the death risk assessment model provided by the application has better universality and robustness, combines clinical detection indexes, selects a more representative risk index from the clinical detection indexes to carry out risk assessment on emergency situations and risk degrees of patients, and is beneficial to early taking corresponding measures; the evaluation system has higher accuracy of evaluation results, is simpler and more convenient to operate, and is suitable for being used in more different areas and institutions.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:
FIG. 1 is a schematic diagram of an evaluation system for risk of acquired pneumonia death in an senile community according to an embodiment of the present application;
fig. 2 is a flow chart of a method for evaluating risk of acquired pneumonia death in an senile community according to an embodiment of the present application.
Detailed Description
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
Example 1
As shown in fig. 1, the embodiment provides an evaluation system for risk of acquired pneumonia death in an elderly community, which includes a data acquisition module, a data preprocessing module, a statistical analysis module and a risk evaluation module that are sequentially connected, wherein:
the data acquisition module is used for acquiring clinical data and clinical detection indexes of elderly patients suffering from senile community acquired pneumonia, and carrying out reinforced CURB scoring and PSI scoring on each of the elderly patients;
the data preprocessing module is used for cleaning and regulating the clinical data and clinical detection indexes;
the statistical analysis module is used for carrying out statistical analysis on the processed clinical data and clinical detection indexes, selecting indexes with statistical significance as independent variables by taking the survival or non-survival of the elderly patients as the dependent variables, and carrying out multi-factor analysis to obtain evaluation indexes of death risk of the elderly patients;
the risk assessment module is used for constructing a death risk assessment model based on the reinforced CURB-PCT combination, and inputting the death risk assessment index into the death risk assessment model to assess the death risk of the elderly patient.
Clinical data for an elderly patient may include at least: name, gender, age, hospitalization time, whether to stay in the intensive care unit, 28-day return, history of illness, history of smoking, history of drinking; wherein the disease history comprises at least: hypertension, chronic obstructive pulmonary disease, congestive heart failure, coronary heart disease, diabetes, cerebral stroke, solid tumors without metastasis, kidney disease, history of surgery, history of trauma;
the clinical detection indexes at least comprise physical examination, assay indexes, blood gas analysis indexes and imaging examination; wherein the physical examination includes: body temperature, heart rate, respiratory rate, blood pressure, and disturbance of consciousness; the assay index comprises: white blood cells, lymphocytes, platelets, red blood cell volume distribution width, hematocrit, hemoglobin, albumin, total cholesterol, triglycerides, procalcitonin, sodium, blood glucose, and urea nitrogen; the blood gas analysis index comprises: PH value, oxygen partial pressure, carbon dioxide partial pressure, blood oxygen saturation and oxygenation index; the imaging examination includes: chest radiographs, chest CT with or without lung nodules, pleural effusion and multiple lobular infiltration.
After the data are collected, each study object is respectively scored according to the reinforced CURB scoring and PSI scoring standard and filled in an Excel questionnaire.
The statistical analysis module comprises a statistical unit and an analysis unit; the statistical unit is used for dividing the acquired elderly patients into survival groups and death groups, and carrying out normal examination on the pretreated clinical indexes and clinical detection indexes, wherein metering data meeting normal distribution is represented by mean number +/-standard deviation, and independent sample t-test is adopted for mean number comparison between the two groups; the non-normally distributed metering data is represented by "median (quartile range)", and the median comparison between two sets uses rank sum test (Mann-Whitney test). The group composition comparison adopts 2 tests, and then the statistical result of all indexes is obtained.
