Early detection of COVID-19 outbreaks using textual analysis of electronic medical records

Shapiro, Michael; Landau, Regev; Shay, Shahaf; Kaminski, Marina; Verhovsky, Guy

doi:10.1016/j.jcv.2022.105251

Cited by 7 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, a study carried out in Israel used a similar technique to detect Covid cases, with specificity found to be 81.5%. However, 78 cases were used to verify the model’s accuracy at an individual level, not a curve level [ 28 ]. Therefore, the initiative presented in our article is unique in the current context of epidemiological surveillance.…”

Section: Discussionmentioning

confidence: 99%

COVID-19 outbreaks surveillance through text mining applied to electronic health records

Rocha,

Solha,

Furtado

et al. 2024

BMC Infect Dis

View full text Add to dashboard Cite

Background The COVID-19 pandemic has caused significant disruptions to everyday life and has had social, political, and financial consequences that will persist for years. Several initiatives with intensive use of technology were quickly developed in this scenario. However, technologies that enhance epidemiological surveillance in contexts with low testing capacity and healthcare resources are scarce. Therefore, this study aims to address this gap by developing a data science model that uses routinely generated healthcare encounter records to detect possible new outbreaks early in real-time. Methods We defined an epidemiological indicator that is a proxy for suspected cases of COVID-19 using the health records of Emergency Care Unit (ECU) patients and text mining techniques. The open-field dataset comprises 2,760,862 medical records from nine ECUs, where each record has information about the patient’s age, reported symptoms, and the time and date of admission. We also used a dataset where 1,026,804 cases of COVID-19 were officially confirmed. The records range from January 2020 to May 2022. Sample cross-correlation between two finite stochastic time series was used to evaluate the models. Results For patients with age 18 years, we find time-lag () = 72 days and cross-correlation () ~ 0.82, = 25 days and ~ 0.93, and = 17 days and ~ 0.88 for the first, second, and third waves, respectively. Conclusions In conclusion, the developed model can aid in the early detection of signs of possible new COVID-19 outbreaks, weeks before traditional surveillance systems, thereby anticipating in initiating preventive and control actions in public health with a higher likelihood of success.

show abstract

Section: Discussionmentioning

confidence: 99%

COVID-19 outbreaks surveillance through text mining applied to electronic health records

Rocha,

Solha,

Furtado

et al. 2024

BMC Infect Dis

View full text Add to dashboard Cite

show abstract

“…In total, 60 studies were included for data analysis on booster COVID-19 vaccination, 43 studies reported on the immune response of a total of 4754 patients with a diagnosis of hematological malignancy, and 22 studies determined immune seroconversion in 2440 patients with solid tumors [ 78 , 79 , 84 , 85 , 86 , 87 , 88 , 89 , 90 , 91 , 92 , 93 , 94 , 95 , 96 , 97 , 98 , 99 , 100 , 101 , 102 , 103 , 104 , 105 , 106 , 107 , 108 , 109 , 110 , 111 , 112 , 113 , 114 , 115 , 116 , 117 , 118 , 119 , 120 , 121 , 122 , 123 , 124 , 125 , 126 , 127 , 128 , 129 , 130 , 131 , 132 ,…”

Section: Resultsmentioning

confidence: 99%

Adult Patients with Cancer Have Impaired Humoral Responses to Complete and Booster COVID-19 Vaccination, Especially Those with Hematologic Cancer on Active Treatment: A Systematic Review and Meta-Analysis

Liatsou

Ntanasis‐Stathopoulos

Lykos

et al. 2023

Cancers

View full text Add to dashboard Cite

The exclusion of patients with cancer in clinical trials evaluating COVID-19 vaccine efficacy and safety, in combination with the high rate of severe infections, highlights the need for optimizing vaccination strategies. The aim of this study was to perform a systematic review and meta-analysis of the published available data from prospective and retrospective cohort studies that included patients with either solid or hematological malignancies according to the PRISMA Guidelines. A literature search was performed in the following databases: Medline (Pubmed), Scopus, Clinicaltrials.gov, EMBASE, CENTRAL and Google Scholar. Overall, 70 studies were included for the first and second vaccine dose and 60 studies for the third dose. The Effect Size (ES) of the seroconversion rate after the first dose was 0.41 (95%CI: 0.33–0.50) for hematological malignancies and 0.56 (95%CI: 0.47–0.64) for solid tumors. The seroconversion rates after the second dose were 0.62 (95%CI: 0.57–0.67) for hematological malignancies and 0.88 (95%CI: 0.82–0.93) for solid tumors. After the third dose, the ES for seroconversion was estimated at 0.63 (95%CI: 0.54–0.72) for hematological cancer and 0.88 (95%CI: 0.75–0.97) for solid tumors. A subgroup analysis was performed to evaluate potential factors affecting immune response. Production of anti-SARS-CoV-2 antibodies was found to be more affected in patients with hematological malignancies, which was attributed to the type of malignancy and treatment with monoclonal antibodies according to the subgroup analyses. Overall, this study highlights that patients with cancer present suboptimal humoral responses after COVID-19 vaccination. Several factors including timing of vaccination in relevance with active therapy, type of therapy, and type of cancer should be considered throughout the immunization process.

