Development and validation of a multivariable risk prediction model for serious infection in patients with psoriasis receiving systemic therapy

Clinical Timing-Sequence Warning Models for Serious Bacterial Infections in Adults Based on Machine Learning: Retrospective Study

BACKGROUND

Serious bacterial infections (SBIs) are linked to unplanned hospital admissions and a high mortality rate. The early identification of SBIs is crucial in clinical practice.

OBJECTIVE

This study aims to establish and validate clinically applicable models designed to identify SBIs in patients with infective fever.

METHODS

Clinical data from 945 patients with infective fever, encompassing demographic and laboratory indicators, were retrospectively collected from a 2200-bed teaching hospital between January 2013 and December 2020. The data were randomly divided into training and test sets at a ratio of 7:3. Various machine learning (ML) algorithms, including Boruta, Lasso (least absolute shrinkage and selection operator), and recursive feature elimination, were utilized for feature filtering. The selected features were subsequently used to construct models predicting SBIs using logistic regression (LR), random forest (RF), and extreme gradient boosting (XGBoost) with 5-fold cross-validation. Performance metrics, including the receiver operating characteristic (ROC) curve and area under the ROC curve (AUC), accuracy, sensitivity, and other relevant parameters, were used to assess model performance. Considering both model performance and clinical needs, 2 clinical timing-sequence warning models were ultimately confirmed using LR analysis. The corresponding predictive nomograms were then plotted for clinical use. Moreover, a physician, blinded to the study, collected additional data from the same center involving 164 patients during 2021. The nomograms developed in the study were then applied in clinical practice to further validate their clinical utility.

RESULTS

In total, 69.9% (661/945) of the patients developed SBIs. Age, hemoglobin, neutrophil-to-lymphocyte ratio, fibrinogen, and C-reactive protein levels were identified as important features by at least two ML algorithms. Considering the collection sequence of these indicators and clinical demands, 2 timing-sequence models predicting the SBI risk were constructed accordingly: the early admission model (model 1) and the model within 24 hours of admission (model 2). LR demonstrated better stability than RF and XGBoost in both models and performed the best in model 2, with an AUC, accuracy, and sensitivity of 0.780 (95% CI 0.720-841), 0.754 (95% CI 0.698-804), and 0.776 (95% CI 0.711-832), respectively. XGBoost had an advantage over LR in AUC (0.708, 95% CI 0.641-775 vs 0.686, 95% CI 0.617-754), while RF achieved better accuracy (0.729, 95% CI 0.673-780) and sensitivity (0.790, 95% CI 0.728-844) than the other 2 approaches in model 1. Two SBI-risk prediction nomograms were developed for clinical use based on LR, and they exhibited good performance with an accuracy of 0.707 and 0.750 and a sensitivity of 0.729 and 0.927 in clinical application.

CONCLUSIONS

The clinical timing-sequence warning models demonstrated efficacy in predicting SBIs in patients suspected of having infective fever and in clinical application, suggesting good potential in clinical decision-making. Nevertheless, additional prospective and multicenter studies are necessary to further confirm their clinical utility.

Acceptance of a digital therapy recommender system for psoriasis

BACKGROUND

About 2% of the German population are affected by psoriasis. A growing number of cost-intensive systemic treatments are available. Surveys have shown high proportions of patients with moderate to severe psoriasis are not adequately treated despite a high disease burden. Digital therapy recommendation systems (TRS) may help implement guideline-based treatment. However, little is known about the acceptance of such clinical decision support systems (CDSSs). Therefore, the aim of the study was to access the acceptance of a prototypical TRS demonstrator.

METHODS

Three scenarios (potential test patients with psoriasis but different sociodemographic and clinical characteristics, previous treatments, desire to have children, and multiple comorbidities) were designed in the demonstrator. The TRS demonstrator and test patients were presented to a random sample of 76 dermatologists attending a national dermatology conference in a cross-sectional face-to-face survey with case vignettes. The dermatologist were asked to rate the demonstrator by system usability scale (SUS), whether they would use it for certain patients populations and barriers of usage. Reasons for potential usage of the TRS demonstrator were tested via a Poisson regression with robust standard errors.

RESULTS

Acceptance of the TRS was highest for patients eligible for systemic therapy (82%). 50% of participants accepted the system for patients with additional comorbidities and 43% for patients with special subtypes of psoriasis. Dermatologists in the outpatient sector or with many patients per week were less willing to use the TRS for patients with special psoriasis-subtypes. Dermatologists rated the demonstrator as acceptable with an mean SUS of 76.8. Participants whose SUS was 10 points above average were 27% more likely to use TRS for special psoriasis-subtypes. The main barrier in using the TRS was time demand (47.4%). Participants who perceived time as an obstacle were 22.3% less willing to use TRS with systemic therapy patients. 27.6% of physicians stated that they did not understand exactly how the recommendation was generated by the TRS, with no effect on the preparedness to use the system.