The analysis unit is used for presetting a statistical threshold value, and comparing the statistical results of all indexes with the statistical threshold value to obtain indexes with statistical significance; furthermore, whether the elderly patient survives or not is taken as a dependent variable, an index with statistical significance is taken as an independent variable, and a two-class Logistic regression is adopted to carry out multi-factor analysis, so as to obtain an evaluation index of death risk; wherein the statistically significant indicators include: consciousness disturbance, in-circuit ICU, coronary heart disease, systolic pressure, diastolic pressure, platelets, NLR (neutrophil to lymphocyte count ratio), albumin, total cholesterol, procalcitonin (PCT), urea nitrogen, pneumonia severity scoring system (PSI score), scoring system enhancement of severity of community-acquired pneumonia (CURB score), hypoxia, multiple lobe infiltration, pleural effusion; the evaluation index of the death risk comprises the following steps: diastolic blood pressure, NLR, PCT, PSI score, boost CURB score.
As a specific example, the results of comparing clinical data from the surviving and dying groups of patients with senile Community Acquired Pneumonia (CAP) are shown below:
1) Comparison of two general sets of features
The study included 172 cases, the age range of the inclusion patients was 65-95 years, and the average age was 77.73 + -7.95 years. 134 patients in the surviving group and 38 patients in the dead group, there was no statistical difference in mean age between the surviving group and the dead group (77.45.+ -. 7.87 vs. 78.71.+ -. 8.26, P > 0.05). 98 male patients and 74 female patients. Survival group men 79 and women 55. The death group had 19 men and 19 women. There was no statistical difference in gender between the two groups (P > 0.05). 150 conscious persons, 22 conscious disturbance persons, 123 conscious persons and 11 conscious disturbance persons in the survival group, 27 conscious persons and 11 conscious disturbance persons in the death group, and statistical difference (P < 0.05) exists between the two groups. Median hospitalization for 11 days (8 days, 18 days) in the surviving group, median hospitalization for 13 days (10 days, 24 days) in the dead group, and no statistical significance (P > 0.05) was observed between the two groups. 123 non-smokers, 49 smokers, 94 and 40 non-smokers and 40 smokers in the surviving group, 29 and 9 non-smokers and 9 smokers in the dead group, respectively, and there was a statistical difference (P > 0.05) between the two groups. 142 non-drinkers, 30 drinkers, 110 and 24 survival groups, 32 death groups, and 6 drinkers, respectively, and no statistical difference (P > 0.05) between the two groups. 136 patients without surgical history, 36 patients with surgical history, 106 patients with survival group without surgical history and 28 patients with surgical history, 30 patients with death group without surgical history and 8 patients with surgical history, and two groups without statistical difference (P > 0.05) in presence of surgical history. The number of non-live ICU110, live ICU62, the number of live groups non-live ICU and live ICU 91 and 43 respectively, the number of dead groups non-live ICU and live ICU 19 and 19 respectively, and the difference between the two groups is statistically significant (P < 0.05). See table 1.
TABLE 1
Note that: a mean ± standard deviation: b t-value for the average comparison t-test: c median (quartile spacing): * comparing the rank sum checked z value for the median; the other numbers in (%)
2) Comparison of two groups of underlying diseases
The difference in the proportion of surviving and dead groups and coronary heart disease was statistically significant (P < 0.05). The ratio difference between the two groups combined with hypertension, COPD, congestive heart failure, diabetes, cerebral apoplexy, solid tumor without metastasis, metastasis and kidney disease has no statistical significance (P > 0.05). See table 2.
TABLE 2
Note that: the numbers in the ()'s in the tables are constituent ratios (%)
3) Comparison of two sets of vital signs
The difference was statistically significant (P < 0.05) in the comparison of systolic and diastolic blood pressure in the surviving and dead groups. The body temperature, pulse and respiratory rate of the two groups are compared, and the difference has no statistical significance (P is more than 0.05). See table 3.
TABLE 3 Table 3
Note that: the numbers in the table () are the quartile spacing
4) Comparison of two groups of assay indicators
The differences were statistically significant (P < 0.05) in the surviving group compared to the platelets, NLR, albumin, TC, PCT, urea nitrogen levels in the dead group. The difference was statistically significant (P > 0.05) in comparison of the white blood cell, lymphocyte, RDW, hematocrit, hemoglobin, TG, sodium, blood glucose levels between the two groups. See table 4.
TABLE 4 Table 4
Note that: a mean ± standard deviation: b t-value for the average comparison t-test: () The internal number is the interquartile spacing
5) The PSI scores of the two groups of PSI scores and the reinforced CURB scores were compared with those of the death group of patients, the reinforced CURB scores were significantly higher than those of the survival group, and the difference was statistically significant (P < 0.05). See table 5.
