Objective To investigate the impact of large language models on medical record coding,providing insights for the medical record management industry and professionals to better understand,familiarize with,and utilize large language models.Methods The study compared the time consumption,completion rate,and accuracy rate of coding 93 rare diseases u-sing ICD-10 codes between manual search and multiple large language models,elucidating the influence of large language models on medical record coding.Results In terms of coding time consumption,Model A and Model B required the least time,comple-ting all coding in 8 minutes,which is 90 times faster than manual search.Regarding completion rate,all models except Model C(91.4％)achieved 100％.In terms of accuracy rate,Model A was the highest(87.1％),surpassing manual search coding(84.9％).Model B and Model C had similar accuracy rates,47.3％and 43.5％respectively,while Model D had the lowest(0％).Conclusion There is a significant difference in coding accuracy among different large language models,but the accura-cy of Model A has already surpassed that of manual search coding.This demonstrates the powerful capabilities and potential of large language models in medical record coding.In the future,AI based on large language models may replace much of the manu-al work in disease coding.

Objective Guided by"Medical Record Management Quality Control Indicators(2021 Edition)"(hereafter regarded as Medical Record Quality Indicators),this study aims to evaluate the quality of inpatient hospice medical records at a tertiary hospital in Guangzhou.Methods A total of 1,071 inpatient hospice medical records from the year 2023 in a tertiary gen-eral hospital in Guangzhou were selected for evaluation.The evaluation focused on three aspects:documentation compliance of documentation of critical examinations(including CT/MRI,pathology,and pathogen examinations),the compliance rate of treat-ment behavior records(encompassing antibiotic usage,chemotherapy or radiotherapy or targeted or immunotherapy for malignant tumors,and surgical records),and the incidence of unreasonable duplication within medical record.Results The compliance rate for major examination records ranged from 47.7％to 100.0％,with the lowest compliance rate(47.7％)observed in docu-mentation of pathogen culture analysis.Treatment behavior documentation compliance varied from 49.1％to 100.0％,with the lowest compliance rate of 49.1％observed in the recording of antibiotic usage.Rates of inappropriate duplication ranged from 1.0％to duplication(63.1％),with the highest rate of 63.1％occurring when initial progress notes replicated admission histo-ries without synthesis(63.1％).Conclusion The Medical Record Management Quality Control Indicators serves as an effective tool for evaluating the dimensions of medical record quality and offers a systematic framework for enhancing documentation integri-ty within hospitals.

Objective:To explore the grouping and standard cost of malignant tumors chemotherapy patients under the diagnosis-intervention packet (DIP) system based on the decision tree model, for references for optimizing the detailed grouping scheme of this disease.Methods:The data of the first page of medical records of malignant tumors chemotherapy patients in a tertiary hospital in 2022 were collected. Univariate analysis and multiple linear regression were used to analyze the influencing factors of patients′ hospitalization expenses. The Chi squared automatic interaction detection was used to construct the decision tree model to obtain the case grouping scheme and its standard expenses. The coefficient of variation and chi-square test were used to evaluate the grouping effect.Results:A total of 27 235 patients were included in this study. The number of surgical operations, length of hospital stay, gender, the number of other diagnoses, chemotherapy pathways and targeted therapy were taken as classification nodes and included in the decision tree model. A total of 13 groups were formed. The homogeneity within the groups was good(CV<0.70), and the heterogeneity between the groups was strong( χ2= 9 564.65, P<0.001). Conclusions:Based on the decision tree model, the grouping scheme for chemotherapy cases of malignant tumors was established by comprehensively considering factors such as surgical operations within the group, length of hospital stay, other diagnostic and chemotherapy pathways is relatively reasonable, which could provide references for relevant management departments to optimize the detailed grouping scheme of this disease and formulate relevant payment standards.

Objective To investigate the impact of large language models on medical record coding,providing insights for the medical record management industry and professionals to better understand,familiarize with,and utilize large language models.Methods The study compared the time consumption,completion rate,and accuracy rate of coding 93 rare diseases u-sing ICD-10 codes between manual search and multiple large language models,elucidating the influence of large language models on medical record coding.Results In terms of coding time consumption,Model A and Model B required the least time,comple-ting all coding in 8 minutes,which is 90 times faster than manual search.Regarding completion rate,all models except Model C(91.4％)achieved 100％.In terms of accuracy rate,Model A was the highest(87.1％),surpassing manual search coding(84.9％).Model B and Model C had similar accuracy rates,47.3％and 43.5％respectively,while Model D had the lowest(0％).Conclusion There is a significant difference in coding accuracy among different large language models,but the accura-cy of Model A has already surpassed that of manual search coding.This demonstrates the powerful capabilities and potential of large language models in medical record coding.In the future,AI based on large language models may replace much of the manu-al work in disease coding.

Objective Guided by"Medical Record Management Quality Control Indicators(2021 Edition)"(hereafter regarded as Medical Record Quality Indicators),this study aims to evaluate the quality of inpatient hospice medical records at a tertiary hospital in Guangzhou.Methods A total of 1,071 inpatient hospice medical records from the year 2023 in a tertiary gen-eral hospital in Guangzhou were selected for evaluation.The evaluation focused on three aspects:documentation compliance of documentation of critical examinations(including CT/MRI,pathology,and pathogen examinations),the compliance rate of treat-ment behavior records(encompassing antibiotic usage,chemotherapy or radiotherapy or targeted or immunotherapy for malignant tumors,and surgical records),and the incidence of unreasonable duplication within medical record.Results The compliance rate for major examination records ranged from 47.7％to 100.0％,with the lowest compliance rate(47.7％)observed in docu-mentation of pathogen culture analysis.Treatment behavior documentation compliance varied from 49.1％to 100.0％,with the lowest compliance rate of 49.1％observed in the recording of antibiotic usage.Rates of inappropriate duplication ranged from 1.0％to duplication(63.1％),with the highest rate of 63.1％occurring when initial progress notes replicated admission histo-ries without synthesis(63.1％).Conclusion The Medical Record Management Quality Control Indicators serves as an effective tool for evaluating the dimensions of medical record quality and offers a systematic framework for enhancing documentation integri-ty within hospitals.

Objective:To explore the grouping and standard cost of malignant tumors chemotherapy patients under the diagnosis-intervention packet (DIP) system based on the decision tree model, for references for optimizing the detailed grouping scheme of this disease.Methods:The data of the first page of medical records of malignant tumors chemotherapy patients in a tertiary hospital in 2022 were collected. Univariate analysis and multiple linear regression were used to analyze the influencing factors of patients′ hospitalization expenses. The Chi squared automatic interaction detection was used to construct the decision tree model to obtain the case grouping scheme and its standard expenses. The coefficient of variation and chi-square test were used to evaluate the grouping effect.Results:A total of 27 235 patients were included in this study. The number of surgical operations, length of hospital stay, gender, the number of other diagnoses, chemotherapy pathways and targeted therapy were taken as classification nodes and included in the decision tree model. A total of 13 groups were formed. The homogeneity within the groups was good(CV<0.70), and the heterogeneity between the groups was strong( χ2= 9 564.65, P<0.001). Conclusions:Based on the decision tree model, the grouping scheme for chemotherapy cases of malignant tumors was established by comprehensively considering factors such as surgical operations within the group, length of hospital stay, other diagnostic and chemotherapy pathways is relatively reasonable, which could provide references for relevant management departments to optimize the detailed grouping scheme of this disease and formulate relevant payment standards.