The challenge of clinical end points in sickle cell disease.

As most patients with sickle cell disease (SCD) do not have access to curative therapies, the availability of drug therapies that can modify disease severity remains highly desirable. Despite an increased understanding of the pathophysiology of SCD, only 4 drugs are approved by the US Food and Drugs Administration. Most drug trials in SCD have involved the use of acute pain episodes as the primary clinical end point. These studies have typically been to prevent or shorten the duration of such episodes. To date, no drug has received regulatory approval for shortening the duration of acute vaso-occlusive complications, likely highlighting the complex pathophysiology of acute pain episodes. Trials to prevent acute pain episodes have largely evaluated those episodes requiring health care use as a surrogate end point. However, with differences in culture and health care practices among countries, health care use may not reliably predict clinically important effects on acute pain episodes. This article discusses issues related to the use of health care use as the primary end point for prevention trials of acute pain episodes and highlights the importance of evaluating patient-reported outcomes as well as other SCD-related complications as outcome measures.

Soluble urokinase plasminogen activator receptor is associated with kidney disease and its progression in sickle cell anemia.

Not available.

Machine Learning Predicts Acute Kidney Injury in Hospitalized Patients with Sickle Cell Disease.

INTRODUCTION: Acute kidney injury (AKI) is common among hospitalized patients with sickle cell disease (SCD) and contributes to increased morbidity and mortality. Early identification and management of AKI is essential to preventing poor outcomes. We aimed to predict AKI earlier in patients with SCD using a machine-learning model that utilized continuous minute-by-minute physiological data. METHODS: A total of6,278 adult SCD patient encounters were admitted to inpatient units across five regional hospitals in Memphis, TN, over 3 years, from July 2017 to December 2020. From these, 1,178 patients were selected after filtering for data availability. AKI was identified in 82 (7%) patient encounters, using the 2012 Kidney Disease Improving Global Outcomes (KDIGO) criteria. The remaining 1,096 encounters served as controls. Features derived from five physiological data streams, heart rate, respiratory rate, and blood pressure (systolic, diastolic, and mean), captured every minute from bedside monitors were used. An XGBoost classifier was used for classification. RESULTS: Our model accurately predicted AKI up to 12 h before onset with an area under the receiver operator curve (AUROC) of 0.91 (95% CI [0.89-0.93]) and up to 48 h before AKI with an AUROC of 0.82 (95% CI [0.80-0.83]). Patients with AKI were more likely to be female (64.6%) and have history of hypertension, pulmonary hypertension, chronic kidney disease, and pneumonia than the control group. CONCLUSION: XGBoost accurately predicted AKI as early as 12 h before onset in hospitalized SCD patients and may enable the development of innovative prevention strategies.

Expert consensus on the management of infusion-related reactions (IRRs) in patients with sickle cell disease (SCD) receiving crizanlizumab: a RAND/UCLA modified Delphi panel.

Crizanlizumab, a monoclonal antibody against P-selectin, has been shown to reduce vaso-occlusive crises (VOCs) compared to placebo in patients ≥ 16 years with sickle cell disease (SCD). However, there have been rare reports of patients experiencing severe pain and subsequent complications within 24 hours of crizanlizumab infusions. These events are defined as infusion-related reactions (IRRs). Informed by current literature and clinical experience, a group of content experts developed clinical guidelines for the management of IRRs in patients with SCD. We used the RAND/University of California, Los Angeles (UCLA) modified Delphi panel method, a valid, reproducible technique for achieving consensus. We present our recommendations for managing IRRs, which depend on patient characteristics including: prior history of IRRs to other monoclonal antibodies or medications, changes to crizanlizumab infusion rate and patient monitoring, pain severity relative to patient's typical SCD crises, and severe allergic symptoms. These recommendations outline how to evaluate and manage IRRs in patients receiving crizanlizumab. Future research should validate this guidance using clinical data and identify patients at risk for these IRRs.

Hydroxyurea at escalated dose versus fixed low-dose hydroxyurea in adults with sickle cell disease.

