Clinical utility of the full blood count in identifying patients with pandemic influenza A (H1N1)

Prolonged lymphopenia and prognoses among inpatients with different respiratory virus infections: A retrospective cohort study

Background

Lymphopenia is common in respiratory viral infection. However, no studies elucidated the impact of prolonged lymphopenia on worse outcome in the way of quantitative risk.

Methods

Adult patients with laboratory-confirmed respiratory virus infection (influenza, SARS-CoV-2, and other viruses) between January 1st, 2016, and February 1st, 2023 were enrolled in this retrospective cohort study. Serial data of laboratory examination during hospitalization were acquired. The primary outcome was in-hospital all-cause death, and all information was obtained from the electronic medical records system. Legendre orthogonal polynomials (LOP), restricted cubic splines, and multivariable logistic regression were performed.

Results

Finally, 2388 inpatients were involved in this study, including 436 patients with influenza, 1397 with SARS-CoV-2, and 319 with other respiratory virus infections. After being adjusted for age, corticosteroids, chronic kidney disease, chronic respiratory disease, cardiovascular disease, lymphopenia on admission and length of hospital stay, prolonged lymphopenia was significantly associated with death in influenza (OR 7.20, 95 % CI 2.27-22.77, p = 0. 0008 for lasting for 3-7 days; OR 17.80, 95 % CI 5.21-60.82, p < 0.0001 for lasting for more than 7 days) and SARS-CoV-2 (OR 3.07, 95 % CI 1.89-5.01, p < 0.0001 for lasting for 3-7 days; OR 6.28, 95 % CI 3.53-11.18, p < 0.0001 for lasting for more than 7 days), compared with a transient lymphopenia of 1-2 days, while no significant association was found in other respiratory viruses. Prolonged lymphopenia was also associated with multi-organ damage in influenza and SARS-CoV-2 infections.

Conclusions

Prolonged lymphopenia was significantly associated with worse clinical prognoses in influenza and SARS-CoV-2 infections, but not in other respiratory virus infections.

Hemogram data as a tool for decision-making in COVID-19 management: applications to resource scarcity scenarios

Background

COVID-19 pandemics has challenged emergency response systems worldwide, with widespread reports of essential services breakdown and collapse of health care structure. A critical element involves essential workforce management since current protocols recommend release from duty for symptomatic individuals, including essential personnel. Testing capacity is also problematic in several countries, where diagnosis demand outnumbers available local testing capacity.

Purpose

This work describes a machine learning model derived from hemogram exam data performed in symptomatic patients and how they can be used to predict qRT-PCR test results.

Methods

Hemogram exams data from 510 symptomatic patients (73 positives and 437 negatives) were used to model and predict qRT-PCR results through Naïve-Bayes algorithms. Different scarcity scenarios were simulated, including symptomatic essential workforce management and absence of diagnostic tests. Adjusts in assumed prior probabilities allow fine-tuning of the model, according to actual prediction context.

Results

Proposed models can predict COVID-19 qRT-PCR results in symptomatic individuals with high accuracy, sensitivity and specificity, yielding a 100% sensitivity and 22.6% specificity with a prior of 0.9999; 76.7% for both sensitivity and specificity with a prior of 0.2933; and 0% sensitivity and 100% specificity with a prior of 0.001. Regarding background scarcity context, resources allocation can be significantly improved when model-based patient selection is observed, compared to random choice.

Conclusions

Machine learning models can be derived from widely available, quick, and inexpensive exam data in order to predict qRT-PCR results used in COVID-19 diagnosis. These models can be used to assist strategic decision-making in resource scarcity scenarios, including personnel shortage, lack of medical resources, and testing insufficiency.