Incidence of Adverse Drug Reactions in HIV/AIDS patients in China: an active monitoring study using leveraging natural language processing and machine learning

Incidence of Adverse Drug Reactions in HIV/AIDS patients in China: an active monitoring study using leveraging natural language processing and machine learning | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Incidence of Adverse Drug Reactions in HIV/AIDS patients in China: an active monitoring study using leveraging natural language processing and machine learning Ji Sun, Juanjuan Huang, Junlong Ma, Hui Qi, Guoqiang Zhou, Shiqiong Huang, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5703681/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract To evaluate the incidence and type with adverse drug reactions (ADRs) among HIV/AIDS patients by Hospital Intelligent Pharmacovigilance System. A retrospective analysis was performed on 3971 HIV/AIDS patients admitted to the First Hospital of Changsha in China, from January 1, 2022 to December 31, 2023. Intelligent Recognition Models with Natural Language Processing Techniques for Intelligent Monitoring Systems was used to detect ADR signals of hospital information system. The causality risk factors for the ADRs of adverse drug reactions were classified using the WHO-UMC system. Our results showed that the prevalence of ADRs was 15.69% in the patients, which mainly was predominated by skin and appendages disorders and gastrointestinal (GI) disorders (2.87% vs. 2.67% ). The most of the reactions were associated with ADR could be explained by the use of antimicrobials and antiretrovirals with by 34.92% and 26.32%, respectively. 75.36% of ADRs had occurrenceed within 14 days of hospitalization. Together, the incidence of adverse reaction ADRs of patients was significantly high during the treatment period. Moreover, the active monitoring of the CHPS system reflected the adverse reaction ADRs of patients with during COVID-19 treatment in the real world, which provided reference for clinical safe medication in clinic. Adverse Drug Reactions AIDS real-world 1 Introduction Adverse drug reactions (ADRs) are one of the leading causes of hospital admissions and morbidity in developed and developing countries, and represent a substantial burden on healthcare delivery systems[ 1 , 2 ]. Characterised by rapid transmission, slow onset and high mortality rate, AIDS is an important public health problem that poses a serious threat to public health[ 3 ]. According to the latest report released by UNAIDS on 22 July 2024, 39.9 million people were living with HIV globally as of 2023, with 1.3 million new infections and 630,000 deaths from AIDS-related illnesses in 2023. Adverse reactions to antiretroviral drugs can significantly affect patients' adherence to medication, [ 4 ] [ 5 ]and although there have been many studies on adverse reactions in AIDS patients[ 6 – 11 ], there are fewer studies on adverse reactions in the Chinese population[ 12 – 16 ]. Proactive monitoring of adverse drug events using triggers or information technology is becoming increasingly popular in pharmacovigilance services.[ 2 , 17 – 20 ]。Natural language processing techniques can be effectively used for drug safety monitoring and pharmacovigilance[ 21 ].[ 22 , 23 ].Based on a deep learning and knowledge graph framework, DKADE can be used to identify ADEs by combining drug order and existing drug knowledge to infer missing drug entities and assess their relevance to ADEs.[ 24 ] [ 25 , 26 ] In recent years, with the continuous progress in the development of anti-HIV drugs, the types and occurrence of adverse drug reactions have changed accordingly, [ 10 ]and at the same time, patients with HIV/AIDS use a wide range of drugs, and it is more common for patients to combine drugs, usually applying a combination of antiviral drugs, antimicrobials, and other symptomatic management drugs. The incidence of adverse drug reactions in HIV/AIDS patients was significantly higher than that in ordinary hospitalized patients.In this study, to investigate the ADRs of the HIV/AIDS patients in the real world, we used Hospital Intelligent Pharmacovigilance System to actively monitor the medication safety of patients with HIV/AIDS, which provide reference for clinical safe medication. 2 Methods 2.1 Study design and population A retrospective study was carried out in this study. Three thousand nine hundred seventy one HIV/AIDS patients admitted to the first Hospital of Changsha, from January 1, 2022 to December 31, 2023, were enrolled. All the diagnosed patients met the diagnostic criteria of the Chinese Guidelines for the Diagnosis and Treatment of AIDS. This study was approved by the Ethics Committee of Changsha First Hospital. All patients were codified and anonymized to protect the confidentiality of individual participants. After data coding and analysis, all records were deleted to further protect participants’ confidentiality. 2.2 Active monitoring All treatments used in the HIV/AIDS patients were selected in the study.Through the intelligent recognition model of adverse events constructed by natural language processing technology, the knowledge graph is introduced to assist in the discrimination, the text in the unstructured cultural electronic medical record is intelligently monitored, and the system output identifies the adverse drug reactions. Afterwards, two clinical pharmacists check the system alarm cases one by one and evaluate the relevance. 2.3 Data collection The characteristics of the HIV/AIDS patients (time of admission, length of stay, sex, age, etc.), history of drug allergies, the Antiviral Protocol and the number of medications used during hospitalization were extracted. ADRs were evaluated after system recognition. And then, the causality, the time of occurrence, suspicious drugs, clinical outcome of ADRs were recorded. 2.4 Case assessment Causality assessment was performed for all suspected ADRs using the World Health Organization-Uppsala Monitoring Centre (WHO-UMC) system. The WHO-UMC system is a universally accepted method for causality assessment. The relationship between the reported ADRs and drugs was categorized as certain, probable, possible, unlikely, conditional/unclassified, or unassessable/unclassifiable. Only cases categorized as certain, probable, and possible were included. Seriousness of the identified suspected ADRs was determined according to the definition of the ICH E2A guideline (ICH E2A Clinical safety data management: definitions and standards for expedited reporting). According to the ICH E2A guideline, a serious adverse event or reaction is any untoward medical occurrence that at any dose: Resulted in death, Is life-threatening, Required hospitalization or resulted in prolongation of existing hospitalization, Resulted in persistent or significant disability/incapacity, Caused congenital anomaly/birth defect or medically important event or reaction that required medical/surgical intervention to prevent serious outcome. The clinical outcome indicators of ADRs generally include death, cured, improvement, recovered with sequelae, no healing and unknown. The clinical cure of ADR was considered when ADR symptoms disappeared or recovery of the abnormal indexes to normal values was observed. 2.5 Data processing and statistical analysis Data was captured into computer using an entry program developed with WPS software package. Data was edited during and after data entry using WPS and Statistical Package for Social Science version 20 (SPSS 20). Both descriptive and analytical analysis was carried out on the data using SPSS. Results were presented as percentages and frequencies as appropriate. 3 Results 3.1 Characteristics of patients Three thousand nine hundred seventy one (3971) patients were included in this study (Table 1). Of the 3971 patients, 739(18.6%) were females while 3232(81.4%) were males. The mean age and Length of stay of the patients with ADRs was 48.84 ± 15.4 years,13.7±11.83 days, respectively. Of the 3971 patients, 1,473 cases of ADR signal data were identified by the intelligent monitoring system, which were reviewed individually by two clinical pharmacists, and a total of 694 data were excluded, of which 383 were duplicates, 86 were considered to be caused by the disease itself and 225 were considered to be false positives. Finally, 622 discharged patients were reviewed and a total of 779 ADRs occurred. The incidence of adverse drug reactions was 15.69%.The mean age and Length of stay of the patients with ADRs was47.88±14.4 years,23.16±17.13 days, respectively. 