Hydroxyurea reduces the frequency of vaso-occlusive complications, increases hemoglobin, and decreases mortality in sickle cell disease (SCD). Although current guidelines recommend escalation to maximum tolerated dose (MTD), the use of fixed low-dose hydroxyurea is common in low-resource countries. We conducted a systematic review and meta-analysis to evaluate the efficacy of escalated doses versus fixed low-dose of hydroxyurea in adults with SCD. Nine studies were included in the quantitative synthesis, four evaluating fixed low-dose and five evaluating escalated doses of hydroxyurea. Average daily doses of hydroxyurea in the fixed low-dose and escalated dose studies were ~10 and 22 mg/kg, respectively. There was no difference in the estimate of vaso-occlusive crisis rate between escalated and fixed low-dose studies (p = .73). The mean difference in hemoglobin from baseline to follow-up was greater for fixed low-dose than escalated dose studies (1.07 g/dL vs. 0.54 g/dL, p = .01). No difference was seen in the mean estimate of fetal hemoglobin. Despite limited eligible studies and substantial heterogeneity of effect between the studies for several outcomes, there appears to be clinical equipoise regarding the most appropriate hydroxyurea dosing regimen in adults with SCD. Controlled studies of hydroxyurea at MTD versus fixed low-dose in adults with SCD are required.

Comparative pharmacovigilance assessment of adverse events associated with the use of hydroxyurea, L-glutamine, voxelotor, and crizanlizumab in sickle cell disease.

Using disproportionality analysis, this study compared the adverse events (AEs) associated with the use of the new agents (e.g., L-glutamine, voxelotor, and crizanlizumab) to the commonly used medication, hydroxyurea, in sickle cell disease. We found that the most frequent drug-related AEs observed in this real-world study were consistent with those in the HOPE (voxelotor) and SUSTAIN (crizanlizumab) trials, but the rates of AEs were lower. Our study demonstrates that the most common AEs and symptoms of an increased risk associated with the individual drugs varied by treatment. Disproportionate reporting signals of drug-related AEs may also capture information that is independent of subjective measures of patient-reported symptoms. Our study highlights the important need for facilitating patient-physician communication in routine clinical care to understand patient-reported symptoms.

Kidney failure outcomes in children and young adults with sickle cell disease in the United States Renal Data System.

BACKGROUND: Children and young adults with sickle cell disease (SCD) develop kidney disease early in childhood, with some patients progressing to require dialysis and kidney transplantation. The prevalence and outcomes of children with kidney failure (chronic kidney disease stage 5) due to SCD are not well described. This study aimed to assess the outcome of children and young adults with SCD with kidney failure compared to matched children and young adults without SCD with kidney failure in a large national database. METHODS: Utilizing the United States Renal Data System (USRDS), we retrospectively examined kidney failure outcomes in children and young adults with SCD from 1998 to 2019. RESULTS: We identified 97 patients with SCD who developed kidney failure and identified 96 matched controls with a median age of 19 years (IQR 17, 21) at the time of kidney failure diagnosis. SCD patients had significantly shorter survival (8.4 years vs. 14.0 years, p < 0.001) and had a longer waiting time for their first transplant when compared to matched non-SCD kidney failure patients (12.1 years vs. 7.3 years, p < 0.001). CONCLUSIONS: Children and young adults with SCD kidney failure have significantly higher mortality when matched to non-SCD kidney failure children and experience a longer mean time to kidney transplant.

Urinary angiotensinogen is associated with albuminuria in adults with sickle cell anaemia.

We explored the association of novel urinary biomarkers with albumin-creatinine ratio (ACR) in adults with sickle cell anaemia. Of 37 participants, 13 (35.2%) had persistent albuminuria (PA). Urinary levels of clusterin (p = 0.002), retinol-binding protein 4 (p = 0.008), alpha-1 microglobulin (p = 0.002) and angiotensinogen (p = 0.006) were significantly higher in participants with PA than in those without PA. Although univariate analysis showed significant associations between both alpha-1 microglobulin (p = 0.035) and angiotensinogen (p = 0.0021) with ACR, only angiotensinogen was associated with ACR in multivariable analysis (p = 0.04). Our results suggest that urinary angiotensinogen may identify sickle cell anaemia patients at risk for kidney disease.

