Clinical Validation of the Vitro HPV Screening Assay for Its Use in Primary Cervical Cancer Screening.

Many scientific societies have issued guidelines to introduce population-based cervical cancer screening with HPV testing. The Vitro HPV Screening assay is a fully automatic multiplex real-time PCR test targeting the L1 GP5+/GP6+ region of HPV genome. The assay detects 14 high risk (HR) HPV genotypes, identifying individual HPV16 and HPV18 genotypes, and the HPV-positive samples for the other 12 HR HPV types are subsequently genotyped with the HPV Direct Flow Chip test. Following international guidelines, the aim of this study was to validate the clinical accuracy of the Vitro HPV Screening test on ThinPrep-collected samples for its use as primary cervical cancer screening, using as comparator the validated cobas® 4800 HPV test. The non-inferiority analysis showed that the clinical sensitivity and specificity of the Vitro HPV Screening assay for a diagnosis of cervical intraepithelial neoplasia of grade 2 or worse (CIN2+) were not inferior to those of cobas® 4800 HPV (p = 0.0049 and p < 0.001 respectively). The assay has demonstrated a high intra- and inter-laboratory reproducibility, also among the individual genotypes. The Vitro HPV Screening assay is valid for cervical cancer screening and it provides genotyping information on HPV-positive samples without further sample processing in a fully automated workflow.

Loss of the epithelial marker CDX1 predicts poor prognosis in early-stage CRC patients.

BACKGROUND: We have previously shown that non-curative chemotherapy imposes fetal conversion and high metastatic capacity to cancer cells. From the set of genes differentially expressed in Chemotherapy Resistant Cells, we obtained a characteristic fetal intestinal cell signature that is present in a group of untreated tumors and is sufficient to predict patient prognosis. A feature of this fetal signature is the loss of CDX1. METHODS: We have analyzed transcriptomic data in public datasets and performed immunohistochemistry analysis of paraffin embedded tumor samples from two cohorts of colorectal cancer patients. RESULTS: We demonstrated that low levels of CDX1 are sufficient to identify patients with poorest outcome at the early tumor stages II and III. Presence tumor areas that are negative for CDX1 staining in stage I cancers is associated with tumor relapse. CONCLUSIONS: Our results reveal the actual possibility of incorporating CDX1 immunostaining as a valuable biomarker for CRC patients.

Genomic classification and outcomes of young patients with polycythemia vera and essential thrombocythemia according to the presence of splanchnic vein thrombosis and its chronology.

To elucidate the role of splanchnic vein thrombosis (SVT) and genomic characteristics in prognosis and survival, we compared patients with polycythemia vera (PV) or essential thrombocythemia (ET) presenting SVT at diagnosis (n = 69, median age 43 years) or during follow-up (n = 21, median age 46 years) to a sex- and age-matched control group of PV/ET without SVT (n = 165, median age 48 years). The majority of patients presenting with SVT at diagnosis were classified as myeloproliferative neoplasm with heterozygous JAK2 mutation (87% of cases vs. 69% in PV/ET control group, p < 0.05), characterized by low JAK2 allele burden and no high-risk mutations. Despite this lower molecular complexity, patients presenting with SVT showed a higher risk of death (HR 3.0, 95% CI 1.5-6.0, p = 0.003) and lower event-free survival (HR 3.0, 95% CI 1.9-4.8, p < 0.001) than age- and sex-matched PV/ET controls. In patients presenting with SVT, molecular high-risk was associated with increased risk of venous re-thrombosis (HR 5.8, 95% CI 1.4-24.0, p = 0.01). Patients developing SVT during follow-up were more frequently allocated in molecular high-risk than those with SVT at diagnosis (52% versus 13%, p < 0.05). In the whole cohort of patients, molecular classification identified PV/ET patients at higher risk of disease progression whereas DNMT3A/TET2/ASXL1 mutations were associated with higher risk of arterial thrombosis. In conclusion, clinical and molecular characteristics are different in PV/ET patients with SVT, depending on whether it occurs at diagnosis or at follow-up. Molecular characterization by NGS is useful for assessing the risk of thrombosis and disease progression in young patients with PV/ET.