TABLE 5
6) The ratio of the hypoxia to the hypoxia, the multi-lobe infiltration and the hydrothorax in the death group is higher than that in the survival group compared with the imaging performance of the two groups, the difference has statistical significance (P is less than 0.05), and the ratio difference of the lung nodules between the two groups has no statistical significance (P is more than 0.05). See table 6.
TABLE 6
Note that: () The internal numbers are constituent ratios (%)
PSI score, boost CURB score, relationship analysis of PCT, NLR and senile CAP prognosis:
1) The relation analysis of PSI score and senile CAP prognosis takes two groups of median 109 of PSI score as a critical value, PSI score is more than or equal to 109 as exposure, otherwise, PSI score is not exposure, the relation of PSI score and senile CAP prognosis is analyzed, and the result is shown in Table 7. The results show that the risk of senile CAP death in the exposed population is 9.19 times that in the non-exposed population, and has statistical significance (P < 0.05), indicating that the PSI score is closely related to the prognosis of senile CAP death.
TABLE 7
2) Analysis of relationship between enhanced CURB score and senile CAP prognosis
The relationship between the reinforced CURB score and the aged CAP prognosis was analyzed with the median 10 of the reinforced CURB score as the threshold, the reinforced CURB score > 10 as the exposure, and the non-exposure, and the results are shown in Table 8. The results showed that the risk of senile CAP death in the exposed population was 9.78 times that in the non-exposed population, with statistical significance (P < 0.05), indicating that the boost CURB score was closely related to the prognosis of senile CAP death.
TABLE 8
3) Analysis of relationship between PCT and senile CAP prognosis
PCT two groups with median 0.44 as critical value and PCT > 0.44 as exposure, otherwise non-exposure, and analysis of PCT and senile CAP prognosis relationship, the results are shown in Table 9. The results show that the risk of senile CAP death in the exposed population is 9.48 times that in the non-exposed population, with statistical significance (P < 0.05), indicating that PCT is closely related to the prognosis of senile CAP death.
TABLE 9
Analysis of relationship between NLR and senile CAP prognosis
The relationship between NLR score and aged CAP prognosis is analyzed with the median 4.80 of the NLR groups as the critical value and NLR > 4.80 as the exposure, or not as the exposure, and the results are shown in Table 10. The results show that the risk of senile CAP death in the exposed population is 8.92 times that in the non-exposed population, and has statistical significance (P < 0.05), indicating that NLR is closely related to the prognosis of senile CAP death.
Table 10
The above 16 statistically significant indicators were used as independent variables (consciousness disturbance, check-in ICU, coronary heart disease, systolic pressure, diastolic pressure, platelets, NLR, albumin, TC, PCT, urea nitrogen, PSI score, intensive cure score, hypoxia, multipulmonary lobe infiltration, pleural effusion), and whether old CAP survived or died was used as dependent variable (assignment of each variable is shown in table 11), and a multifactor Logistic regression analysis was performed.
TABLE 11
The multi-factor Logistic regression analysis shows that: diastolic blood pressure, NLR, PCT, PSI score, and fortified CURB score are closely related to the risk of death in elderly CAP patients, see table 12. Indicating that PSI score, boost CURB score, NLR, PCT are independent risk factors for prognosis of elderly CAP patients (P < 0.05). PSI score, boost CURB score, NLR, PCT levels increased and the prognosis of elderly CAP patients was poor.
Table 12
The risk assessment module comprises a model building unit and a risk assessment unit; the model construction unit is used for discarding the PSI score after comparing and analyzing the corresponding prediction result with the real situation of the advanced patient based on the PSI score, the reinforced CURB score, the PCT and NLR death risks of the advanced patient; performing correlation analysis on the reinforced CURB score, the PCT and the NLR, constructing reinforced CURB-PCT combination and reinforced CURB-NLR combination, respectively predicting death risk of the elderly patient, comparing the corresponding prediction result with the real situation of the elderly patient again, and taking the reinforced CURB-PCT combination with highest sensitivity and specificity as a death risk assessment model; the risk assessment unit is used for inputting the assessment index of the death risk into the death risk assessment model to assess the death risk of the elderly patient.