Age-related differences in risks and outcomes of 30-day readmission in adults with sickle cell disease.

BACKGROUND: Literature on 30-day readmission in adults with sickle cell disease (SCD) is limited. This study examined the overall and age-stratified rates, risk factors, and healthcare resource utilization associated with 30-day readmission in this population. METHODS: Using the Nationwide Readmissions Database, a retrospective cohort study was conducted to identify adult patients (aged ≥ 18) with SCD in 2016. Patients were stratified by age and followed for 30 days to assess readmission following an index discharge. The primary outcome was 30-day unplanned all-cause readmission. Secondary outcomes included index hospitalization costs and readmission outcomes (e.g., time to readmission, readmission costs, and readmission lengths of stay). Separate generalized linear mixed models estimated the adjusted odds ratios (aORs) for associations of readmission with patient and hospital characteristics, overall and by age. RESULTS: Of 15,167 adults with SCD, 2,863 (18.9%) experienced readmission. Both the rates and odds of readmission decreased with increasing age. The SCD complications vaso-occlusive crisis and end-stage renal disease (ESRD) were significantly associated with increased likelihood of readmission (p < 0.05). Age-stratified analyses demonstrated that diagnosis of depression significantly increased risk of readmission among patients aged 18-to-29 years (aOR = 1.537, 95%CI: 1.215-1.945) but not among patients of other ages. All secondary outcomes significantly differed by age (p < 0.05). CONCLUSION: This study demonstrates that patients with SCD are at very high risk of 30-day readmission and that younger adults and those with vaso-occlusive crisis and ESRD are among those at highest risk. Multifaceted, age-specific interventions targeting individuals with SCD on disease management are needed to prevent readmissions.

Evaluation of treatment patterns, healthcare resource utilization and cost of illness for sickle cell disease in Ghana: a private medical insurance claims database study.

BACKGROUND: Sickle cell disease (SCD) is a major public health concern in sub-Saharan Africa, accounting for nearly 75% of the global disease burden. The current analysis evaluated patient characteristics, treatment patterns, healthcare resource utilization (HCRU) and associated costs in patients with SCD based on a Private Medical Insurance Database in Ghana. METHODS: This retrospective longitudinal cohort study was conducted using an e-claims database from Ghana (01 January 2015 to 31 March 2021). Patients were stratified by age (0 month to < 2 years, ≥ 2 years to ˂6 years, ≥ 6 years to < 12 years, ≥ 12 years to < 16 years; ≥16 years), vaso-occlusive crisis (VOC) (< 1, ≥ 1 to < 3, and ≥ 3 per year), and continuous enrolment. Study outcomes related to patient characteristics, comorbidities, treatment pattern, HCRU were evaluated for pre- and post-index period (index period was between July 2015 to March 2020). Descriptive analysis was used to analyse different study variables. RESULTS: The study included 2,863 patients (mean age: 20.1 years; Min age: 0; Max age: 83; females 56.1%). Overall, 52.2% (n = 1,495) of SCD patients were ≥ 16 years and 17.0% (n = 486) were in the ≥ 2 to ˂6-years age group. The majority of patients aged ≥ 16 years (62.5%) in the database did not have reported VOC episodes, 35.9% of patients had 1 to 3 VOCs per year and 1.5% had ≥ 3 VOCs per year during the follow-up period. Consultation-based prevalence of SCD was 0.5% [95% confidence interval (CI): 0-1.3%] - 1.4% [CI: 0.6-2.2%]. Malaria, upper respiratory tract infection (URTI) and sepsis were the common complications of SCD. Analgesics were the most frequently prescribed medications followed by anti-infectives, hematinics, and antimalarials. Hydroxyurea, a routine standard of care for SCD was under-utilized. SCD patients had median cost incurred for consultation/hospital services of $11.3 (Interquartile range [IQR] $6.2 - $27.2). For patients with VOC, maximum median cost was incurred for medications ($10.9 [IQR $5.0-$32.6]). Overall median healthcare cost was highest for individuals with ≥ 3 VOCs per year during the follow-up period ($166.8 [IQR $70.3-$223.5]). CONCLUSION: In this retrospective private insurance claims database analysis, SCD imposes a significant healthcare burden, especially in patients with VOC. There is a need for reimbursed treatment options that could reduce the long-term burden associated with SCD and VOC.

