scholarly journals Automated Travel History Extraction From Clinical Notes for Informing the Detection of Emergent Infectious Disease Events: Algorithm Development and Validation

10.2196/26719 ◽  
2021 ◽  
Vol 7 (3) ◽  
pp. e26719
Author(s):  
Kelly S Peterson ◽  
Julia Lewis ◽  
Olga V Patterson ◽  
Alec B Chapman ◽  
Daniel W Denhalter ◽  
...  
Keyword(s):  
Public Health ◽  
Infectious Disease ◽  
United States ◽  
Text Processing ◽  
The United States ◽  
Language Models ◽  
Travel History ◽  
Patient Travel ◽  
Electronic Health ◽  
Automated Text Processing

Background Patient travel history can be crucial in evaluating evolving infectious disease events. Such information can be challenging to acquire in electronic health records, as it is often available only in unstructured text. Objective This study aims to assess the feasibility of annotating and automatically extracting travel history mentions from unstructured clinical documents in the Department of Veterans Affairs across disparate health care facilities and among millions of patients. Information about travel exposure augments existing surveillance applications for increased preparedness in responding quickly to public health threats. Methods Clinical documents related to arboviral disease were annotated following selection using a semiautomated bootstrapping process. Using annotated instances as training data, models were developed to extract from unstructured clinical text any mention of affirmed travel locations outside of the continental United States. Automated text processing models were evaluated, involving machine learning and neural language models for extraction accuracy. Results Among 4584 annotated instances, 2659 (58%) contained an affirmed mention of travel history, while 347 (7.6%) were negated. Interannotator agreement resulted in a document-level Cohen kappa of 0.776. Automated text processing accuracy (F1 85.6, 95% CI 82.5-87.9) and computational burden were acceptable such that the system can provide a rapid screen for public health events. Conclusions Automated extraction of patient travel history from clinical documents is feasible for enhanced passive surveillance public health systems. Without such a system, it would usually be necessary to manually review charts to identify recent travel or lack of travel, use an electronic health record that enforces travel history documentation, or ignore this potential source of information altogether. The development of this tool was initially motivated by emergent arboviral diseases. More recently, this system was used in the early phases of response to COVID-19 in the United States, although its utility was limited to a relatively brief window due to the rapid domestic spread of the virus. Such systems may aid future efforts to prevent and contain the spread of infectious diseases.

scholarly journals Automated Travel History Extraction from Clinical Notes: Development and Application during Emergent Infectious Disease Events (Preprint)

2020 ◽  
Author(s):  
Kelly S Peterson ◽  
Julia Lewis ◽  
Olga V Patterson ◽  
Alec B Chapman ◽  
Daniel Denhalter ◽  
...  
Keyword(s):  
Public Health ◽  
Infectious Disease ◽  
United States ◽  
Text Processing ◽  
The United States ◽  
Language Models ◽  
Travel History ◽  
Patient Travel ◽  
Automated Text Processing ◽  
Arboviral Disease

BACKGROUND Patient travel history can be crucial in evaluating evolving infectious disease events. Such information can be challenging to acquire in electronic health records as it is often available only in unstructured text. OBJECTIVE Assess the feasibility of annotating and automatically extracting travel history mentions from unstructured clinical documents in the Department of Veterans Affairs (VA) across disparate healthcare facilities and among millions of patients. Information about travel exposure augments existing surveillance applications for increased preparedness in responding quickly to public health threats. METHODS Clinical documents related to arboviral disease were annotated following selection using a semi-automated bootstrapping process. Using annotated instances as training data, models were developed to extract from unstructured clinical text any mention of affirmed travel locations outside of the continental United States. Automated text processing models were evaluated involving machine learning and neural language models for extraction accuracy. RESULTS Among annotated instances, 2,659 (58%) contained an affirmed mention of travel history while 347 (7.6%) were negated. Inter-annotator agreement resulted in a document-level Cohen’s kappa (Κc) of 0.776. Automated text processing accuracy (F1=85.6) and computational burden were acceptable such that the system can provide a rapid screen for public health events. CONCLUSIONS Automated extraction of patient travel history from clinical documents is feasible for enhanced capabilities to improve public health systems. This evaluation was initially performed on emergent arboviral disease. More recently, this system was utilized in early phases of response to COVID-19 in the United States although its utility was limited to a relatively brief window due to rapid domestic spread of the virus. Such systems may aid future efforts to prevent and contain the spread of infectious diseases.

