AI-based disease risk score for community-acquired pneumonia hospitalization

Shakibfar et al., iScience, doi:10.1016/j.isci.2023.107027

Jul 2023

Source PDF All Studies Meta AnalysisMeta

Pre-COVID model of community-acquired pneumonia (CAP) identifying acetaminophen as one of the top 10 predictors for hospitalization.

Authors claim that acetaminophen was not a biologically plausible predictor of CAP, hypothesizing that acetaminophen may be a proxy for other conditions that increase CAP risk, specifically chronic pain.

Although authors claim there is no biological plausibility, there are multiple potential mechanisms including:

- Glutathione depletion - acetaminophen metabolism relies on glutathione. Higher or chronic doses can deplete glutathione levels. Lower glutathione reduces antioxidant defenses and impairs immune cell function.

- Prostaglandin inhibition - acetaminophen inhibits prostaglandins like PGE2 that help regulate immune responses. Reduced prostaglandins could potentially alter immune regulation.

- Disruption of redox balance - in addition to glutathione, acetaminophen may disrupt the redox balance which can impair immune cell function.

- Glycine depletion - conjugating acetaminophen requires glycine. Depletion of glycine can reduce antioxidant production and have immunomodulatory effects.

- Microbiome alteration - acetaminophen exposure might alter the intestinal microbiota in ways that promote inflammation and reduce colonization resistance.

- Cell/tissue injury - even at normal doses, acetaminophen may cause low-grade cell or tissue damage that induces inflammatory and immune effects.

- Fever suppression - by reducing fever through effects on the hypothalamus, acetaminophen could potentially prolong infections. Acetaminophen is also known as paracetamol, Tylenol, Panadol, Calpol, Tempra, Calprofen, Doliprane, Efferalgan, Grippostad C, Dolo, Acamol, Fevadol, Crocin, and Perfalgan.

Important missing comments or errors? Let us know.

Shakibfar et al., 31 Jul 2023, Denmark, peer-reviewed, 3 authors.

Contact: maurizio.sessa@sund.ku.dk.

All Studies Meta Analysis Submit Updates or Corrections

This Paper Acetaminophen All

AI-based disease risk score for communityacquired pneumonia hospitalization

Saeed Shakibfar, Morten Andersen, Maurizio Sessa

doi:10.1016/j.isci

We developed a disease risk score for CAP hospitalization based on real-world data This tool can help to identify individuals requiring specific clinical management Further studies are needed to investigate the optimal use of our disease risk

Detailed methods are provided in the online version of this paper and include the following: SUPPLEMENTAL INFORMATION Supplemental information can be found online at https://doi.org/10.1016/j.isci.2023.107027. AUTHOR CONTRIBUTIONS S.S. wrote the original draft, conceptualized the study, and performed the data analysis. M.A. supervised the study, acquired the funding, and revised the manuscript. M.S. planned the study, performed the data analysis, wrote the original draft, and supervised the study. DECLARATION OF INTERESTS None. INCLUSION AND DIVERSITY We support inclusive, diverse, and equitable conduct of research. KEY RESOURCES TABLE RESOURCE AVAILABILITY Lead contact Further information and requests for data sources should be directed to and will be fulfilled by the lead contact, Maurizio Sessa (maurizio.sessa@sund.ku.dk). Material availability This study did not generate new unique reagents. Data and code availability d All data will be shared upon request to the lead contact. No standardized datatype data were generated in this study. d This study did not generate new code. d Any additional analysis information for this work is available by request to the lead contact. EXPERIMENTAL MODEL AND STUDY PARTICIPANT DETAILS The study does not need ethical approval and patient consent because Danish register-based cohort studies are exempted. Patient records/information before the analysis was pseudonymized. The University of Copenhagen and Statistics..

References

Adamuz, Viasus, Camprecio ´s-Rodrı ´guez, Can ˜avate-Jurado, Jime ´nez-Martı ´nez et al., A prospective cohort study of healthcare visits and rehospitalizations after discharge of patients with community-acquired pneumonia, Respirology

Aliberti, Dela Cruz, Amati, Sotgiu, Restrepo, Communityacquired pneumonia, Lancet

Andersen, Olivarius, Krasnik, The Danish national health service register, Scand. J. Public Health

Bischl, Lang, Kotthoff, Schiffner, Richter et al., Mlr: machine learning in R, J. Mach. Learn. Res

Branco, Torgo, Ribeiro, A survey of predictive modelling under imbalanced distributions, doi:10.48550/arXiv.1505.01658

Breiman, Random forests, Mach. Learn

Capelastegui, Espan ˜a Yandiola, Quintana, Bilbao, Diez et al., Predictors of short-term rehospitalization following discharge of patients hospitalized with community-acquired pneumonia, Chest

Cavallazzi, Ramirez, Community-acquired pneumonia in chronic obstructive pulmonary disease, Curr. Opin. Infect. Dis

Corrales-Medina, Alvarez, Weissfeld, Angus, Chirinos et al., Association between hospitalization for pneumonia and subsequent risk of cardiovascular disease, JAMA

File, Jr, Community-acquired pneumonia, Lancet

Graffelman, Van Eeuwijk, Calibration of multivariate scatter plots for exploratory analysis of relations within and between sets of variables in genomic research, Biom. J