A Phase 3 Randomized Trial of Voxelotor in Sickle Cell Disease.

BACKGROUND: Deoxygenated sickle hemoglobin (HbS) polymerization drives the pathophysiology of sickle cell disease. Therefore, direct inhibition of HbS polymerization has potential to favorably modify disease outcomes. Voxelotor is an HbS polymerization inhibitor. METHODS: In a multicenter, phase 3, double-blind, randomized, placebo-controlled trial, we compared the efficacy and safety of two dose levels of voxelotor (1500 mg and 900 mg, administered orally once daily) with placebo in persons with sickle cell disease. The primary end point was the percentage of participants who had a hemoglobin response, which was defined as an increase of more than 1.0 g per deciliter from baseline at week 24 in the intention-to-treat analysis. RESULTS: A total of 274 participants were randomly assigned in a 1:1:1 ratio to receive a once-daily oral dose of 1500 mg of voxelotor, 900 mg of voxelotor, or placebo. Most participants had sickle cell anemia (homozygous hemoglobin S or hemoglobin Sß0-thalassemia), and approximately two thirds were receiving hydroxyurea at baseline. In the intention-to-treat analysis, a significantly higher percentage of participants had a hemoglobin response in the 1500-mg voxelotor group (51%; 95% confidence interval [CI], 41 to 61) than in the placebo group (7%; 95% CI, 1 to 12). Anemia worsened between baseline and week 24 in fewer participants in each voxelotor dose group than in those receiving placebo. At week 24, the 1500-mg voxelotor group had significantly greater reductions from baseline in the indirect bilirubin level and percentage of reticulocytes than the placebo group. The percentage of participants with an adverse event that occurred or worsened during the treatment period was similar across the trial groups. Adverse events of at least grade 3 occurred in 26% of the participants in the 1500-mg voxelotor group, 23% in the 900-mg voxelotor group, and 26% in the placebo group. Most adverse events were not related to the trial drug or placebo, as determined by the investigators. CONCLUSIONS: In this phase 3 randomized, placebo-controlled trial involving participants with sickle cell disease, voxelotor significantly increased hemoglobin levels and reduced markers of hemolysis. These findings are consistent with inhibition of HbS polymerization and indicate a disease-modifying potential. (Funded by Global Blood Therapeutics; HOPE ClinicalTrials.gov number, NCT03036813.).

Enuresis and Hyperfiltration in Children With Sickle Cell Disease.

Nocturnal enuresis is a common symptom in children with sickle cell disease (SCD). Risk factors for development of enuresis are currently unknown. An early manifestation of SCD-associated kidney damage is glomerular hyperfiltration. We test the hypothesis that in a pediatric SCD cohort, individuals with hyperfiltration are more likely to have nocturnal enuresis when compared to children without hyperfiltration. To assess the relationship between nocturnal enuresis and hyperfiltration, we retrospectively evaluated children with SCD enrolled in the Evaluation of Nocturnal Enuresis and Barriers to Treatment among Pediatric Patients with SCD study and prospectively identified children who reported nocturnal enuresis and were enrolled in the longitudinal cohort study Sickle Cell Clinical Research and Intervention Program. Nocturnal enuresis occurred in 46.5% of Pediatric Patients with Sickle Cell Disease participants and was more frequent in participants with HbSS/HbSß 0 thalassemia and in male participants. We did not identify an association between hyperfiltration from 3 to 5 years of age with the later development of enuresis. Severe SCD genotypes and male sex were associated with nocturnal enuresis after age 5 years. We could not identify additional renal or hematologic predictors associated with the diagnosis of nocturnal enuresis. Future studies should incorporate nonrenal risk factors into studies that predict development of enuresis.