As specific examples, PSI score, enhanced CURB score, PCT and NLR prediction sensitivity were 84.2%, 86.8%, 78.9%, 84.2%, respectively, as described in table 13; the specificity was 80.6%, 59.7%, 81.3% and 61.2%, respectively. Wherein, the sensitivity and specificity of PSI scoring prediction are high, and the prediction result is the highest with the actual consistency (kappa=0.55).
TABLE 13
But PSI scoring is cumbersome and limited in use. The sensitivity of the enhanced CURB score prediction is higher (86.8%), but the specificity (59.7%) and the prediction consistency (kappa=0.32) are not ideal, so that a simpler and effective evidence-based experiment based on the enhanced CURB score is adopted for early and rapid prediction of the aged CAP prognosis. The cut-off values of the selected reinforced CURB-PCT combinations and the reinforced CURB-NLR combinations were predicted based on the about dengue index maximum, and the results showed that the sensitivity of the two combination tests was 81.6% and 63.2%, the specificity was 86.6% and 84.3%, and the Kappa was 0.62 and 0.45, respectively. Wherein the predicted outcome of the enhanced CURB-PCT combination test is consistent with the actual outcome (kappa=0.62) to be a final mortality risk assessment model. See table 14.
TABLE 14
The reinforced CURB-PCT combination is used as a death risk assessment model, and the combined test improves the guidance and the practicability of the reinforced CURB model. Aiming at elderly patients with complex medical history, a scoring system and serum biomarkers can be synthesized, so that the specificity of a prediction model is improved, the accuracy of evaluation prognosis is improved, the occurrence of excessive treatment of a part of patients is reduced, and the method has a certain application value.
As shown in fig. 2, the embodiment further provides a method for evaluating risk of acquired pneumonia death in an elderly community, which includes the following steps:
collecting clinical data and clinical detection indexes of elderly patients suffering from senile community acquired pneumonia, and carrying out reinforced CURB score and PSI score on each of the elderly patients;
cleaning and orderly preprocessing the clinical data and clinical detection indexes;
carrying out statistical analysis on the pretreated clinical data and clinical detection indexes, selecting indexes with statistical significance as independent variables by taking the survival of the elderly patients as dependent variables, and carrying out multi-factor analysis to obtain evaluation indexes of death risk of the elderly patients;
and constructing a death risk assessment model based on the reinforced CURB-PCT combination, and inputting the death risk assessment index into the death risk assessment model to assess the death risk of the elderly patient.
In practice, the statistical analysis of the pre-processed clinical data and clinical test indicators includes: dividing the acquired elderly patients into a survival group and a death group, carrying out normal examination on the pretreated clinical indexes and clinical detection indexes, and carrying out t-test on the average number between the survival group and the death group based on independent samples for indexes meeting normal distribution; for indexes of the non-normal distribution, the median between the survival group and the death group is checked based on the rank sum, and then the statistical result of all indexes is obtained.
In practice, the process of obtaining an assessment of the risk of death of an elderly patient comprises: presetting a statistical threshold, and comparing the statistical results of all indexes with the statistical threshold to obtain indexes with statistical significance; and then taking whether the elderly patient survives or not as a dependent variable, taking an index with statistical significance as an independent variable, and adopting two-class Logistic regression to carry out multi-factor analysis so as to obtain an evaluation index of death risk.
In one embodiment, the process for constructing the death risk assessment model includes: based on PSI score, reinforced CURB score, PCT and NLR, comparing and analyzing the corresponding prediction result with the real situation of the advanced patient, and discarding the PSI score; and further carrying out correlation analysis on the reinforced CURB score, the PCT and the NLR, constructing reinforced CURB-PCT combination and reinforced CURB-NLR combination, respectively predicting death risk of the elderly patient, comparing the corresponding prediction result with the real situation of the elderly patient again, and taking the reinforced CURB-PCT combination with highest sensitivity and specificity as a death risk assessment model.
The present application is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present application are intended to be included in the scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims (9)