CONCLUSION

The considerably high acceptance and the preparedness to use the psoriasis CDSS suggests that a TRS appears to be implementable in routine healthcare and may improve clinical care. Main barrier is the additional time demand posed on dermatologists in a busy clinical setting. Therefore, it will be a major challenge to identify a limited set of variables that still allows a valid recommendation with precise prediction of the patient-individual benefits and harms.

Expectations and attitudes towards medical artificial intelligence: A qualitative study in the field of stroke

INTRODUCTION

Artificial intelligence (AI) has the potential to transform clinical decision-making as we know it. Powered by sophisticated machine learning algorithms, clinical decision support systems (CDSS) can generate unprecedented amounts of predictive information about individuals' health. Yet, despite the potential of these systems to promote proactive decision-making and improve health outcomes, their utility and impact remain poorly understood due to their still rare application in clinical practice. Taking the example of AI-powered CDSS in stroke medicine as a case in point, this paper provides a nuanced account of stroke survivors', family members', and healthcare professionals' expectations and attitudes towards medical AI.

METHODS

We followed a qualitative research design informed by the sociology of expectations, which recognizes the generative role of individuals' expectations in shaping scientific and technological change. Semi-structured interviews were conducted with stroke survivors, family members, and healthcare professionals specialized in stroke based in Germany and Switzerland. Data was analyzed using a combination of inductive and deductive thematic analysis.

RESULTS

Based on the participants' deliberations, we identified four presumed roles that medical AI could play in stroke medicine, including an administrative, assistive, advisory, and autonomous role AI. While most participants held positive attitudes towards medical AI and its potential to increase accuracy, speed, and efficiency in medical decision making, they also cautioned that it is not a stand-alone solution and may even lead to new problems. Participants particularly emphasized the importance of relational aspects and raised questions regarding the impact of AI on roles and responsibilities and patients' rights to information and decision-making. These findings shed light on the potential impact of medical AI on professional identities, role perceptions, and the doctor-patient relationship.

CONCLUSION

Our findings highlight the need for a more differentiated approach to identifying and tackling pertinent ethical and legal issues in the context of medical AI. We advocate for stakeholder and public involvement in the development of AI and AI governance to ensure that medical AI offers solutions to the most pressing challenges patients and clinicians face in clinical care.

Management of Infections in Psoriatic Patients Treated with Systemic Therapies: A Lesson from the Immunopathogenesis of Psoriasis

Modern treatments continue to be developed based on identifying targets within the innate and adaptive immune pathways associated with psoriasis. Whilst there is a sound biologic rationale for increased risk of infection following treatment with immunomodulators, the clinical evidence is confounded by these agents being used in patients affected with several comorbidities. In an era characterized by an ever greater and growing risk of infections, it is necessary to always be updated on this risk. In this mini-review, we will discuss recent updates in psoriasis immunopathogenesis as a rationale for systemic therapy, outline the risk of infections linked to the disease itself and systemic therapy as well, and provide an overview of the prevention and management of infections.

Response to Vaccines in Patients with Immune-Mediated Inflammatory Diseases: A Narrative Review

Patients with immune-mediated inflammatory diseases (IMIDs), such as rheumatoid arthritis and inflammatory bowel disease, are at increased risk of infection. International guidelines recommend vaccination to limit this risk of infection, although live attenuated vaccines are contraindicated once immunosuppressive therapy has begun. Biologic therapies used to treat IMIDs target the immune system to stop chronic pathogenic process but may also attenuate the protective immune response to vaccines. Here, we review the current knowledge regarding vaccine responses in IMID patients receiving treatment with biologic therapies, with a focus on the interleukin (IL)-12/23 inhibitors. B cell-depleting therapies, such as rituximab, strongly impair vaccines immunogenicity, and tumor necrosis factor (TNF) inhibitors and the cytotoxic T-lymphocyte-associated antigen-4 (CTLA-4) fusion protein abatacept are also associated with attenuated antibody responses, which are further diminished in patients taking concomitant immunosuppressants. On the other hand, integrin, IL-6, IL-12/23, IL-17, and B-cell activating factor (BAFF) inhibitors do not appear to affect the immune response to several vaccines evaluated. Importantly, treatment with biologic therapies in IMID patients is not associated with an increased risk of infection with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) or developing severe disease. However, the efficacy of SARS-CoV-2 vaccines on IMID patients may be reduced compared with healthy individuals. The impact of biologic therapies on the response to SARS-CoV-2 vaccines seems to replicate what has been described for other vaccines. SARS-CoV-2 vaccination appears to be safe and well tolerated in IMID patients. Attenuated but, in general, still protective responses to SARS-CoV-2 vaccination in the context of certain therapies warrant current recommendations for a third primary dose in IMID patients treated with immunosuppressive drugs.

External Validation of a Predictive Model to Estimate Renal Function After Living Donor Nephrectomy

BACKGROUND

Transplantation from living donor nephrectomy (LDN) is the best treatment for end-stage renal disease but observed decrease in donor renal function is a major concern. The aim of this study was to externally validate a predictive model to estimate 1-y postdonation estimated glomerular filtration rate (eGFR) and risk of chronic kidney disease (CKD) in living donors.