3.2 Characteristics of ADRs Drug-related adverse reactions, as categorized by the system used, and the onset time were listed in Tables 1 and 2, respectively. Skin and appendages disorders were the most frequent ADRs(2.87%), Gastrointestinal (GI) disorders followed by liver disorders (2.67% ), metabolic and nutrtional disorders (2.64%) and white cell and res disorders(2.57%).There were also higher incidence of damage to the liver and biliary system disorders damage(2.17%) and body as a whole-general disorders(2.17%). Tab 2 Frequency of adverse drug reactions for the HIV/AIDS patients according to the time of onset. ADRs The time interval between drug administration and the onset of ADRs (days) Occurred on admission 1-3 4-7 8-14 >14 skin and appendages disorders 24(3.08 ) 9(1.16) 16(2.05 ) 35(4.49 ) 30(3.85) gastro-intestinal system disorders 23(2.95) 10(1.28 ) 26(3.34) 27(3.47) 20(2.57) metabolic and nutrtional disorders 59(7.57) 1(0.13) 12(1.54) 25(3.21) 8(1.03) white cell and res disorders 14(1.80) 1(0.13 ) 10(1.28) 27(3.47) 50(6.42) liver and biliary system disorders 27(3.47 ) 2(0.26 ) 12(1.54) 23(2.95 ) 22(2.82) body as a whole-general disorders 10(1.28) 11(1.41) 21(2.70) 19(2.44 ) 25(3.21) urinary system disorders 26(3.34 ) 0(0.00 ) 2(0.26) 7(0.90) 16(2.05) palatelet, blooding & clotting disorders 3(0.39 ) 1(0.13) 3(0.39) 13(1.67) 17(2.18) central & peripher nervous system disorders 13(1.67) 2(0.26 ) 5(0.64) 9(1.16 ) 8(1.03) red blood cell disorders 11(1.41) 0(0.00 ) 2(0.26) 6(0.77) 7(0.90) psychiatric disorders 9(1.16) 1(0.13) 3(0.39) 2(0.26) 10(1.28) respiratory system disorders 5(0.64 ) 4(0.51) 2(0.26) 3(0.39 ) 1(0.13) MYO-,ENDO-,pericardial & valve disorders 11(1.41) 0(0.00) 0(0.00 ) 1(0.13) 1(0.13) musculo-skieletal system disorders 1(0.13) 1(0.13) 1(0.13) 1(0.13) 0(0.00) vision abnormal 1(0.13) 0(0.00) 0(0.00) 1(0.13) 1(0.13) endocrine disorders 2(0.26) 0(0.00 ) 0(0.00 ) 0(0.00 ) 0(0.00) Site of application damage 0(0.00) 0(0.00 ) 1(0.13) 0(0.00 ) 0(0.00) Hearing and vestibular impairment 0(0.00) 0(0.00) 0(0.00) 0(0.00) 1(0.13) Total 229(29.40) 43(5.52) 116(14.89 ) 199(25.55) 217(27.86 ) Data are n (%). ADRs are presented as individual symptoms and system organ class, based on the MedDRA classification. Frequency was calculated as number779*100%. ADR, adverse drug reaction; MedDRA, Medical Dictionary for Regulatory Activities. In terms of time of onset of the ADRs, 29.40% (hyperlipoidemia ,CK-MB Elevated,hyperuricemia,liver function injury,renal function impairment,rash,et al.) occurred on admission,20.41% occurred within 7 days of treatment, 75.36% occurred within 14 days of treatment.It is important to note that 27.86% of these ADRs occurred after 14 days of hospitalization. Suspected drugs with ADRs were listed in Table 3.Most adverse drug reactions are related to antimicrobials(34.92%), including amphotericin B, linezolid, cotrimoxazole. Second, antiretrovirals(26.32%) cause more adverse drug reactions, including hyperlipidaemia with lopinavir/ritonavir, anaemia with zidovudine, and elevated creatine kinase with tenofovir. Tab 3 Suspicious Drugs, Casualty Assessment and prognosis of adverse drug reactions for the HIV/AIDS patients Suspicious Drugs ADRs Casualty Assessment prognosis All ADRs SADRs certain Probable Possible cure improvement not quite clear not improvement antibacterials 272(34.92) 33(4.24) 2(0.26 ) 127(16.30 ) 143(18.36) 1(0.13) 223(28.63) 38(4.88) 10(1.28) Antiretroviral drugs 205(26.32 ) 37(4.75) 0(0.00) 83(10.65 ) 122(15.66) 0(0.00) 152(19.51) 45(5.78) 8(1.03) antituberculosis drugs 147(18.87 ) 17(2.18 ) 1(0.13 ) 53(6.80 ) 93(11.94 ) 0(0.00) 102(13.09) 36(4.62) 9(1.16) antitumor drug 62(7.96 ) 24(3.08) 0(0.00 ) 32(4.11) 30(3.85) 0(0.00) 38(4.88) 17(2.18) 7(0.90) antiviral drug 27(3.47 ) 10(1.28) 0(0.00 ) 17(2.18 ) 10(1.28) 0(0.00) 23(2.95 ) 3(0.39) 1(0.13) Other drugs 66(8.47) 1(0.13) 0(0.00) 27(3.47 ) 39(5.01) 0(0.00) 60(7.70 ) 4(0.51) 2(0.26) Total 779(100.00) 122(15.66) 3(0.39) 339(43.52) 437(56.10) 1(0.13) 598(76.77) 143(18.36) 37(4.75) Data are n (%).Frequency was calculated as number/779*100%. ADRs were associated with antituberculosis drugs and antitumor drug with 18.87% and 7.96% respectively. Of these, 15.66% were found to be serious. The causal relationship assessed by using the WHO-UMC system in the suspected adverse drug reactions cases were found to be probable and possible (43.52% vs. 56.10% ). The prognosis of ADRs in these patients were favorable, with 76.77% improved. Systems and drugs involved in ADRs in HIV/AIDS patients hospitalised for ADRs were listed in Table 4. Of these patients, 79 were admitted to hospital due to adverse drug reactions.The main reason was adverse reactions to the antiretroviral drugs used. Tab 4 Systems and drugs involved in ADRs in HIV/AIDS patients hospitalised for ADRs Suspicious Drugs Number of ADR(n%) The system involved(n) Antiretroviral drugs 56(7.19) gastro-intestinal system disorders(16),urinary system disorders(8),body as a whole-general disorders(7),psychiatric disorders(5),metabolic and nutrtional disorders(4),liver and biliary system disorders(4),central & peripher nervous system disorders(4), red blood cell disorders(3),white cell and res disorders(2), endocrine disorders(2),skin and appendages disorders(2),respiratory system disorders(1),palatelet, blooding & clotting disorders(1) antituberculosis drugs 11(1.41) metabolic and nutrtional disorders(2),liver and biliary system disorders(2),astro-intestinal system disorders(2),central & peripher nervous system disorders(2),white cell and res disorders(1),skin and appendages disorders(1),vision abnormal(1) antibacterials 5(0.64) white cell and res disorders(2),skin and appendages disorders(2),body as a whole-general disorders(1),palatelet, blooding & clotting disorders(1) antitumor drug 3(0.39) central & peripher nervous system disorders(2),metabolic and nutrtional disorders(1) Other drugs 1(0.13) urinary system disorders(1) Total 76(9.76) Data are n (%). ADRs are presented as individual symptoms and system organ class, based on the MedDRA classification. Frequency was calculated as number779*100%. ADR, adverse drug reaction; MedDRA, Medical Dictionary for Regulatory Activities. 4 Discussion HIV-positive people are more susceptible to drug reactions than the general population. [ 27 ].There have been a number of studies on the adverse effects of antiretroviral drugs in patients with AIDS, but there have been fewer studies on the occurrence of ADRs in the HIV population as a whole, and there have been even fewer studies on ADRs in the Chinese HIV population. Early studies found that the incidence of ADRs among HIV patients was 32.0%, with the dermatological, hepatic and hematologic systems being the most affected by ADRs[ 28 ]. Our study found that the incidence of ADRs in patients with HIV/AIDS was 15.69%,which is lower than earlier studies.However, our findings are similar to a recent study in southern Ethiopia.[ 10 ]The systems involved in adverse reactions were similar to the earlier study, mainly gastro-intestinal system disorders, skin and appendages disorders and metabolic and nutrtional disorders. It is important to note that we need to focus on the occurrence of pre-hospital ADRs in HIV patients, that is, the occurrence of ADRs while the patient is at home. This is because in our study, 29.4% of ADRs occurred on admission and 76 (9.76%) of these were admitted to hospital for ADRs. This may be related to the overall higher Medication Regimen Complexity Index (MRCI) in HIV patients, which has shown a significant association between higher baseline MRCI scores and hospitalisation for ADRs.[ 29 ]. There are important limitations to this retrospective study. First, while NLP maximizes the extraction of adverse events hidden in clinical documentation, this method still relies on healthcare providers’ ability to accurately record adverse events in medical records. Secondly, using natural semantic recognition, active monitoring may have false-negative results, resulting in some ADRs that may be missed.Thirdly,the RTC cohort consisted of patients from health facilities in Hunan province and may not be representative of patients across China. Furthermore, we only observed adverse reactions during hospitalization. However, lipid abnormalities caused by lopinavir-ritonavir and central nervous system abnormalities caused by long-term efavirenz cannot be fully monitored during hospitalization, especially in initial patients. So further studies with more extended follow-up periods are needed to assess the longer-term implications of AEs and the potential fluidity in predictors of such events. 