Prediction of pneumonia in outpatients with acute cough—A statistical approach

doi:10.1016/0021-9681(84)90149-8

Journal of Chronic Diseases

Volume 37, Issue 3, 1984, Pages 215-225

Journal of Chronic D...

https://doi.org/10.1016/0021-9681(84)90149-8 Get rights and content

Abstract

Cough is the fifth most common reason for physician visits, but data on acute cough have rarely been collected in a standardized manner and have not been analyzed in a multivariate fashion. We report data on 1819 patients presenting with cough, all of whom received a standardized history and physical, and a chest X-ray. Only 48 (2.6%) were found to have an acute radiographic infiltrate (pneumonia). The prevalence of common signs and symptoms is shown for the patients with and without pneumonia. Thirty-two of these findings were significant predictors of pneumonia (p < 0.05, one-tailed). These 32 did not include some of the expected predictors of pneumonia and did include some predictors not previously described in the literature. A diagnostic rule is developed which identifies pneumonia patients with 91% sensitivity and 40% specificity, or 74% sensitivity and 70% specificity. The study results suggest that many pneumonias could be predicted based only on the patients histories. Physician visits to determine physical findings and chest X-rays might be avoided by telephone triage, with substantial cost savings.

References (8)

Cypress et al.
Patients reasons for visiting physicians
JB Bushyhead et al.
The effect of chest radiographs on the management and clinical course of patients with acute cough
Med Care
(1983)
J Ipsen et al.
Bancroft's Introduction to Biostatistics
(1970)
DG Kleinbaum et al.
Applied Regression Analysis and other Multivariable Methods
(1978)

There are more references available in the full text version of this article.

Cited by (168)