Cell-Free DNA as a Biomarker at Diagnosis and Follow-Up in 256 B and T-Cell Lymphomas.

BACKGROUND: Cell-free DNA (cfDNA) analysis has become a promising tool for the diagnosis, prognosis, and monitoring of lymphoma cases. Until now, research in this area has mainly focused on aggressive lymphomas, with scanty information from other lymphoma subtypes. METHODS: We selected 256 patients diagnosed with lymphomas, including a large variety of B-cell and T-cell non-Hodgkin and Hodgkin lymphomas, and quantified cfDNA from plasma at the time of diagnosis. We further selected 49 large B-cell lymphomas (LBCL) and analyzed cfDNA levels at diagnosis (pre-therapy) and after therapy. In addition, we performed NGS on cfDNA and tissue in this cohort of LBCL. RESULTS: Lymphoma patients showed a statistically significant higher cfDNA concentration than healthy controls (mean 53.0 ng/mL vs. 5.6 ng/mL, p < 0.001). The cfDNA concentration was correlated with lymphoma subtype, lactate dehydrogenase, the International Prognostic Index (IPI) score, Ann Arbor (AA), and B-symptoms. In 49 LBCL cases, the cfDNA concentration decreased after therapy in cases who achieved complete response (CR) and increased in non-responders. The median cfDNA at diagnosis of patients who achieved CR and later relapsed was higher (81.5 ng/mL) compared with levels of those who did not (38.6 ng/mL). A concordance of 84% was observed between NGS results in tumor and cfDNA samples. Higher VAF in cfDNA is correlated with advanced stage and bulky disease. CONCLUSIONS: cfDNA analysis can be easily performed in almost all lymphoma cases. The cfDNA concentration correlated with the characteristics of the aggressiveness of the lymphomas and, in LBCL, with the response achieved after therapy. These results support the utility of cfDNA analysis as a complementary tool in the management of lymphoma patients.

The prognostic impact of non-driver gene mutations and variant allele frequency in primary myelofibrosis.

Prognostic impact of non-MPN driver gene mutations in primary myelofibrosis. MIPSS70: Mutation-Enhanced International Prognostic Score System.

Are Cutibacterium acnes delivered from skin to deep tissues in primary reverse shoulder arthroplasty? A prospective study.

INTRODUCTION: The objective of this study is to determine whether the deep tissues are inoculated during surgery with the Cutibacterium acnes still present in the skin after the surgical preparation in reverse shoulder arthroplasties. MATERIALS AND METHODS: Prospective study including patients undergoing surgery with reverse shoulder arthroplasty. All the patients received preoperative antibiotic prophylaxis with cefazolin (2 g IV) and the skin was prepared with 2% chlorhexidine gluconate and 70% isopropyl alcohol. From all the patients, 9 cultures were obtained after the antibiotic was administrated and the skin surgically prepared. The cultures were sent to isolate C. acnes. DNA was extracted from the C. acnes isolated colonies. Isolate nucleotide distances were calculated using the Genome-based distance matrix calculator from the Enveomics collection toolbox. RESULTS: The study included 90 patients. C. acnes was isolated in 24 patients (26.6%) with a total of 61 positive cultures. There were 12 phylotype II, 27 IB and 22 IA. In 9 patients, C. acnes was present in both skin and deep tissues, and they constituted the sample to be studied by means of genomic analysis. In 7 out of the 9 patients, deep tissue samples clustered closer to at least one of its corresponding skin isolates when compared to the other independent bacterial ones. CONCLUSIONS: The C. acnes present in the skin at the beginning of the surgery are the same as those found in the deep tissues at the end of the surgery. This result strengthens the possibility that the C. acnes is delivered from the skin to the deep tissues.

High-throughput RNA sequencing of the T cell receptor alpha and beta chains for simultaneous clonality and biological analyses in Sezary syndrome.