5 Conclusion There has been a decline in the incidence of ADR among people with HIV/AIDS.We use natural semantic recognition technology to effectively identify adverse drug reactions in AIDS patients, which provides a scientific basis for further effective drug safety assurance for AIDS patients. Declarations Conflict of Interest The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. Funding The research is supported by Natural Science Foundation of Hunan Province (No.2024JJ8202) Author Contribution S.J.conceived, designed this study and wrote the manuscript. M.JL. performed data extraction,H.JJ.,Q.H.and Z.GQ.were responsible for coordinating the study and the acquisition of the data. H.GF. and H.SQ. reviewed the first draft of the manuscript. All authors reviewed the manuscript. Acknowledgement The authors gratefully acknowledge their colleagues for valuable assistance and advice in the course of this work. References Angamo MT, Chalmers L, Curtain CM, Bereznicki LR: Adverse-Drug-Reaction-Related Hospitalisations in Developed and Developing Countries: A Review of Prevalence and Contributing Factors. Drug Saf 2016, 39(9):847-857. Mt M, Ss J, Plgc L, Tghk S: Prevalence, Characteristics and Factors Associated with Adverse Drug Reactions Among Hospitalized Patients. Hosp Pharm 2024, 59(4):489-497. Abdool Karim Q, Mayer KH, Mohan J, Del Rio C: The audacious goal to end AIDS by 2030: aspiration or reality? J Int AIDS Soc 2024, 27(7):e26339. Li H, Marley G, Ma W, Wei C, Lackey M, Ma Q, Renaud F, Vitoria M, Beanland R, Doherty M et al : The Role of ARV Associated Adverse Drug Reactions in Influencing Adherence Among HIV-Infected Individuals: A Systematic Review and Qualitative Meta-Synthesis. AIDS Behav 2017, 21(2):341-351. Li H, Wang Z, Cui WG, Liang Y, Xin TY, Li J: [Study on adherence and interrelated factors of acquired immunedeficiency syndrome patients receiving antiretroviral treatment]. Zhonghua Liu Xing Bing Xue Za Zhi 2005, 26(7):507-510. Darge T, Babusha A, Chilo D, Dukessa A, Teferi S: Predictors of severe hepatotoxicity among retroviral infected adults on HAART regimen in Ilubabor Zone, Southwest Ethiopia. Sci Rep 2024, 14(1):8473. Tanaka H, Satoh M, Takigawa M, Onoda T, Ishii T: Characteristics of adverse event reports among people living with human immunodeficiency virus (HIV) in Japan: Data mining of the Japanese Adverse Drug Event Report database. Drug Discov Ther 2023, 17(3):183-190. Ray S, Seth A, Singh S, Sharma G, Gaur N, Shah Y, Kumar P, Chandra J: Short-Term Adverse Drug Reactions to Antiretroviral Therapy in Children with HIV: A Cohort Study. Indian J Pediatr 2023, 90(1):9-15. Zondi SL, Naidoo P: Reporting and recording of adverse drug reactions of highly active antiretroviral therapy by HIV infected patients and healthcare professionals respectively in the Ethekwini Metropolitan of Kwa-Zulu Natal, South Africa: a cross-sectional and retrospective comparative study. Pan Afr Med J 2022, 42:218. Sherfa A, Haile D, Yihune M, Sako S: Incidence and predictors of Adverse Drug Reaction (ADR) among adult HIV positive patients on anti-retroviral treatment in Arba Minch town public health facilities, southern Ethiopia: A retrospective cohort study, 2020. PLoS One 2021, 16(5):e0251763. Silva AM, Pereira M, Dias CC, Ventura Â, Sousa-Pinto B: Real-world evidence in antiretroviral therapy: drug safety data. Braz J Infect Dis 2020, 24(3):271-272. Zhou XY, Li CX, Zhang JB, Tan JT, Yang X, Albarmaqi RA, Li YY, Kuang YQ: Association of Human Leukocyte Antigen Alleles and Hypersensitivity of Efavirenz/Nevirapine in HIV-Infected Chinese Patients. AIDS Res Hum Retroviruses 2022, 38(12):884-889. Lin YC, Lai YY, Liu HY, Chen YC, Liu LF, Ko NY: [Trends in Immunity and Adverse Drug Reactions Among People Newly Diagnosed With HIV]. Hu Li Za Zhi 2020, 67(1):55-65. Dai L, Liu A, Zhang H, Wu H, Zhang T, Su B, Shao Y, Li J, Ye J, Scott SR et al : Impact of Lopinavir/Ritonavir and Efavirenz-Based Antiretroviral Therapy on the Lipid Profile of Chinese HIV/AIDS Treatment-Naïve Patients in Beijing: A Retrospective Study. Curr HIV Res 2019, 17(5):324-334. Gao SC, Gui XE, Deng LP, Zhang YX, Yan YJ, Rong YP, Liang K, Yang RR: [Nevirapine related hepatotoxicity: the prevalence and risk factors in a cohort of ART naive Han Chinese with AIDS]. Zhonghua Gan Zang Bing Za Zhi 2010, 18(9):689-693. Yuan J, Xu Q, Chen X, Meng P, Li Q, Xu L, Meng X, Jin Y, Guo H: Prevalence of liver injury among patients with acquired immunodeficiency syndrome treated with highly active antiretroviral therapy in China. J Tradit Chin Med 2019, 39(2):275-280. Domingues Í P, Costa MRD: [Update of triggers for detection of adverse drug events in hematologic patients]. Cad Saude Publica 2023, 39(12):e00077923. Sun J, Deng X, Chen X, Huang J, Huang S, Li Y, Feng J, Liu J, He G: Incidence of Adverse Drug Reactions in COVID-19 Patients in China: An Active Monitoring Study by Hospital Pharmacovigilance System. Clin Pharmacol Ther 2020, 108(4):791-797. Wang L, Cai C, Huang L, Shi D, Chen Q, Chen Y, Yu W: Safety profile of methotrexate used off-label in ectopic pregnancy: an active monitoring study based on a Chinese hospital pharmacovigilance system. Curr Med Res Opin 2024, 40(1):35-42. Wu S, Yin Q, Wu L, Wu Y, Yu N, Yan J, Bian Y: Establishing a trigger tool based on global trigger tools to identify adverse drug events in obstetric inpatients in China. BMC Health Serv Res 2024, 24(1):72. Ma J, Chen H, Sun J, Huang J, He G, Yang G: Efficient analysis of drug interactions in liver injury: a retrospective study leveraging natural language processing and machine learning. BMC Med Res Methodol 2024, 24(1):312. Murphy RM, Klopotowska JE, de Keizer NF, Jager KJ, Leopold JH, Dongelmans DA, Abu-Hanna A, Schut MC: Adverse drug event detection using natural language processing: A scoping review of supervised learning methods. PLoS One 2023, 18(1):e0279842. Chen L, Gu Y, Ji X, Sun Z, Li H, Gao Y, Huang Y: Extracting medications and associated adverse drug events using a natural language processing system combining knowledge base and deep learning. J Am Med Inform Assoc 2020, 27(1):56-64. Li F, Liu W, Yu H: Extraction of Information Related to Adverse Drug Events from Electronic Health Record Notes: Design of an End-to-End Model Based on Deep Learning. JMIR Med Inform 2018, 6(4):e12159. Jagannatha A, Liu F, Liu W, Yu H: Overview of the First Natural Language Processing Challenge for Extracting Medication, Indication, and Adverse Drug Events from Electronic Health Record Notes (MADE 1.0). Drug Saf 2019, 42(1):99-111. Feng ZY, Wu XH, Ma JL, Li M, He GF, Cao DS, Yang GP: DKADE: a novel framework based on deep learning and knowledge graph for identifying adverse drug events and related medications. Brief Bioinform 2023, 24(4). Carr A, Cooper DA: Adverse effects of antiretroviral therapy. Lancet 2000, 356(9239):1423-1430. González-Martín G, Yañez CG, González-Contreras L, Labarca J: Adverse drug reactions (ADRs) in patients with HIV infection. A prospective study. Int J Clin Pharmacol Ther 1999, 37(1):34-40. Poojar B, Kamath A, Rao SB, Ullal SD, Ramapuram J, Yadiyal MB, Shenoy AK: A Prospective Study of the Medication Regimen Complexity Index and Hospitalization Due to Adverse Drug Reactions Among People Living with HIV. Medicina (Kaunas) 2024, 60(10). Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-5703681","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":396170299,"identity":"b7840db0-dd3b-4057-9da4-471c04c7bc99","order_by":0,"name":"Ji Sun","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEElEQVRIie2RsWrDMBCGzwic5ZysChTcR7hgMBlE/CBdzgQ0JaVjhlAMBWcpZPXb1CDoZOiaUWOHDoYuGQqtnA6dbK+B6hukG/6PO+kAPJ4rhVhJAOGqlhTOhDB2XNES0ClBtdM380OoabyPBkB3CWyMoje8lUPhuNrWD5aXq5dJZN6jUmBiEAj26q53qNM9E7NcP4upXs7LEFMT1RZe9bboU+SGKD/LNQpMaVGiU6ZMQWF6lbhyStflouSlxOQJSQ4pcPpVVk5JbN0QkhhRqPm4KIwG06DYMUrjPpkH3hIfNunizI/Z5Ngkn1/0nc2Oxth2r/oHAwi7xeUuEP6tg/vjHcK6I+uKdjjo8Xg8/5Ufm2hSdLXORh0AAAAASUVORK5CYII=","orcid":"","institution":"The first hospital of Changsha","correspondingAuthor":true,"prefix":"","firstName":"Ji","middleName":"","lastName":"Sun","suffix":""},{"id":396170300,"identity":"64921f3e-c011-4625-9da0-815e7d5ba346","order_by":1,"name":"Juanjuan Huang","email":"","orcid":"","institution":"The first hospital of Changsha","correspondingAuthor":false,"prefix":"","firstName":"Juanjuan","middleName":"","lastName":"Huang","suffix":""},{"id":396170301,"identity":"9fb5e971-94ad-47c9-8573-5d76fd1eb873","order_by":2,"name":"Junlong Ma","email":"","orcid":"","institution":"Third Xiangya Hospital, Central South University","correspondingAuthor":false,"prefix":"","firstName":"Junlong","middleName":"","lastName":"Ma","suffix":""},{"id":396170302,"identity":"c27ddce1-335b-4683-9214-2c328728bf0e","order_by":3,"name":"Hui Qi","email":"","orcid":"","institution":"The first hospital of Changsha","correspondingAuthor":false,"prefix":"","firstName":"Hui","middleName":"","lastName":"Qi","suffix":""},{"id":396170303,"identity":"9f98ef9d-0f6b-4db6-b1f9-179dc54435ac","order_by":4,"name":"Guoqiang Zhou","email":"","orcid":"","institution":"The first hospital of Changsha","correspondingAuthor":false,"prefix":"","firstName":"Guoqiang","middleName":"","lastName":"Zhou","suffix":""},{"id":396170304,"identity":"e22518b4-fbd9-4e64-91c5-5a38f48e9971","order_by":5,"name":"Shiqiong Huang","email":"","orcid":"","institution":"The first hospital of Changsha","correspondingAuthor":false,"prefix":"","firstName":"Shiqiong","middleName":"","lastName":"Huang","suffix":""},{"id":396170305,"identity":"2204e58f-b9fd-41a9-bfaa-a02a5c26fd3e","order_by":6,"name":"Gefei He","email":"","orcid":"","institution":"The first hospital of Changsha","correspondingAuthor":false,"prefix":"","firstName":"Gefei","middleName":"","lastName":"He","suffix":""}],"badges":[],"createdAt":"2024-12-24 05:53:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5703681/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5703681/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":73095573,"identity":"fdd23131-016c-4b66-9538-41eb56761e1f","added_by":"auto","created_at":"2025-01-06 16:25:27","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":584612,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5703681/v1/f1169eac-9f89-4eab-9dc5-df4a6b684342.