1. The evaluation system for the risk of acquired pneumonia death in the senile community is characterized by comprising a data acquisition module, a data preprocessing module, a statistical analysis module and a risk evaluation module which are connected in sequence, wherein:
the data acquisition module is used for acquiring clinical data and clinical detection indexes of elderly patients suffering from senile community acquired pneumonia, and carrying out reinforced CURB scoring and PSI scoring on each of the elderly patients;
the data preprocessing module is used for cleaning and regulating the clinical data and clinical detection indexes;
the statistical analysis module is used for carrying out statistical analysis on the processed clinical data and clinical detection indexes, selecting indexes with statistical significance as independent variables by taking the survival or non-survival of the elderly patients as the dependent variables, and carrying out multi-factor analysis to obtain evaluation indexes of death risk of the elderly patients;
the risk assessment module is used for constructing a death risk assessment model based on the reinforced CURB-PCT combination, and inputting the death risk assessment index into the death risk assessment model to assess the death risk of the elderly patient.
2. The senile community risk of acquired pneumonia death assessment system according to claim 1, wherein,
clinical data for elderly patients include at least: name, gender, age, hospitalization time, whether to stay in the ICU, 28-day afterward, history of illness, history of smoking, history of drinking; wherein the disease history comprises at least: hypertension, chronic obstructive pulmonary disease, congestive heart failure, coronary heart disease, diabetes, cerebral stroke, solid tumors without metastasis, kidney disease, history of surgery, history of trauma;
the clinical detection indexes at least comprise physical examination, assay indexes, blood gas analysis indexes and imaging examination; wherein the physical examination includes: body temperature, heart rate, respiratory rate, blood pressure, and disturbance of consciousness; the assay index comprises: white blood cells, lymphocytes, platelets, red blood cell volume distribution width, hematocrit, hemoglobin, albumin, total cholesterol, triglycerides, procalcitonin, sodium, blood glucose, and urea nitrogen; the blood gas analysis index comprises: PH value, oxygen partial pressure, carbon dioxide partial pressure, blood oxygen saturation and oxygenation index; the imaging examination includes: chest radiographs, chest CT with or without lung nodules, pleural effusion and multiple lobular infiltration.
3. The senile community risk of acquired pneumonia death assessment system according to claim 1, wherein,
the statistical analysis module comprises a statistical unit and an analysis unit; the statistical unit is used for dividing the acquired elderly patients into a survival group and a death group, carrying out normal examination on the clinical indexes and clinical detection indexes after pretreatment, and carrying out t-test on the average number between the survival group and the death group based on independent samples for indexes meeting normal distribution; for indexes of the non-normal distribution, the median between the survival group and the death group is checked based on the rank sum, and then the statistical result of all indexes is obtained.
4. The system for assessing the risk of acquired pneumonecia in an elderly community according to claim 3, wherein,
the analysis unit is used for presetting a statistical threshold value, and comparing the statistical results of all indexes with the statistical threshold value to obtain indexes with statistical significance; furthermore, whether the elderly patient survives or not is taken as a dependent variable, an index with statistical significance is taken as an independent variable, and a two-class Logistic regression is adopted to carry out multi-factor analysis, so as to obtain an evaluation index of death risk;
wherein the statistically significant indicators include: consciousness disturbance, check-in ICU, coronary heart disease, systolic pressure, diastolic pressure, platelet, neutrophil to lymphocyte count ratio, albumin, total cholesterol, procalcitonin, urea nitrogen, PSI score, enhanced CURB score, hypoxia, multiple lobe infiltration, pleural effusion; the evaluation index of the death risk comprises the following steps: diastolic pressure, neutrophil to lymphocyte count ratio, procalcitonin, PSI score, and boost CURB score.
5. The senile community risk of acquired pneumonia death assessment system according to claim 1, wherein,