Longitudinal study of glomerular hyperfiltration and normalization of estimated glomerular filtration in adults with sickle cell disease.

Glomerular hyperfiltration is common in sickle cell disease (SCD) and precedes proteinuria and declining kidney function. We evaluated hyperfiltration in SCD patients and its "normalization." Routine visit data were collected retrospectively from adult SCD patients in a single centre from 2004 to 2013. Baseline was defined as first available serum creatinine and hyperfiltration as estimated glomerular filtration rates (eGFR) >130 ml/min/1·73 m2 for women and >140 ml/min/1·73 m2 for men. Normalization of hyperfiltration was eGFR reduction to 90-130 ml/min/1·73 m2 for women or 90-140 ml/min/1·73 m2 for men. Among 292 patients, median age was 27 years [interquartile range (IQR):20·0-38·0], and 56·8% had baseline hyperfiltration. Baseline hyperfiltration was inversely associated with age [odds ratio (OR):0·86, 95% confidence interval (CI): 0·82-0·90; P < 0·0001], male sex (OR:0·16, 95% CI: 0·07-0·41; P = 0·0001), haemoglobin (OR:0·76, 95% CI 0·61-0·94; P = 0·01), weight (OR:0·96, 95% CI: 0·93-0·99; P = 0·004), and angiotensin-converting enzyme inhibitor/angiotensin receptor blocker (ACE-I/ARB) use (OR:0·08, 95% CI: 0·01-0·75; P = 0·03), and positively with hydroxycarbamide use (OR:2·99, 95% CI: 1·18-7·56; P = 0·02). Of 89 hyperfiltration patients without baseline proteinuria, 10 (11·2%) developed new-onset proteinuria [median 1·05 years (IQR:0·63-2·09)]. Normalization of hyperfiltration was less likely with higher baseline eGFR [hazard ratio (HR):0·90, 95% CI: 0·86-0·95; P < 0·0001] and more likely in males (HR:6·35, 95% CI:2·71-14·86, <0·0001). Hyperfiltration is common in adult SCD patients, particularly when younger. Decline to normal values is more likely in males, possibly representing kidney function loss rather than improvement in hyperfiltration.

Generalization of a genetic risk score for time to first albuminuria in children with sickle cell anaemia: SCCRIP cohort study results.

Albuminuria predicts kidney disease progression in individuals with sickle cell anaemia (SCA); however, earlier prediction of kidney disease with introduction of reno-protective therapies prior to the onset of albuminuria may attenuate disease progression. A genetic risk score (GRS) for SCA-related nephropathy may provide an improved one-time test for early identification of high-risk patients. We utilized a GRS from a recent, large, trans-ethnic meta-analysis to identify three single nucleotide polymorphisms that associate individually and in a GRS with time to first albuminuria episode in children with SCA.

Red blood cells modulate structure and dynamics of venous clot formation in sickle cell disease.

Sickle cell disease (SCD) is associated with chronic activation of coagulation and an increased risk of venous thromboembolism. Erythrocyte sickling, the primary pathologic event in SCD, results in dramatic morphological changes in red blood cells (RBCs) because of polymerization of the abnormal hemoglobin. We used a mouse model of SCD and blood samples from sickle patients to determine if these changes affect the structure, properties, and dynamics of sickle clot formation. Sickling of RBCs and a significant increase in fibrin deposition were observed in venous thrombi formed in sickle mice. During ex vivo clot contraction, the number of RBCs extruded from sickle whole blood clots was significantly reduced compared with the number released from sickle cell trait and nonsickle clots in both mice and humans. Entrapment of sickled RBCs was largely factor XIIIa-independent and entirely mediated by the platelet-free cellular fraction of sickle blood. Inhibition of phosphatidylserine, but not administration of antisickling compounds, increased the number of RBCs released from sickle clots. Interestingly, whole blood, but not plasma clots from SCD patients, was more resistant to fibrinolysis, indicating that the cellular fraction of blood mediates resistance to tissue plasminogen activator. Sickle trait whole blood clots demonstrated an intermediate phenotype in response to tissue plasminogen activator. RBC exchange in SCD patients had a long-lasting effect on normalizing whole blood clot contraction. Furthermore, RBC exchange transiently reversed resistance of whole blood sickle clots to fibrinolysis, in part by decreasing platelet-derived PAI-1. These properties of sickle clots may explain the increased risk of venous thromboembolism observed in SCD.