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Incidence of Adverse Drug Reactions in HIV/AIDS patients in China: an active monitoring study using leveraging natural language processing and machine learning","fulltext":[{"header":"1 Introduction","content":"\u003cp\u003eAdverse drug reactions (ADRs) are one of the leading causes of hospital admissions and morbidity in developed and developing countries, and represent a substantial burden on healthcare delivery systems[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. Characterised by rapid transmission, slow onset and high mortality rate, AIDS is an important public health problem that poses a serious threat to public health[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. According to the latest report released by UNAIDS on 22 July 2024, 39.9\u0026nbsp;million people were living with HIV globally as of 2023, with 1.3\u0026nbsp;million new infections and 630,000 deaths from AIDS-related illnesses in 2023. Adverse reactions to antiretroviral drugs can significantly affect patients' adherence to medication, [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e] [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]and although there have been many studies on adverse reactions in AIDS patients[\u003cspan additionalcitationids=\"CR7 CR8 CR9 CR10\" citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e], there are fewer studies on adverse reactions in the Chinese population[\u003cspan additionalcitationids=\"CR13 CR14 CR15\" citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eProactive monitoring of adverse drug events using triggers or information technology is becoming increasingly popular in pharmacovigilance services.[\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan additionalcitationids=\"CR18 CR19\" citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]。Natural language processing techniques can be effectively used for drug safety monitoring and pharmacovigilance[\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e].[\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e].Based on a deep learning and knowledge graph framework, DKADE can be used to identify ADEs by combining drug order and existing drug knowledge to infer missing drug entities and assess their relevance to ADEs.[\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e] [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e, \u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]\u003c/p\u003e \u003cp\u003eIn recent years, with the continuous progress in the development of anti-HIV drugs, the types and occurrence of adverse drug reactions have changed accordingly, [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]and at the same time, patients with HIV/AIDS use a wide range of drugs, and it is more common for patients to combine drugs, usually applying a combination of antiviral drugs, antimicrobials, and other symptomatic management drugs. The incidence of adverse drug reactions in HIV/AIDS patients was significantly higher than that in ordinary hospitalized patients.In this study, to investigate the ADRs of the HIV/AIDS patients in the real world, we used Hospital Intelligent Pharmacovigilance System to actively monitor the medication safety of patients with HIV/AIDS, which provide reference for clinical safe medication.\u003c/p\u003e"},{"header":"2 Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e2.1 Study design and population\u003c/h2\u003e \u003cp\u003eA retrospective study was carried out in this study. Three thousand nine hundred seventy one HIV/AIDS patients admitted to the first Hospital of Changsha, from January 1, 2022 to December 31, 2023, were enrolled. All the diagnosed patients met the diagnostic criteria of the Chinese Guidelines for the Diagnosis and Treatment of AIDS. This study was approved by the Ethics Committee of Changsha First Hospital. All patients were codified and anonymized to protect the confidentiality of individual participants. After data coding and analysis, all records were deleted to further protect participants\u0026rsquo; confidentiality.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e2.2 Active monitoring\u003c/h2\u003e \u003cp\u003eAll treatments used in the HIV/AIDS patients were selected in the study.Through the intelligent recognition model of adverse events constructed by natural language processing technology, the knowledge graph is introduced to assist in the discrimination, the text in the unstructured cultural electronic medical record is intelligently monitored, and the system output identifies the adverse drug reactions. Afterwards, two clinical pharmacists check the system alarm cases one by one and evaluate the relevance.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e2.3 Data collection\u003c/h2\u003e \u003cp\u003eThe characteristics of the HIV/AIDS patients (time of admission, length of stay, sex, age, etc.), history of drug allergies, the Antiviral Protocol and the number of medications used during hospitalization were extracted. ADRs were evaluated after system recognition. And then, the causality, the time of occurrence, suspicious drugs, clinical outcome of ADRs were recorded.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e2.4 Case assessment\u003c/h2\u003e \u003cp\u003eCausality assessment was performed for all suspected ADRs using the World Health Organization-Uppsala Monitoring Centre (WHO-UMC) system. The WHO-UMC system is a universally accepted method for causality assessment.\u003c/p\u003e \u003cp\u003eThe relationship between the reported ADRs and drugs was categorized as certain, probable, possible, unlikely, conditional/unclassified, or unassessable/unclassifiable. Only cases categorized as certain, probable, and possible were included.\u003c/p\u003e \u003cp\u003e Seriousness of the identified suspected ADRs was determined according to the definition of the ICH E2A guideline (ICH E2A Clinical safety data management: definitions and standards for expedited reporting). According to the ICH E2A guideline, a serious adverse event or reaction is any untoward medical occurrence that at any dose:\u003c/p\u003e \u003cp\u003eResulted in death,\u003c/p\u003e \u003cp\u003eIs life-threatening,\u003c/p\u003e \u003cp\u003eRequired hospitalization or resulted in prolongation of existing hospitalization,\u003c/p\u003e \u003cp\u003eResulted in persistent or significant disability/incapacity,\u003c/p\u003e \u003cp\u003eCaused congenital anomaly/birth defect or medically important event or reaction that required medical/surgical intervention to prevent serious outcome.\u003c/p\u003e \u003cp\u003eThe clinical outcome indicators of ADRs generally include death, cured, improvement, recovered with sequelae, no healing and unknown. The clinical cure of ADR was considered when ADR symptoms disappeared or recovery of the abnormal indexes to normal values was observed.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003e2.5 Data processing and statistical analysis\u003c/h2\u003e \u003cp\u003eData was captured into computer using an entry program developed with WPS software package. Data was edited during and after data entry using WPS and Statistical Package for Social Science version 20 (SPSS 20). Both descriptive and analytical analysis was carried out on the data using SPSS. Results were presented as percentages and frequencies as appropriate.