Chronic Obstructive Pulmonary Disease and the Physical Examination
2022, Medical Clinics of North America
AI4COVID-19: AI enabled preliminary diagnosis for COVID-19 from cough samples via an app
2020, Informatics in Medicine Unlocked
The inability to test at scale has become humanity's Achille's heel in the ongoing war against the COVID-19 pandemic. A scalable screening tool would be a game changer. Building on the prior work on cough-based diagnosis of respiratory diseases, we propose, develop and test an Artificial Intelligence (AI)-powered screening solution for COVID-19 infection that is deployable via a smartphone app. The app, named AI4COVID-19 records and sends three 3-s cough sounds to an AI engine running in the cloud, and returns a result within 2 min.
Cough is a symptom of over thirty non-COVID-19 related medical conditions. This makes the diagnosis of a COVID-19 infection by cough alone an extremely challenging multidisciplinary problem. We address this problem by investigating the distinctness of pathomorphological alterations in the respiratory system induced by COVID-19 infection when compared to other respiratory infections. To overcome the COVID-19 cough training data shortage we exploit transfer learning. To reduce the misdiagnosis risk stemming from the complex dimensionality of the problem, we leverage a multi-pronged mediator centered risk-averse AI architecture.
Results show AI4COVID-19 can distinguish among COVID-19 coughs and several types of non-COVID-19 coughs. The accuracy is promising enough to encourage a large-scale collection of labeled cough data to gauge the generalization capability of AI4COVID-19. AI4COVID-19 is not a clinical grade testing tool. Instead, it offers a screening tool deployable anytime, anywhere, by anyone. It can also be a clinical decision assistance tool used to channel clinical-testing and treatment to those who need it the most, thereby saving more lives.
Clinical prediction rule to predict pneumonia in adult presented with acute febrile respiratory illness
2019, American Journal of Emergency Medicine
Citation Excerpt :
In line with other literature, we have demonstrated age, temperature, abnormal breath sounds and history of pneumonia significantly increased the odds of having pneumonia [2,9,12-15]. The presence of chronic lung diseases, immunocompromised state was not significant predictors [9]. However, the number of such cases in our cohort might be too small to detect such an association.
To derive a clinical prediction rule to predict pneumonia in patients with acute febrile respiratory illness to emergency departments.
This was a prospective multicentre study. 537 adults were recruited. Those requiring resuscitation or were hypoxaemic on presentation were excluded. Pneumonia was defined as new onset infiltrates on chest X-ray (CXR), or re-attendance within 7 days and diagnosed clinically as having pneumonia. A predictive model, the Acute Febrile Respiratory Illness (AFRI) rule was derived by logistic regression analysis based on clinical parameters. The AFRI rule was internally validated with bootstrap resampling and was compared with the Diehr and Heckerling rule.
In the 363 patients who underwent CXR, 100 had CXR confirmed pneumonia. There were 7 weighted factors within the ARFI rule, which on summation, gave the AFRI score: age ≥ 65 (1 point), peak temperature within 24 h ≥ 40 °C (2 points), fever duration ≥3 days (2 points), sore throat (−2 points), abnormal breath sounds (1 point), history of pneumonia (1 point) and SpO2 ≤ 96% (1 point). With the bootstrap resampling, the AFRI rule was found to be more accurate than the Diehr and Heckerling rule (area under ROC curve 0.816, 0.721 and 0.566 respectively, p < 0.001). At a cut-off of AFRI≥0, the rule was found to have 95% sensitivity, with a negative predictive value of 97.2%. Using the AFRI score, we found CXR could be avoided for patients having a score of <0.
AFRI score could assist emergency physicians in identifying pneumonia patients among all adult patients presented to ED for acute febrile respiratory illness.
Adult Outpatients With Acute Cough Due to Suspected Pneumonia or Influenza: CHEST Guideline and Expert Panel Report
2019, Chest
Citation Excerpt :
Still, 41% of patients with pneumonia were missed at this cutoff point. Emerman et al22 was a prospective cross-sectional study that evaluated the decision rule developed by Diehr et al21 as well as the three other decision rules noted earlier. A total of 290 patients were included in the study, of whom 7% had pneumonia diagnosed based on chest radiographs.
Patients commonly present to primary care services with upper and lower respiratory tract infections, and guidelines to help physicians investigate and treat acute cough due to suspected pneumonia and influenza are needed.
A systematic search was carried out with eight patient, intervention, comparison, outcome questions related to acute cough due to suspected pneumonia or influenza.
There was a lack of randomized controlled trials in the setting of outpatients presenting with acute cough due to suspected pneumonia or influenza who were not hospitalized. Both clinical suggestions and research recommendations were made on the evidence available and CHEST Expert Cough Panel advice.
For outpatient adults with acute cough due to suspected pneumonia, we suggest the following clinical symptoms and signs are suggestive of pneumonia: cough; dyspnea; pleural pain; sweating, fevers, or shivers; aches and pains; temperature ≥ 38°C; tachypnea; and new and localizing chest examination signs. Those suspected of having pneumonia should undergo chest radiography to improve diagnostic accuracy. Although the measurement of C-reactive protein levels strengthens both the diagnosis and exclusion of pneumonia, there was no added benefit of measuring procalcitonin levels in this setting. We suggest that there is no need for routine microbiological testing. We suggest the use of empiric antibiotics according to local and national guidelines when pneumonia is suspected in settings in which imaging cannot be performed. Where there is no clinical or radiographic evidence of pneumonia, we do not suggest the routine use of antibiotics. There is insufficient evidence to make recommendations for or against specific nonantibiotic, symptomatic therapies. Finally, for outpatient adults with acute cough and suspected influenza, we suggest that initiating antiviral treatment (according to Centers for Disease Control and Prevention advice) within 48 hours of symptoms could be associated with decreased antibiotic use and hospitalization and improved outcomes.
Guidelines for the Evaluation and Treatment of Pneumonia
2018, Primary Care - Clinics in Office Practice
Citation Excerpt :
Important components of a history include recent travel, history of underlying lung disease, and smoking history.4,6 A study by Diehr and colleagues7 found that history of alcoholism or bloody sputum have relative risk of 1, so the presence of these findings is not predictive of pneumonia. Physical examination findings frequently appreciated in patients with pneumonia include decreased breath sounds, rales, tactile fremitus, and crackles.4,8
Emergency Medicine Evaluation of Community-Acquired Pneumonia: History, Examination, Imaging and Laboratory Assessment, and Risk Scores
2017, Journal of Emergency Medicine
Pneumonia is a common infection, accounting for approximately one million hospitalizations in the United States annually. This potentially life-threatening disease is commonly diagnosed based on history, physical examination, and chest radiograph.
To investigate emergency medicine evaluation of community-acquired pneumonia including history, physical examination, imaging, and the use of risk scores in patient assessment.
Pneumonia is the number one cause of death from infectious disease. The condition is broken into several categories, the most common being community-acquired pneumonia. Diagnosis centers on history, physical examination, and chest radiograph. However, all are unreliable when used alone, and misdiagnosis occurs in up to one-third of patients. Chest radiograph has a sensitivity of 46–77%, and biomarkers including white blood cell count, procalcitonin, and C-reactive protein provide little benefit in diagnosis. Biomarkers may assist admitting teams, but require further study for use in the emergency department. Ultrasound has shown utility in correctly identifying pneumonia. Clinical gestalt demonstrates greater ability to diagnose pneumonia. Clinical scores including Pneumonia Severity Index (PSI); Confusion, blood Urea nitrogen, Respiratory rate, Blood pressure, age 65 score (CURB-65); and several others may be helpful for disposition, but should supplement, not replace, clinical judgment. Patient socioeconomic status must be considered in disposition decisions.
The diagnosis of pneumonia requires clinical gestalt using a combination of history and physical examination. Chest radiograph may be negative, particularly in patients presenting early in disease course and elderly patients. Clinical scores can supplement clinical gestalt and assist in disposition when used appropriately.

View all citing articles on Scopus

^☆

This research was supported in part by the U.S. Army Health Services command through Contracts DADA11-77-C-0008 and DADA11-78-C-0009, and by DHHS Bureau of Medical Services.

The views expressed here are not necessarily those of the U.S. Army or of DHHS.

View full text

Original articlePrediction of pneumonia in outpatients with acute cough—A statistical approach☆

Abstract

Patients reasons for visiting physicians

The effect of chest radiographs on the management and clinical course of patients with acute cough

Med Care

Bancroft's Introduction to Biostatistics

Applied Regression Analysis and other Multivariable Methods

Original article
Prediction of pneumonia in outpatients with acute cough—A statistical approach☆