Hagengaard, Søgaard, Espersen, Sessa, Lund et al., Association between serum potassium levels and short-term mortality in patients with atrial fibrillation or flutter co-treated with diuretics and rate-or rhythm-controlling drugs, Eur. Heart J. Cardiovasc. Pharmacother

Helweg-Larsen, The Danish register of causes of death, Scand. J. Public Health

Jain, Self, Wunderink, Fakhran, Balk et al., Community-acquired pneumonia requiring hospitalization among US adults, N. Engl. J. Med

Jasti, Mortensen, Obrosky, Kapoor, Fine, Causes and risk factors for rehospitalization of patients hospitalized with communityacquired pneumonia, Clin. Infect. Dis

Kildemoes, Sørensen, Hallas, The Danish national prescription registry, Scand. J. Public Health

Klausen, Petersen, Lindhardt, Bandholm, Hendriksen et al., Outcomes in elderly Danish citizens admitted with community-acquired pneumonia. Regional differencties, in a public healthcare system, Respir. Med

Kuhn, Johnson, Applied Predictive Modeling

Larj, Bleecker, Therapeutic responses in asthma and COPD: corticosteroids, Chest

Letourneau, Issa, Baden, Pneumonia in the immunocompromised host, Curr. Opin. Pulm. Med

Luke, Harris, Network analysis in public health: history, methods, and applications

Lynge, Sandegaard, Rebolj, The Danish national patient register, Scand. J. Public Health

Mather, Fortunato, Ash, Davis, Kumar, Prediction of pneumonia 30-day readmissions: a singlecenter attempt to increase model performance, Respir. Care

Nembrini, Ko ¨nig, Wright, The revival of the Gini importance?, Bioinformatics

Neumann, Genze, Heider, EFS: an ensemble feature selection tool implemented as R-package and webapplication, BioData Min, doi:10.1186/s13040-017-0142-8

Pedersen, The Danish civil registration system, Scand. J. Public Health

Restrepo, Reyes, Pneumonia as a cardiovascular disease, Respirology

Sankaran, Mattana, Pollack, Bhat, Ahuja et al., Laboratory abnormalities in patients with bacterial pneumonia, Chest

Sessa, Mascolo, Andersen, Rosano, Rossi et al., Effect of chronic kidney diseases on mortality among digoxin users treated for non-valvular atrial fibrillation: a nationwide register-based retrospective cohort study, PLoS One

Sessa, Mascolo, Dalhoff, Andersen, The risk of fractures, acute myocardial infarction, atrial fibrillation and ventricular arrhythmia in geriatric patients exposed to promethazine, Expert Opin. Drug Saf

Sessa, Mascolo, Mortensen, Andersen, Rosano et al., None

Sessa, Mascolo, Scavone, Perone, Di Giorgio et al., Comparison of long-term clinical implications of beta-blockade in patients with obstructive airway diseases exposed to beta-blockers with different b1-adrenoreceptor selectivity: an Italian Population-Based Cohort Study, Front. Pharmacol

Sessa, Rasmussen, Jensen, Kragholm, Torp-Pedersen et al., Metoprolol versus carvedilol in patients with heart failure, chronic obstructive pulmonary disease, diabetes mellitus, and renal failure, Am. J. Cardiol

Shorr, Zilberberg, Reichley, Kan, Hoban et al., Readmission following hospitalization for pneumonia: the impact of pneumonia type and its implication for hospitals, Clin. Infect. Dis

Stern, Skalsky, Avni, Carrara, Leibovici et al., Corticosteroids for pneumonia

Sun, Douiri, Gulliford, Applying machine learning algorithms to electronic health records predicted pneumonia after respiratory tract infection, J. Clin. Epidemiol

Søgaard, Nielsen, Schønheyder, Nørgaard, Thomsen, Nationwide trends in pneumonia hospitalization rates and mortality, Denmark 1997-2011, Respir. Med

Tang, Halm, Fine, Johnson, Anzueto et al., Predictors of rehospitalization after admission for pneumonia in the veterans affairs healthcare system, J. Hosp. Med

Ticona, Zaccone, Mcfarlane, Community-acquired pneumonia: a focused review, Am. J. Med. Case Rep

Torp-Pedersen, Relationship between heart failure, concurrent chronic obstructive pulmonary disease and beta-blocker use: a Danish nationwide cohort study, Eur. J. Heart Fail

Torres, Cilloniz, Niederman, Mene ´ndez, Chalmers et al., None, Pneumonia. Nat. Rev. Dis. Primers, doi:10.1038/s41572-021-00259-0

Torres, Peetermans, Viegi, Blasi, Risk factors for communityacquired pneumonia in adults in Europe: a literature review, Thorax

Yu, Liu, Efficient feature selection via analysis of relevance and redundancy, J. Mach. Learn. Res

Late treatment
is less effective

Please send us corrections, updates, or comments. Vaccines and treatments are complementary. All practical, effective, and safe means should be used based on risk/benefit analysis. No treatment, vaccine, or intervention is 100% available and effective for all current and future variants. We do not provide medical advice. Before taking any medication, consult a qualified physician who can provide personalized advice and details of risks and benefits based on your medical history and situation. FLCCC and WCH provide treatment protocols.

Submit

@CovidAnalysis

FAQ

Public domain CC0 1.0