\u003c/p\u003e \u003c/div\u003e"},{"header":"3 Results","content":"\u003cp\u003e\u003cstrong\u003e3.1 Characteristics of patients\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThree thousand nine hundred seventy one (3971) patients were included in this study (Table 1). Of the 3971 patients, 739(18.6%) were females while 3232(81.4%) were males. The mean age and Length of stay of the patients with ADRs was 48.84 \u0026plusmn; 15.4 years,13.7\u0026plusmn;11.83 days, respectively.\u0026nbsp;Of the 3971 patients, 1,473 cases of ADR signal data were identified by the intelligent monitoring system, which were reviewed individually by two clinical pharmacists, and a total of 694 data were excluded, of which 383 were duplicates, 86 were considered to be caused by the disease itself and 225 were considered to be false positives. Finally, 622 discharged patients were reviewed and a total of 779 ADRs occurred. The incidence of adverse drug reactions was 15.69%.The mean age and Length of stay of the patients with ADRs was47.88\u0026plusmn;14.4 years,23.16\u0026plusmn;17.13 days, respectively.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.2 Characteristics of ADRs\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eDrug-related adverse reactions, as categorized by the system used, and the onset time were listed in Tables 1 and 2, respectively. Skin and appendages disorders were the most frequent ADRs(2.87%), Gastrointestinal (GI) disorders followed by liver disorders (2.67% ), metabolic and nutrtional disorders (2.64%) and white cell and res disorders(2.57%).There were also higher incidence of damage to the liver and biliary system disorders damage(2.17%) and body as a whole-general disorders(2.17%).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTab 2 Frequency of adverse drug reactions for the HIV/AIDS patients according to the time of onset.\u003c/strong\u003e\u003c/p\u003e\n\u003cdiv align=\"\"\u003e\n \u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" width=\"661\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eADRs\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"5\" style=\"width: 469px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eThe time interval between drug administration and the onset of ADRs (days)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 109px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eOccurred on admission\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e1-3\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 93px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e4-7\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e8-14\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 94px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026gt;14\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003eskin and appendages disorders\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e24(3.08 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e9(1.16)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e16(2.05 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e35(4.49 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e30(3.85)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003egastro-intestinal system disorders\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e23(2.95)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e10(1.28 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e26(3.34)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e27(3.47)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e20(2.57)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003emetabolic and nutrtional disorders\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e59(7.57)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e12(1.54)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e25(3.21)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e8(1.03)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003ewhite cell and res disorders\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e14(1.80)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e1(0.13 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e10(1.28)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e27(3.47)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e50(6.42)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003eliver and biliary system disorders\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e27(3.47 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e2(0.26 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e12(1.54)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e23(2.95 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e22(2.82)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003ebody as a whole-general disorders\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e10(1.28)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e11(1.41)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e21(2.70)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e19(2.44 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e25(3.21)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003eurinary system disorders\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e26(3.34 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e0(0.00 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e2(0.26)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e7(0.90)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e16(2.05)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003epalatelet, blooding \u0026amp; clotting disorders\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e3(0.39 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e3(0.39)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e13(1.67)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e17(2.18)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003ecentral \u0026amp; peripher nervous system disorders\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e13(1.67)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e2(0.26 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e5(0.64)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e9(1.16 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e8(1.03)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003ered blood cell disorders\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e11(1.41)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e0(0.00 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e2(0.26)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e6(0.77)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e7(0.90)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003epsychiatric disorders\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e9(1.16)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e3(0.39)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e2(0.26)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e10(1.28)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003erespiratory system disorders\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e5(0.64 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e4(0.51)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e2(0.26)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e3(0.39 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003eMYO-,ENDO-,pericardial \u0026amp; valve disorders\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e11(1.41)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e0(0.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e0(0.00 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003emusculo-skieletal system disorders\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0(0.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003evision abnormal\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e0(0.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e0(0.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003eendocrine disorders\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e2(0.26)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e0(0.00 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e0(0.00 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0(0.00 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0(0.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003eSite of application damage\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e0(0.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e0(0.00 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0(0.00 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0(0.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003eHearing and vestibular impairment\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e0(0.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e0(0.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e0(0.