show abstract

“…Recent literature shows an increased use and interest in NLP for the analysis of EHRs [16]. Concerning the COVID-19 pandemic, several studies have highlighted the potential of NLP methods to detect and characterize cases from EHR data [17][18][19][20]. A large review focusing on the predictive value of COVID-19 symptoms showed that both the absence and presence of specific symptoms could accurately determine COVID-19 status [21].…”

Section: Comparison With Previous Studiesmentioning

confidence: 99%

A Natural Language Processing Model for COVID-19 Detection Based on Dutch General Practice Electronic Health Records by Using Bidirectional Encoder Representations From Transformers: Development and Validation Study

Homburg,

Meijer,

Berends

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

Background Natural language processing (NLP) models such as bidirectional encoder representations from transformers (BERT) hold promise in revolutionizing disease identification from electronic health records (EHRs) by potentially enhancing efficiency and accuracy. However, their practical application in practice settings demands a comprehensive and multidisciplinary approach to development and validation. The COVID-19 pandemic highlighted challenges in disease identification due to limited testing availability and challenges in handling unstructured data. In the Netherlands, where general practitioners (GPs) serve as the first point of contact for health care, EHRs generated by these primary care providers contain a wealth of potentially valuable information. Nonetheless, the unstructured nature of free-text entries in EHRs poses challenges in identifying trends, detecting disease outbreaks, or accurately pinpointing COVID-19 cases. Objective This study aims to develop and validate a BERT model for detecting COVID-19 consultations in general practice EHRs in the Netherlands. Methods The BERT model was initially pretrained on Dutch language data and fine-tuned using a comprehensive EHR data set comprising confirmed COVID-19 GP consultations and non–COVID-19–related consultations. The data set was partitioned into a training and development set, and the model’s performance was evaluated on an independent test set that served as the primary measure of its effectiveness in COVID-19 detection. To validate the final model, its performance was assessed through 3 approaches. First, external validation was applied on an EHR data set from a different geographic region in the Netherlands. Second, validation was conducted using results of polymerase chain reaction (PCR) test data obtained from municipal health services. Lastly, correlation between predicted outcomes and COVID-19–related hospitalizations in the Netherlands was assessed, encompassing the period around the outbreak of the pandemic in the Netherlands, that is, the period before widespread testing. Results The model development used 300,359 GP consultations. We developed a highly accurate model for COVID-19 consultations (accuracy 0.97, F1-score 0.90, precision 0.85, recall 0.85, specificity 0.99). External validations showed comparable high performance. Validation on PCR test data showed high recall but low precision and specificity. Validation using hospital data showed significant correlation between COVID-19 predictions of the model and COVID-19–related hospitalizations (F1-score 96.8; P<.001; R2=0.69). Most importantly, the model was able to predict COVID-19 cases weeks before the first confirmed case in the Netherlands. Conclusions The developed BERT model was able to accurately identify COVID-19 cases among GP consultations even preceding confirmed cases. The validated efficacy of our BERT model highlights the potential of NLP models to identify disease outbreaks early, exemplifying the power of multidisciplinary efforts in harnessing technology for disease identification. Moreover, the implications of this study extend beyond COVID-19 and offer a blueprint for the early recognition of various illnesses, revealing that such models could revolutionize disease surveillance.

show abstract

Early detection of COVID-19 outbreaks using textual analysis of electronic medical records

Cited by 7 publications

References 27 publications

COVID-19 outbreaks surveillance through text mining applied to electronic health records

COVID-19 outbreaks surveillance through text mining applied to electronic health records

Adult Patients with Cancer Have Impaired Humoral Responses to Complete and Booster COVID-19 Vaccination, Especially Those with Hematologic Cancer on Active Treatment: A Systematic Review and Meta-Analysis

A Natural Language Processing Model for COVID-19 Detection Based on Dutch General Practice Electronic Health Records by Using Bidirectional Encoder Representations From Transformers: Development and Validation Study

Contact Info

Product

Resources

About