Ending HIV in the United States Is Possible With the Proper Leadership and Sufficient and Targeted Resources

2021 ◽  
pp. e1-e3
Author(s):  
Carl Schmid
Keyword(s):  
Public Health ◽  
Infectious Disease ◽  
United States ◽  
The United States ◽  
The Right

After 40 years of living and, sadly, dying with HIV, the United States has become rather complacent. Perhaps this is partially attributable to our own success in treating, preventing, and responding to HIV. But imagine if we allowed another deadly infectious disease, such as COVID-19, to continue to spread for 40 years without investing the attention and resources needed to wipe it out. We must end this dangerous cycle, and we can with the right tools and leadership. But will we? (Am J Public Health. Published online ahead of print June 10, 2021: e1–e3. https://doi.org/10.2105/AJPH.2021.306349 )

Reducing Reoccurence and Complications of Gc/Ct

2017 ◽  
Vol 2 (4) ◽  
Keyword(s):  
Public Health ◽  
Infectious Disease ◽  
United States ◽  
Chlamydia Trachomatis ◽  
Sexually Transmitted Infections ◽  
The United States ◽  
Positive Test ◽  
California Department ◽  
Sexually Transmitted ◽  
Initial Episode

Gonococcal Neisseria (GC) and Chlamydia Trachomatis (CT) infections account for the largest number of reported cases of any infectious disease in the United States. The rates at which these infections occur are on the rise. Gonococcal Neisseria (GC) and Chlamydia trachomatis (CT) infections are also among the commonly curable sexually transmitted infections (STI)(California Department of Public Health, 2011). Though subsequent infections are preventable, reinfection rates are high [1]. As many as 20% of patients, especially females, reacquire GC or CT within six months after the initial positive test and treatment, and it is estimated that as many as 40% of adolescents get re-infeceted after an initial episode of GC and/or CT annually [2]. Chlamydia represents the most common reportable disease in the United States, and has comprised the largest proportion of all sexually transmitted infections (STIs) reported [3].

Can increases in Twitter posts predict increases in cumulative incidence of COVID-19 in the United States? Evidence that social media can inform epidemic surveillance. (Preprint)

2020 ◽  
Author(s):  
Ruoyan Sun ◽  
Henna Budhwani
Keyword(s):  
Public Health ◽  
United States ◽  
Cumulative Incidence ◽  
Hot Spots ◽  
Adult Population ◽  
State Level ◽  
The United States ◽  
Education Attainment ◽  
Public Health Systems ◽  
Per Capita

BACKGROUND Though public health systems are responding rapidly to the COVID-19 pandemic, outcomes from publicly available, crowd-sourced big data may assist in helping to identify hot spots, prioritize equipment allocation and staffing, while also informing health policy related to “shelter in place” and social distancing recommendations. OBJECTIVE To assess if the rising state-level prevalence of COVID-19 related posts on Twitter (tweets) is predictive of state-level cumulative COVID-19 incidence after controlling for socio-economic characteristics. METHODS We identified extracted COVID-19 related tweets from January 21st to March 7th (2020) across all 50 states (N = 7,427,057). Tweets were combined with state-level characteristics and confirmed COVID-19 cases to determine the association between public commentary and cumulative incidence. RESULTS The cumulative incidence of COVID-19 cases varied significantly across states. Ratio of tweet increase (p=0.03), number of physicians per 1,000 population (p=0.01), education attainment (p=0.006), income per capita (p = 0.002), and percentage of adult population (p=0.003) were positively associated with cumulative incidence. Ratio of tweet increase was significantly associated with the logarithmic of cumulative incidence (p=0.06) with a coefficient of 0.26. CONCLUSIONS An increase in the prevalence of state-level tweets was predictive of an increase in COVID-19 diagnoses, providing evidence that Twitter can be a valuable surveillance tool for public health.

Sign in / Sign up

Export Citation Format

Share Document