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0(0.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eTotal\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 109px;\"\u003e\n \u003cp\u003e229(29.40)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 77px;\"\u003e\n \u003cp\u003e43(5.52)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 93px;\"\u003e\n \u003cp\u003e116(14.89 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e199(25.55)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e217(27.86 )\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eData are n (%).\u003c/p\u003e\n\u003cp\u003eADRs are presented as individual symptoms and system organ class, based on the MedDRA classification. Frequency was calculated as number779*100%.\u003c/p\u003e\n\u003cp\u003eADR, adverse drug reaction; MedDRA, Medical Dictionary for Regulatory Activities.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eIn terms of time of onset of the ADRs, 29.40% (hyperlipoidemia ,CK-MB Elevated,hyperuricemia,liver function injury,renal function impairment,rash,et al.) occurred on admission,20.41% occurred within 7 days of treatment, 75.36% occurred within 14 days of treatment.It is important to note that 27.86% of these ADRs occurred after 14 days of hospitalization.\u003c/p\u003e\n\u003cp\u003eSuspected drugs with ADRs were listed in Table 3.Most adverse drug reactions are related to antimicrobials(34.92%), including amphotericin B, linezolid, cotrimoxazole. Second, antiretrovirals(26.32%) cause more adverse drug reactions, including hyperlipidaemia with lopinavir/ritonavir, anaemia with zidovudine, and elevated creatine kinase with tenofovir.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTab 3 Suspicious Drugs, Casualty Assessment and prognosis of adverse drug reactions for the HIV/AIDS patients\u003c/strong\u003e\u003c/p\u003e\n\u003cdiv align=\"center\"\u003e\n \u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" width=\"788\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" style=\"width: 128px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSuspicious Drugs\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 155px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eADRs\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"3\" style=\"width: 209px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eCasualty Assessment\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"4\" style=\"width: 297px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eprognosis\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eAll ADRs\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSADRs\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ecertain\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 76px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eProbable\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePossible\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ecure\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eimprovement\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e\u003cstrong\u003enot quite clear\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u003cstrong\u003enot improvement\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 128px;\"\u003e\n \u003cp\u003eantibacterials\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e272(34.92)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e33(4.24)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003e2(0.26 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 76px;\"\u003e\n \u003cp\u003e127(16.30 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e143(18.36)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e223(28.63)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e38(4.88)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e10(1.28)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 128px;\"\u003e\n \u003cp\u003eAntiretroviral drugs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e205(26.32 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e37(4.75)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003e0(0.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 76px;\"\u003e\n \u003cp\u003e83(10.65 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e122(15.66)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e0(0.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e152(19.51)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e45(5.78)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e8(1.03)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 128px;\"\u003e\n \u003cp\u003eantituberculosis drugs\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e147(18.87 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e17(2.18 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003e1(0.13 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 76px;\"\u003e\n \u003cp\u003e53(6.80 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e93(11.94 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e0(0.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e102(13.09)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e36(4.62)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e9(1.16)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 128px;\"\u003e\n \u003cp\u003eantitumor drug\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e62(7.96 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e24(3.08)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003e0(0.00 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 76px;\"\u003e\n \u003cp\u003e32(4.11)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e30(3.85)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e0(0.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e38(4.88)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e17(2.18)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e7(0.90)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 128px;\"\u003e\n \u003cp\u003eantiviral drug\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e27(3.47 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e10(1.28)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003e0(0.00 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 76px;\"\u003e\n \u003cp\u003e17(2.18 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e10(1.28)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e0(0.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e23(2.95 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e3(0.39)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 128px;\"\u003e\n \u003cp\u003eOther drugs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e66(8.47)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003e0(0.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 76px;\"\u003e\n \u003cp\u003e27(3.47 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e39(5.01)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e0(0.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e60(7.70 )\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e4(0.51)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e2(0.26)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 128px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eTotal\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 80px;\"\u003e\n \u003cp\u003e779(100.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e122(15.66)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003e3(0.39)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 76px;\"\u003e\n \u003cp\u003e339(43.52)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e437(56.10)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56px;\"\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e598(76.77)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 74px;\"\u003e\n \u003cp\u003e143(18.36)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e37(4.75)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eData are n (%).Frequency was calculated as number/779*100%.\u003c/p\u003e\n\u003cp\u003eADRs were associated with antituberculosis drugs and antitumor drug with 18.87% and 7.96% respectively. Of these, 15.66% were found to be serious. The causal relationship assessed by using the WHO-UMC system in the suspected adverse drug reactions cases were found to be probable and possible (43.52% vs. 56.10% ). The prognosis of ADRs in these patients were favorable, with 76.77% improved.\u003c/p\u003e\n\u003cp\u003eSystems and drugs involved in ADRs in HIV/AIDS patients hospitalised for ADRs were listed in Table 4. Of these patients, 79 were admitted to hospital due to adverse drug reactions.The main reason was adverse reactions to the antiretroviral drugs used.