METHODS

All LDN performed at Necker Hospital from January 2006 to May 2018 were retrospectively included. Observed eGFR (using CKD-EPI formula) at 1-y post LDN was compared with the predicted eGFR calculated with a formula developed at Toulouse-Rangueil and based on predonation eGFR and age. Pearson correlation, receiver operating characteristics curve (ROC curve), and calibration curve were used to assess external validity of the proposed prognostic model to predict postoperative eGFR and occurrence of CKD in donors.

RESULTS

Four hundred donors were evaluated with a mean postoperative eGFR of 62.1 ± 14 mL/min/1.73m2. Significant correlation (Pearson r = 0.66; P < 0.001) and concordance (Bradley-Blackwood F = 49.189; P < 0.001) were observed between predicted and observed 1-y eGFR. Area under the receiver operating characteristic curve of the model relevant accuracy was 0.86 (95% CI, 0.82-0.89).

CONCLUSIONS

This study externally validated the formula to predict 1-y postdonation eGFR. The calculator could be an accurate tool to improve the selection of living kidney donor candidate.

Immune checkpoint inhibitors and tuberculosis: an old disease in a new context

Tuberculosis, the leading cause of infection-related death in developing regions, is a leading cause of morbidity and mortality worldwide. Screening for, and treatment of, latent Mycobacterium tuberculosis infection is routine before initiation of anti-tumour necrosis factor α (anti-TNFα) agents in the management of psoriasis, Crohn's disease, and rheumatoid arthritis. By contrast, screening for latent tuberculosis before immune checkpoint inhibitor treatment in cancer is not routine, despite the increasing number of reports of primary infection with M tuberculosis or reactivation of latent M tuberculosis infection during such treatment. We present our experience with M tuberculosis screening in 70 patients who underwent immune checkpoint inhibitor therapy for metastatic skin cancer. Based on our understanding of the interaction between M tuberculosis and the immune system, we present the argument for tuberculosis screening before immune checkpoint inhibitor therapy and its use when considering anti-TNFα treatment for severe immune-related adverse events. We call for increased vigilance during immune checkpoint inhibition until its effects on tuberculosis pathophysiology are fully ascertained.

Novel Coronavirus Disease (COVID-19) and Biologic Therapy for Psoriasis: Successful Recovery in Two Patients After Infection with Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2)

The outbreak of the novel coronavirus known as SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2) causing COVID-19 was first reported in late December 2019. Many patients with psoriasis on biologic therapy have asked their medical providers about the effect of biologics on COVID-19. However, it is currently unknown how biologic therapy for psoriasis might impact patients with psoriasis and COVID-19. In this article, we report on the clinical course of two patients on biologic medication for psoriasis who developed COVID-19 and successfully recovered from SARS-CoV-2 infection. Both patients presented with fever and respiratory symptoms, but neither patient required hospitalization. While more research is needed, it is reassuring to know that successful recovery is possible after COVID-19 infection in patients on biologic therapy for psoriasis.

Independent Evaluation of the Respective Predictive Values for High-Grade Prostate Cancer of Clinical Information and RNA Biomarkers after Upfront MRI and Image-Guided Biopsies

Upfront MRI is taking the lead in the diagnosis of clinically significant prostate cancer, while few image-guided biopsies (IGBs) fail to demonstrate clinically significant prostate cancer. The added value of innovative biomarkers is not confirmed in this context. We analysed SelectMDx-v2 (MDx-2) in a cohort of upfront MRI and image-guided biopsy patients. Participants included patients who received a trans-rectal elastic-fusion registration IGB on the basis of DRE, PSA, PCA3, and PCPT-2.0 risk evaluation. Pre-biopsy MRI DICOM archives were reviewed according to PI-RADS-v2. Post-massage first-void urine samples stored in the institutional registered bio-repository were commercially addressed to MDxHealth to obtain MDx-2 scores. Univariate and multivariate analyses were conducted with the detection on IGB of high-grade (ISUP 2 and higher) as the dependent variable. High-grade cancer was demonstrated in 32/117 (27.4%) patients (8/2010-8/2018). Age, prostate volume, biopsy history, MDx-2, and PI-RADS-v2 scores significantly related to the detection of high-grade cancer. MDx-2 scores and the clinical variables embedded into MDx-2 scores were analysed in multivariate analysis to complement PI-RADS-v2 scores. The two combinations outperformed PI-RADS-v2 alone (AUC-ROC 0.67 vs. 0.73 and 0.80, respectively, p < 0.05) and calibration curves confirmed an adequate prediction. Similar discrimination (C-statistics, p = 0.22) was observed in the prediction of high-grade cancer, thereby questioning the respective inputs and added values of biomarkers and clinical predictors in MDx-2 scores. Based on the results of this study, we can conclude that instruments of prediction developed for systematic prostate biopsies, including those that incorporate innovative biomarkers, must be reassessed and eventually confirmed in the context of upfront MRI and IGB.