the risk assessment module comprises a model construction unit and a risk assessment unit;
the model construction unit is used for discarding the PSI score after comparing and analyzing the corresponding prediction result with the real situation of the advanced patient based on the PSI score, the reinforced CURB score, the PCT and NLR death risks of the advanced patient; performing correlation analysis on the reinforced CURB score, the PCT and the NLR, constructing reinforced CURB-PCT combination and reinforced CURB-NLR combination, respectively predicting death risk of the elderly patient, comparing the corresponding prediction result with the real situation of the elderly patient again, and taking the reinforced CURB-PCT combination with highest sensitivity and specificity as a death risk assessment model;
the risk assessment unit is used for inputting the assessment index of the death risk into the death risk assessment model to assess the death risk of the elderly patient.
6. A method of assessing risk of acquired pneumonic death in an elderly community based on the assessment system according to any one of claims 1 to 5, comprising the steps of:
collecting clinical data and clinical detection indexes of elderly patients suffering from senile community acquired pneumonia, and carrying out reinforced CURB score and PSI score on each of the elderly patients;
cleaning and orderly preprocessing the clinical data and clinical detection indexes;
carrying out statistical analysis on the pretreated clinical data and clinical detection indexes, selecting indexes with statistical significance as independent variables by taking the survival of the elderly patients as dependent variables, and carrying out multi-factor analysis to obtain evaluation indexes of death risk of the elderly patients;
and constructing a death risk assessment model based on the reinforced CURB-PCT combination, and inputting the death risk assessment index into the death risk assessment model to assess the death risk of the elderly patient.
7. The method for evaluating risk of acquired pneumonia death in elderly communities as claimed in claim 6, wherein,
the process of statistical analysis of the pre-processed clinical data and clinical test indicators includes: dividing the acquired elderly patients into a survival group and a death group, carrying out normal examination on the pretreated clinical indexes and clinical detection indexes, and carrying out t-test on the average number between the survival group and the death group based on independent samples for indexes meeting normal distribution; for indexes of the non-normal distribution, the median between the survival group and the death group is checked based on the rank sum, and then the statistical result of all indexes is obtained.
8. The method for evaluating risk of acquired pneumonia death in elderly communities as claimed in claim 6, wherein,
the process of obtaining an assessment of mortality risk in an elderly patient includes: presetting a statistical threshold, and comparing the statistical results of all indexes with the statistical threshold to obtain indexes with statistical significance; and then taking whether the elderly patient survives or not as a dependent variable, taking an index with statistical significance as an independent variable, and adopting two-class Logistic regression to carry out multi-factor analysis so as to obtain an evaluation index of death risk.
9. The method for evaluating risk of acquired pneumonia death in elderly communities as claimed in claim 6, wherein,
the construction process of the death risk assessment model comprises the following steps: based on PSI score, reinforced CURB score, PCT and NLR, comparing and analyzing the corresponding prediction result with the real situation of the advanced patient, and discarding the PSI score; and further carrying out correlation analysis on the reinforced CURB score, the PCT and the NLR, constructing reinforced CURB-PCT combination and reinforced CURB-NLR combination, respectively predicting death risk of the elderly patient, comparing the corresponding prediction result with the real situation of the elderly patient again, and taking the reinforced CURB-PCT combination with highest sensitivity and specificity as a death risk assessment model.
CN202310831340.8A 2023-07-07 2023-07-07 Evaluation system and method for senile community acquired pneumonia death risk Pending CN116759094A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310831340.8A CN116759094A (en) 2023-07-07 2023-07-07 Evaluation system and method for senile community acquired pneumonia death risk