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTab 4\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eSystems and drugs involved in ADRs in HIV/AIDS patients hospitalised for ADRs\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" width=\"622\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 150px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSuspicious Drugs\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eNumber of ADR(n%)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 400px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eThe system involved(n)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eAntiretroviral drugs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e56(7.19)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003egastro-intestinal system disorders(16),urinary system disorders(8),body as a whole-general disorders(7),psychiatric disorders(5),metabolic and nutrtional disorders(4),liver and biliary system disorders(4),central \u0026amp; peripher nervous system disorders(4), red blood cell disorders(3),white cell and res disorders(2), endocrine disorders(2),skin and appendages disorders(2),respiratory system disorders(1),palatelet, blooding \u0026amp; clotting disorders(1)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eantituberculosis drugs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e11(1.41)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003emetabolic and nutrtional disorders(2),liver and biliary system disorders(2),astro-intestinal system disorders(2),central \u0026amp; peripher nervous system disorders(2),white cell and res disorders(1),skin and appendages disorders(1),vision abnormal(1)\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eantibacterials\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e5(0.64)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003ewhite cell and res disorders(2),skin and appendages disorders(2),body as a whole-general disorders(1),palatelet, blooding \u0026amp; clotting disorders(1)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eantitumor drug\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e3(0.39)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003ecentral \u0026amp; peripher nervous system disorders(2),metabolic and nutrtional disorders(1)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eOther drugs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e1(0.13)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003eurinary system disorders(1)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eTotal\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e76(9.76)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eData are n (%).\u003c/p\u003e\n\u003cp\u003eADRs are presented as individual symptoms and system organ class, based on the MedDRA classification. Frequency was calculated as number779*100%.\u003c/p\u003e\n\u003cp\u003eADR, adverse drug reaction; MedDRA, Medical Dictionary for Regulatory Activities.\u003c/p\u003e"},{"header":"4 Discussion","content":"\u003cp\u003eHIV-positive people are more susceptible to drug reactions than the general population. [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e].There have been a number of studies on the adverse effects of antiretroviral drugs in patients with AIDS, but there have been fewer studies on the occurrence of ADRs in the HIV population as a whole, and there have been even fewer studies on ADRs in the Chinese HIV population.\u003c/p\u003e \u003cp\u003eEarly studies found that the incidence of ADRs among HIV patients was 32.0%, with the dermatological, hepatic and hematologic systems being the most affected by ADRs[\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eOur study found that the incidence of ADRs in patients with HIV/AIDS was 15.69%,which is lower than earlier studies.However, our findings are similar to a recent study in southern Ethiopia.[\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]The systems involved in adverse reactions were similar to the earlier study, mainly gastro-intestinal system disorders, skin and appendages disorders and metabolic and nutrtional disorders.\u003c/p\u003e \u003cp\u003eIt is important to note that we need to focus on the occurrence of pre-hospital ADRs in HIV patients, that is, the occurrence of ADRs while the patient is at home. This is because in our study, 29.4% of ADRs occurred on admission and 76 (9.76%) of these were admitted to hospital for ADRs. This may be related to the overall higher Medication Regimen Complexity Index (MRCI) in HIV patients, which has shown a significant association between higher baseline MRCI scores and hospitalisation for ADRs.[\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThere are important limitations to this retrospective study. First, while NLP maximizes the extraction of adverse events hidden in clinical documentation, this method still relies on healthcare providers\u0026rsquo; ability to accurately record adverse events in medical records. Secondly, using natural semantic recognition, active monitoring may have false-negative results, resulting in some ADRs that may be missed.Thirdly,the RTC cohort consisted of patients from health facilities in Hunan province and may not be representative of patients across China. Furthermore, we only observed adverse reactions during hospitalization. However, lipid abnormalities caused by lopinavir-ritonavir and central nervous system abnormalities caused by long-term efavirenz cannot be fully monitored during hospitalization, especially in initial patients. So further studies with more extended follow-up periods are needed to assess the longer-term implications of AEs and the potential fluidity in predictors of such events.\u003c/p\u003e"},{"header":"5 Conclusion","content":"\u003cp\u003eThere has been a decline in the incidence of ADR among people with HIV/AIDS.We use natural semantic recognition technology to effectively identify adverse drug reactions in AIDS patients, which provides a scientific basis for further effective drug safety assurance for AIDS patients.\u003c/p\u003e"},{"header":"Declarations","content":"\u003ch2\u003eConflict of Interest\u003c/h2\u003e\n\u003cp\u003eThe authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.\u003c/p\u003e\n\u003ch2\u003eFunding\u003c/h2\u003e\n\u003cp\u003eThe research is supported by Natural Science Foundation of Hunan Province (No.2024JJ8202)\u003c/p\u003e\n\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\n\u003cp\u003eS.J.conceived, designed this study and wrote the manuscript. M.JL. performed data extraction,H.JJ.,Q.H.and Z.GQ.were responsible for coordinating the study and the acquisition of the data. H.GF. and H.SQ. reviewed the first draft of the manuscript. All authors reviewed the manuscript.\u003c/p\u003e\n\u003ch2\u003eAcknowledgement\u003c/h2\u003e\n\u003cp\u003eThe authors gratefully acknowledge their colleagues for valuable assistance and advice in the course of this work.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eAngamo MT, Chalmers L, Curtain CM, Bereznicki LR: Adverse-Drug-Reaction-Related Hospitalisations in Developed and Developing Countries: A Review of Prevalence and Contributing Factors. \u003cem\u003eDrug Saf \u003c/em\u003e2016, 39(9):847-857.\u003c/li\u003e\n\u003cli\u003eMt M, Ss J, Plgc L, Tghk S: Prevalence, Characteristics and Factors Associated with Adverse Drug Reactions Among Hospitalized Patients. \u003cem\u003eHosp Pharm \u003c/em\u003e2024, 59(4):489-497.\u003c/li\u003e\n\u003cli\u003eAbdool Karim Q, Mayer KH, Mohan J, Del Rio C: The audacious goal to end AIDS by 2030: aspiration or reality? \u003cem\u003eJ Int AIDS Soc \u003c/em\u003e2024, 27(7):e26339.\u003c/li\u003e\n\u003cli\u003eLi H, Marley G, Ma W, Wei C, Lackey M, Ma Q, Renaud F, Vitoria M, Beanland R, Doherty M\u003cem\u003e et al\u003c/em\u003e: The Role of ARV Associated Adverse Drug Reactions in Influencing Adherence Among HIV-Infected Individuals: A Systematic Review and Qualitative Meta-Synthesis. \u003cem\u003eAIDS Behav \u003c/em\u003e2017, 21(2):341-351.\u003c/li\u003e\n\u003cli\u003eLi H, Wang Z, Cui WG, Liang Y, Xin TY, Li J: [Study on adherence and interrelated factors of acquired immunedeficiency syndrome patients receiving antiretroviral treatment]. \u003cem\u003eZhonghua Liu Xing Bing Xue Za Zhi \u003c/em\u003e2005, 26(7):507-510.\u003c/li\u003e\n\u003cli\u003eDarge T, Babusha A, Chilo D, Dukessa A, Teferi S: Predictors of severe hepatotoxicity among retroviral infected adults on HAART regimen in Ilubabor Zone, Southwest Ethiopia. \u003cem\u003eSci Rep \u003c/em\u003e2024, 14(1):8473.\u003c/li\u003e\n\u003cli\u003eTanaka H, Satoh M, Takigawa M, Onoda T, Ishii T: Characteristics of adverse event reports among people living with human immunodeficiency virus (HIV) in Japan: Data mining of the Japanese Adverse Drug Event Report database. \u003cem\u003eDrug Discov Ther \u003c/em\u003e2023, 17(3):183-190.