Rapid decline in estimated glomerular filtration rate in sickle cell anemia: results of a multicenter pooled analysis.

Not available.

A pilot study of the effect of rivaroxaban in sickle cell anemia.

INTRODUCTION: The contribution of coagulation activation to the pathogenesis of sickle cell disease (SCD) remains incompletely defined. We evaluated the efficacy and safety of rivaroxaban, an oral direct factor Xa inhibitor, in subjects with sickle cell anemia. MATERIALS AND METHODS: In this pilot, single-center, randomized, double-blind, placebo-controlled, crossover study, eligible subjects with sickle cell anemia received rivaroxaban or placebo. The effect of rivaroxaban on coagulation activation, endothelial activation, inflammation, and microvascular blood flow was evaluated. RESULTS: Fourteen patients (HbSS - 14; females - 9) with mean age of 38 ± 10.6 years were randomized to receive rivaroxaban 20 mg daily or placebo for 4 weeks and, following a 2-week washout phase, were "crossed-over" to the treatment arm opposite to which they were initially assigned. Mean adherence to treatment with rivaroxaban, assessed by pill counts, was 85.6% in the first treatment period and 93.6% in the second period. Treatment with rivaroxaban resulted in a decrease from baseline of thrombin-antithrombin complex versus placebo (-34.4 ug/L [95% CI: -69.4, 0.53] vs. 0.35 ug/L [95% CI: -3.8, 4.5], p = .08), but the difference was not statistically significant. No significant differences were observed in changes from baseline of D-dimer, inflammatory, and endothelial activation markers or measures of microvascular blood flow. Rivaroxaban was well tolerated. CONCLUSIONS: Rivaroxaban was safe but did not significantly decrease coagulation activation, endothelial activation, or inflammation. Rivaroxaban did not improve microvascular blood flow. Adequately powered studies are required to further evaluate the efficacy of rivaroxaban in SCD. Clinicaltrials.gov Identifier: NCT02072668.

Transition care continuity promotes long-term retention in adult care among young adults with sickle cell disease.

BACKGROUND/OBJECTIVES: Care continuity prevents increased health care utilization and mortality during transition from pediatric to adult care. Our program employs a co-located care delivery model, in which pediatric provider involvement continues during young adulthood. We tested the hypothesis that individuals who participated in the co-located model have greater retention in adult care compared to those who only received pediatric transition services. METHODS: This study consisted of 311 youth with SCD (51.4% male; 63.0% HbSS/HbSß0 -thalassemia) who transferred to adult care from 2007 to 2017. Retention was defined as continuation with an adult provider for ≥12 or ≥24 months post-pediatric care. Logistic regression estimated the association between co-location status and retention at 12 and 24 months. Logistic regression and t-tests were used to evaluate potential predictors of retention in adult care. RESULTS: Individuals who participated in the co-location model were 1.9 times more likely to remain in adult care 12 (95% CI: 1.01, 3.47) and 24 (95% CI: 1.01, 3.70) months post-pediatric care compared to those who did not participate. Individuals with HbSS/HbSß0 -thalassemia were 1.9 times more likely to be retained at 12 months compared to those with HbSC/HbSß+ -thalassemia/HbS/HPFH (95% CI: 1.12, 3.09). For every clinic encounter in the last 2 years of pediatric care, the odds of being retained at least 24 months after initiating adult care increased 1.1 times (95% CI: 1.02, 1.13). CONCLUSIONS: Continuity of providers from pediatric to adult care may increase long-term retention in adult care. Longitudinal monitoring of adult outcomes is critical to identifying the efficacy of transition services.

Crizanlizumab for the Prevention of Pain Crises in Sickle Cell Disease.