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310831340.8A CN116759094A (en) 2023-07-07 2023-07-07 Evaluation system and method for senile community acquired pneumonia death risk

Publications (1)

Publication Number Publication Date
CN116759094A true CN116759094A (en) 2023-09-15

Family

ID=87951338

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310831340.8A Pending CN116759094A (en) 2023-07-07 2023-07-07 Evaluation system and method for senile community acquired pneumonia death risk

Country Status (1)

Country Link
CN (1) CN116759094A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117912704A (en) * 2024-01-18 2024-04-19 中国医学科学院北京协和医院 Method, equipment and system for predicting viral pneumonia

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117912704A (en) * 2024-01-18 2024-04-19 中国医学科学院北京协和医院 Method, equipment and system for predicting viral pneumonia

Similar Documents

Publication Publication Date Title
Cheng et al. Quantitative computed tomography of the coronavirus disease 2019 (COVID-19) pneumonia
Lorente et al. Acute respiratory distress syndrome in patients with and without diffuse alveolar damage: an autopsy study
Lowrie et al. Medical outcomes study short form-36: a consistent and powerful predictor of morbidity and mortality in dialysis patients
CN116759094A (en) Evaluation system and method for senile community acquired pneumonia death risk
Druckmann et al. Presence of sarcopenia before kidney transplantation is associated with poor outcomes
Metwaly et al. ARDS metabolic fingerprints: characterization, benchmarking, and potential mechanistic interpretation
Cheng et al. Chronic kidney disease: prevalence and association with handgrip strength in a cross-sectional study
da Cunha Bandeira et al. Evaluation of the prognostic significance of the malnutrition inflammation score in hemodialysis patients
CN111627559B (en) System for predicting patient mortality risk
Ullah et al. Microalbuminuria in type 2 diabetes mellitus and glycemic control
Xu et al. Correlates of Frailty in Hospitalized Older Adults with Hypertension and Its Influence on Clinical Prognosis
Li et al. Validating a pragmatic definition of shock in adult patients presenting to the ED
Li et al. Development and validation of a routine blood parameters-based model for screening the occurrence of retinal detachment in high myopia in the context of PPPM
Stachon et al. Estimation of the mortality risk of surgical intensive care patients based on routine laboratory parameters
Ryu et al. Should the lower limit of impaired fasting glucose be reduced from 110 mg/dL in Korea?
LU504600B1 (en) Method and system for predicting incidence of metabolic dysfunction-associated fatty liver disease
Li et al. Dynamic changes in lactate levels within the first 24 hours in septic patients as a prognostic indicator: A retrospective cohort study utilizing latent class growth analysis
Zhang et al. U-Shaped Association between Serum Chloride Levels and In-Hospital Mortality in Patients with Congestive Heart Failure in Intensive Care Units A Retrospective Observational Study
Shalaby et al. Neutrophil-To-Lymphocyte Ratio [NLR] as A Promising Prognostic Marker in Critically Ill Septic Patients
Lu et al. Establishment and evaluation of a simplified evaluation system of acute respiratory distress syndrome
RU2782796C1 (en) METHOD FOR ASSESSING THE RISK OF DEVELOPING A SEVERE COURSE OF CoVID-19
El-Alfy et al. Alpha-2-Macroglobulin in Saliva as a Noninvasive Glycemic Control Marker in Type 2 Diabetes Mellitus Patients
CN116959734A (en) Prediction method and system for onset of metabolic-related fatty liver disease
Kumaresan et al. A Tertiary Care Centre Experience of COVID-19-Associated AKI During the First and Second Waves of the Pandemic: TH-PO079
Machado et al. Clinical biomarker-based biological age predicts deaths in Brazilian adults: the ELSA-Brasil study

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination