Surveying haemoperfusion impact on COVID-19 from machine learning using Shapley values.

BACKGROUND: Haemoperfusion (HP) is an innovative extracorporeal therapy that utilizes special cartridges to filter the blood, effectively removing pro-inflammatory cytokines, toxins, and pathogens in COVID-19 patients. This retrospective cohort study aimed to assess the clinical benefits of HP for severe COVID-19 cases using Shapley values for machine learning models. METHODS: The research involved 578 inpatients (≥ 20 years old) admitted to Baqiyatallah hospital (Tehran, Iran). The control group (359 patients) received standard treatment, including high doses of corticosteroids (a single 500 mg methylprednisolone pulse, followed by 250 mg for 2 days), categorized as regimen (I). On the other hand, the HP group (219 patients) received regimen II, consisting of the same corticosteroid treatment (regimen I) along with haemoperfusion using Cytosorb H300. The frequency of haemoperfusion sessions varied based on the type of lung involvement determined by chest CT scans. In addition, the value function v defines the Shapley value of the i th feature for the query point x , where the input matrix features represent individual characteristics, drugs, and history and clinical conditions of the patient. RESULTS: Our data showed a favorable clinical response in the HP group compared to the control group. Notably, one-to-three sessions of HP using the CytoSorb® 300 cartridge led to reduced ventilation requirements and mortality rates in severe COVID-19 patients. Shapley values were calculated to evaluate the contribution of haemoperfusion among other factors, such as side effects, medications, and individual characteristics, to COVID-19 patient outcomes. In addition, there is a significant difference between the two groups among the treatments and medications used remdesivir, adalimumab, tocilizumab, favipiravir, Interferon beta-1a, enoxaparin prophylaxis, enoxaparin full dose, heparin prophylaxis, and heparin full dose (P < 0.05). It seems that haemoperfusion has a positive impact on the reduction of inflammation markers and renal functional such as ferritin and creatinine, respectively, as well as D-dimer and WBC levels in the HP group were significantly lower than the control group. CONCLUSION: The findings indicated that haemoperfusion played a crucial role in predicting patient survival, making it a significant feature in classifying patients' prognoses.

A Prospective Study on Risk Factors for Acute Kidney Injury and All-Cause Mortality in Hospitalized COVID-19 Patients From Tehran (Iran).

Background: Several reports suggested that acute kidney injury (AKI) is a relatively common occurrence in hospitalized COVID-19 patients, but its prevalence is inconsistently reported across different populations. Moreover, it is unknown whether AKI results from a direct infection of the kidney by SARS-CoV-2 or it is a consequence of the physiologic disturbances and therapies used to treat COVID-19. We aimed to estimate the prevalence of AKI since it varies by geographical settings, time periods, and populations studied and to investigate whether clinical information and laboratory findings collected at hospital admission might influence AKI incidence (and mortality) in a particular point in time during hospitalization for COVID-19. Methods: Herein we conducted a prospective longitudinal study investigating the prevalence of AKI and associated factors in 997 COVID-19 patients admitted to the Baqiyatallah general hospital of Tehran (Iran), collecting both clinical information and several dates (of: birth; hospital admission; AKI onset; ICU admission; hospital discharge; death). In order to examine how the clinical factors influenced AKI incidence and all-cause mortality during hospitalization, survival analysis using the Cox proportional-hazard models was adopted. Two separate multiple Cox regression models were fitted for each outcome (AKI and death). Results: In this group of hospitalized COVID-19 patients, the prevalence of AKI was 28.5% and the mortality rate was 19.3%. AKI incidence was significantly enhanced by diabetes, hyperkalemia, higher levels of WBC count, and blood urea nitrogen (BUN). COVID-19 patients more likely to die over the course of their hospitalization were those presenting a joint association between ICU admission with either severe COVID-19 or even mild/moderate COVID-19, hypokalemia, and higher levels of BUN, WBC, and LDH measured at hospital admission. Diabetes and comorbidities did not increase the mortality risk among these hospitalized COVID-19 patients. Conclusions: Since the majority of patients developed AKI after ICU referral and 40% of them were admitted to ICU within 2 days since hospital admission, these patients may have been already in critical clinical conditions at admission, despite being affected by a mild/moderate form of COVID-19, suggesting the need of early monitoring of these patients for the onset of eventual systemic complications.