BACKGROUND: The up-regulation of P-selectin in endothelial cells and platelets contributes to the cell-cell interactions that are involved in the pathogenesis of vaso-occlusion and sickle cell-related pain crises. The safety and efficacy of crizanlizumab, an antibody against the adhesion molecule P-selectin, were evaluated in patients with sickle cell disease. METHODS: In this double-blind, randomized, placebo-controlled, phase 2 trial, we assigned patients to receive low-dose crizanlizumab (2.5 mg per kilogram of body weight), high-dose crizanlizumab (5.0 mg per kilogram), or placebo, administered intravenously 14 times over a period of 52 weeks. Patients who were receiving concomitant hydroxyurea as well as those not receiving hydroxyurea were included in the study. The primary end point was the annual rate of sickle cell-related pain crises with high-dose crizanlizumab versus placebo. The annual rate of days hospitalized, the times to first and second crises, annual rates of uncomplicated crises (defined as crises other than the acute chest syndrome, hepatic sequestration, splenic sequestration, or priapism) and the acute chest syndrome, and patient-reported outcomes were also assessed. RESULTS: A total of 198 patients underwent randomization at 60 sites. The median rate of crises per year was 1.63 with high-dose crizanlizumab versus 2.98 with placebo (indicating a 45.3% lower rate with high-dose crizanlizumab, P=0.01). The median time to the first crisis was significantly longer with high-dose crizanlizumab than with placebo (4.07 vs. 1.38 months, P=0.001), as was the median time to the second crisis (10.32 vs. 5.09 months, P=0.02). The median rate of uncomplicated crises per year was 1.08 with high-dose crizanlizumab, as compared with 2.91 with placebo (indicating a 62.9% lower rate with high-dose crizanlizumab, P=0.02). Adverse events that occurred in 10% or more of the patients in either active-treatment group and at a frequency that was at least twice as high as that in the placebo group were arthralgia, diarrhea, pruritus, vomiting, and chest pain. CONCLUSIONS: In patients with sickle cell disease, crizanlizumab therapy resulted in a significantly lower rate of sickle cell-related pain crises than placebo and was associated with a low incidence of adverse events. (Funded by Selexys Pharmaceuticals and others; SUSTAIN ClinicalTrials.gov number, NCT01895361 .).

Using Machine Learning to Predict Early Onset Acute Organ Failure in Critically Ill Intensive Care Unit Patients With Sickle Cell Disease: Retrospective Study.

BACKGROUND: Sickle cell disease (SCD) is a genetic disorder of the red blood cells, resulting in multiple acute and chronic complications, including pain episodes, stroke, and kidney disease. Patients with SCD develop chronic organ dysfunction, which may progress to organ failure during disease exacerbations. Early detection of acute physiological deterioration leading to organ failure is not always attainable. Machine learning techniques that allow for prediction of organ failure may enable early identification and treatment and potentially reduce mortality. OBJECTIVE: The aim of this study was to test the hypothesis that machine learning physiomarkers can predict the development of organ dysfunction in a sample of adult patients with SCD admitted to intensive care units (ICUs). METHODS: We applied diverse machine learning methods, statistical methods, and data visualization techniques to develop classification models to distinguish SCD from controls. RESULTS: We studied 63 sequential SCD patients admitted to ICUs with 163 patient encounters (mean age 30.7 years, SD 9.8 years). A subset of these patient encounters, 22.7% (37/163), met the sequential organ failure assessment criteria. The other 126 SCD patient encounters served as controls. A set of signal processing features (such as fast Fourier transform, energy, and continuous wavelet transform) derived from heart rate, blood pressure, and respiratory rate was identified to distinguish patients with SCD who developed acute physiological deterioration leading to organ failure from patients with SCD who did not meet the criteria. A multilayer perceptron model accurately predicted organ failure up to 6 hours before onset, with an average sensitivity and specificity of 96% and 98%, respectively. CONCLUSIONS: This retrospective study demonstrated the viability of using machine learning to predict acute organ failure among hospitalized adults with SCD. The discovery of salient physiomarkers through machine learning techniques has the potential to further accelerate the development and implementation of innovative care delivery protocols and strategies for medically vulnerable patients.