\u003c/li\u003e\n\u003cli\u003eRay S, Seth A, Singh S, Sharma G, Gaur N, Shah Y, Kumar P, Chandra J: Short-Term Adverse Drug Reactions to Antiretroviral Therapy in Children with HIV: A Cohort Study. \u003cem\u003eIndian J Pediatr \u003c/em\u003e2023, 90(1):9-15.\u003c/li\u003e\n\u003cli\u003eZondi SL, Naidoo P: Reporting and recording of adverse drug reactions of highly active antiretroviral therapy by HIV infected patients and healthcare professionals respectively in the Ethekwini Metropolitan of Kwa-Zulu Natal, South Africa: a cross-sectional and retrospective comparative study. \u003cem\u003ePan Afr Med J \u003c/em\u003e2022, 42:218.\u003c/li\u003e\n\u003cli\u003eSherfa A, Haile D, Yihune M, Sako S: Incidence and predictors of Adverse Drug Reaction (ADR) among adult HIV positive patients on anti-retroviral treatment in Arba Minch town public health facilities, southern Ethiopia: A retrospective cohort study, 2020. \u003cem\u003ePLoS One \u003c/em\u003e2021, 16(5):e0251763.\u003c/li\u003e\n\u003cli\u003eSilva AM, Pereira M, Dias CC, Ventura \u0026Acirc;, Sousa-Pinto B: Real-world evidence in antiretroviral therapy: drug safety data. \u003cem\u003eBraz J Infect Dis \u003c/em\u003e2020, 24(3):271-272.\u003c/li\u003e\n\u003cli\u003eZhou XY, Li CX, Zhang JB, Tan JT, Yang X, Albarmaqi RA, Li YY, Kuang YQ: Association of Human Leukocyte Antigen Alleles and Hypersensitivity of Efavirenz/Nevirapine in HIV-Infected Chinese Patients. \u003cem\u003eAIDS Res Hum Retroviruses \u003c/em\u003e2022, 38(12):884-889.\u003c/li\u003e\n\u003cli\u003eLin YC, Lai YY, Liu HY, Chen YC, Liu LF, Ko NY: [Trends in Immunity and Adverse Drug Reactions Among People Newly Diagnosed With HIV]. \u003cem\u003eHu Li Za Zhi \u003c/em\u003e2020, 67(1):55-65.\u003c/li\u003e\n\u003cli\u003eDai L, Liu A, Zhang H, Wu H, Zhang T, Su B, Shao Y, Li J, Ye J, Scott SR\u003cem\u003e et al\u003c/em\u003e: Impact of Lopinavir/Ritonavir and Efavirenz-Based Antiretroviral Therapy on the Lipid Profile of Chinese HIV/AIDS Treatment-Na\u0026iuml;ve Patients in Beijing: A Retrospective Study. \u003cem\u003eCurr HIV Res \u003c/em\u003e2019, 17(5):324-334.\u003c/li\u003e\n\u003cli\u003eGao SC, Gui XE, Deng LP, Zhang YX, Yan YJ, Rong YP, Liang K, Yang RR: [Nevirapine related hepatotoxicity: the prevalence and risk factors in a cohort of ART naive Han Chinese with AIDS]. \u003cem\u003eZhonghua Gan Zang Bing Za Zhi \u003c/em\u003e2010, 18(9):689-693.\u003c/li\u003e\n\u003cli\u003eYuan J, Xu Q, Chen X, Meng P, Li Q, Xu L, Meng X, Jin Y, Guo H: Prevalence of liver injury among patients with acquired immunodeficiency syndrome treated with highly active antiretroviral therapy in China. \u003cem\u003eJ Tradit Chin Med \u003c/em\u003e2019, 39(2):275-280.\u003c/li\u003e\n\u003cli\u003eDomingues \u0026Iacute; P, Costa MRD: [Update of triggers for detection of adverse drug events in hematologic patients]. \u003cem\u003eCad Saude Publica \u003c/em\u003e2023, 39(12):e00077923.\u003c/li\u003e\n\u003cli\u003eSun J, Deng X, Chen X, Huang J, Huang S, Li Y, Feng J, Liu J, He G: Incidence of Adverse Drug Reactions in COVID-19 Patients in China: An Active Monitoring Study by Hospital Pharmacovigilance System. \u003cem\u003eClin Pharmacol Ther \u003c/em\u003e2020, 108(4):791-797.\u003c/li\u003e\n\u003cli\u003eWang L, Cai C, Huang L, Shi D, Chen Q, Chen Y, Yu W: Safety profile of methotrexate used off-label in ectopic pregnancy: an active monitoring study based on a Chinese hospital pharmacovigilance system. \u003cem\u003eCurr Med Res Opin \u003c/em\u003e2024, 40(1):35-42.\u003c/li\u003e\n\u003cli\u003eWu S, Yin Q, Wu L, Wu Y, Yu N, Yan J, Bian Y: Establishing a trigger tool based on global trigger tools to identify adverse drug events in obstetric inpatients in China. \u003cem\u003eBMC Health Serv Res \u003c/em\u003e2024, 24(1):72.\u003c/li\u003e\n\u003cli\u003eMa J, Chen H, Sun J, Huang J, He G, Yang G: Efficient analysis of drug interactions in liver injury: a retrospective study leveraging natural language processing and machine learning. \u003cem\u003eBMC Med Res Methodol \u003c/em\u003e2024, 24(1):312.\u003c/li\u003e\n\u003cli\u003eMurphy RM, Klopotowska JE, de Keizer NF, Jager KJ, Leopold JH, Dongelmans DA, Abu-Hanna A, Schut MC: Adverse drug event detection using natural language processing: A scoping review of supervised learning methods. \u003cem\u003ePLoS One \u003c/em\u003e2023, 18(1):e0279842.\u003c/li\u003e\n\u003cli\u003eChen L, Gu Y, Ji X, Sun Z, Li H, Gao Y, Huang Y: Extracting medications and associated adverse drug events using a natural language processing system combining knowledge base and deep learning. \u003cem\u003eJ Am Med Inform Assoc \u003c/em\u003e2020, 27(1):56-64.\u003c/li\u003e\n\u003cli\u003eLi F, Liu W, Yu H: Extraction of Information Related to Adverse Drug Events from Electronic Health Record Notes: Design of an End-to-End Model Based on Deep Learning. \u003cem\u003eJMIR Med Inform \u003c/em\u003e2018, 6(4):e12159.\u003c/li\u003e\n\u003cli\u003eJagannatha A, Liu F, Liu W, Yu H: Overview of the First Natural Language Processing Challenge for Extracting Medication, Indication, and Adverse Drug Events from Electronic Health Record Notes (MADE 1.0). \u003cem\u003eDrug Saf \u003c/em\u003e2019, 42(1):99-111.\u003c/li\u003e\n\u003cli\u003eFeng ZY, Wu XH, Ma JL, Li M, He GF, Cao DS, Yang GP: DKADE: a novel framework based on deep learning and knowledge graph for identifying adverse drug events and related medications. \u003cem\u003eBrief Bioinform \u003c/em\u003e2023, 24(4).\u003c/li\u003e\n\u003cli\u003eCarr A, Cooper DA: Adverse effects of antiretroviral therapy. \u003cem\u003eLancet \u003c/em\u003e2000, 356(9239):1423-1430.\u003c/li\u003e\n\u003cli\u003eGonz\u0026aacute;lez-Mart\u0026iacute;n G, Ya\u0026ntilde;ez CG, Gonz\u0026aacute;lez-Contreras L, Labarca J: Adverse drug reactions (ADRs) in patients with HIV infection. A prospective study. \u003cem\u003eInt J Clin Pharmacol Ther \u003c/em\u003e1999, 37(1):34-40.\u003c/li\u003e\n\u003cli\u003ePoojar B, Kamath A, Rao SB, Ullal SD, Ramapuram J, Yadiyal MB, Shenoy AK: A Prospective Study of the Medication Regimen Complexity Index and Hospitalization Due to Adverse Drug Reactions Among People Living with HIV. \u003cem\u003eMedicina (Kaunas) \u003c/em\u003e2024, 60(10).\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Adverse Drug Reactions, AIDS, real-world","lastPublishedDoi":"10.21203/rs.3.rs-5703681/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5703681/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTo evaluate the incidence and type with adverse drug reactions (ADRs) among HIV/AIDS patients by Hospital Intelligent Pharmacovigilance System. A retrospective analysis was performed on 3971 HIV/AIDS patients admitted to the First Hospital of Changsha in China, from January 1, 2022 to December 31, 2023. Intelligent Recognition Models with Natural Language Processing Techniques for Intelligent Monitoring Systems was used to detect ADR signals of hospital information system. The causality risk factors for the ADRs of adverse drug reactions were classified using the WHO-UMC system. Our results showed that the prevalence of ADRs was 15.69% in the patients, which mainly was predominated by skin and appendages disorders and gastrointestinal (GI) disorders (2.87% vs. 2.67% ). The most of the reactions were associated with ADR could be explained by the use of antimicrobials and antiretrovirals with by 34.92% and 26.32%, respectively. 75.36% of ADRs had occurrenceed within 14 days of hospitalization. Together, the incidence of adverse reaction ADRs of patients was significantly high during the treatment period. Moreover, the active monitoring of the CHPS system reflected the adverse reaction ADRs of patients with during COVID-19 treatment in the real world, which provided reference for clinical safe medication in clinic.\u003c/p\u003e","manuscriptTitle":"Incidence of Adverse Drug Reactions in HIV/AIDS patients in China: an active monitoring study using leveraging natural language processing and machine learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-01-02 06:01:05","doi":"10.21203/rs.3.rs-5703681/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"a72db102-772f-4b12-ad73-f919c02b0468","owner":[],"postedDate":"January 2nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-01-10T07:53:22+00:00","versionOfRecord":[],"versionCreatedAt":"2025-01-02 06:01:05","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5703681","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5703681","identity":"rs-5703681","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}