BACKGROUND: Previous investigations pointed out a role for antigen stimulation in Sezary syndrome (SS). High-throughput sequencing of the T cell receptor (TR) offers several applications beyond diagnostic purposes, including the study of T cell pathogenesis. METHODS: We performed high-throughput RNA sequencing of the TR alpha (TRA) and beta (TRB) genes focusing on the complementarity-determining region 3 (CDR3) in 11 SS and one erythrodermic mycosis fungoides (MF) patients. Five psoriasis patients were employed as controls. Peripheral blood CD4+ cells were isolated and RNA sequenced (HiSeq2500). High-resolution HLA typing was performed in neoplastic patients. RESULTS: Highly expanded predominant TRA and TRB CDR3 were only found in SS patients (median frequency: 94.4% and 93.7%). No remarkable CDR3 expansions were observed in psoriasis patients (median frequency of predominant TRA and TRB CDR3: 0.87% and 0.69%, p < 0.001 compared to SS). CDR3 almost identical to the predominant were identified within each SS patient and were exponentially correlated with frequencies of the predominant CDR3 (R2 = 0.918, p < 0.001). Forty-six different CDR3 were shared between SS patients displaying HLA similarities, including predominant TRA and TRB CDR3 in one patient that were found in other three patients. Additionally, 351 antigen matches were detected (Cytomegalovirus, Epstein-Barr, Influenza virus, and self-antigens), and the predominant CDR3 of two different SS patients matched CDR3 with specificity for Influenza and Epstein-Barr viruses. CONCLUSIONS: Besides detecting clonality, these findings shed light on the nature of SS-related antigens, pointing to RNA sequencing as a useful tool for simultaneous clonality and biological analysis in SS.

NLRP3 inflammasome activation and symptom burden in KRAS-mutated CMML patients is reverted by IL-1 blocking therapy.

Chronic myelomonocytic leukemia (CMML) is frequently associated with mutations in the rat sarcoma gene (RAS), leading to worse prognosis. RAS mutations result in active RAS-GTP proteins, favoring myeloid cell proliferation and survival and inducing the NLRP3 inflammasome together with the apoptosis-associated speck-like protein containing a caspase recruitment domain (ASC), which promote caspase-1 activation and interleukin (IL)-1ß release. Here, we report, in a cohort of CMML patients with mutations in KRAS, a constitutive activation of the NLRP3 inflammasome in monocytes, evidenced by ASC oligomerization and IL-1ß release, as well as a specific inflammatory cytokine signature. Treatment of a CMML patient with a KRASG12D mutation using the IL-1 receptor blocker anakinra inhibits NLRP3 inflammasome activation, reduces monocyte count, and improves the patient's clinical status, enabling a stem cell transplant. This reveals a basal inflammasome activation in RAS-mutated CMML patients and suggests potential therapeutic applications of NLRP3 and IL-1 blockers.

MultiCOVID: a multi modal deep learning approach for COVID-19 diagnosis.

The rapid spread of the severe acute respiratory syndrome coronavirus 2 led to a global overextension of healthcare. Both Chest X-rays (CXR) and blood test have been demonstrated to have predictive value on Coronavirus Disease 2019 (COVID-19) diagnosis on different prevalence scenarios. With the objective of improving and accelerating the diagnosis of COVID-19, a multi modal prediction algorithm (MultiCOVID) based on CXR and blood test was developed, to discriminate between COVID-19, Heart Failure and Non-COVID Pneumonia and healthy (Control) patients. This retrospective single-center study includes CXR and blood test obtained between January 2017 and May 2020. Multi modal prediction models were generated using opensource DL algorithms. Performance of the MultiCOVID algorithm was compared with interpretations from five experienced thoracic radiologists on 300 random test images using the McNemar-Bowker test. A total of 8578 samples from 6123 patients (mean age 66 ± 18 years of standard deviation, 3523 men) were evaluated across datasets. For the entire test set, the overall accuracy of MultiCOVID was 84%, with a mean AUC of 0.92 (0.89-0.94). For 300 random test images, overall accuracy of MultiCOVID was significantly higher (69.6%) compared with individual radiologists (range, 43.7-58.7%) and the consensus of all five radiologists (59.3%, P < .001). Overall, we have developed a multimodal deep learning algorithm, MultiCOVID, that discriminates among COVID-19, heart failure, non-COVID pneumonia and healthy patients using both CXR and blood test with a significantly better performance than experienced thoracic radiologists.

Comprehensive NGS profiling to enable detection of ALK gene rearrangements and MET amplifications in non-small cell lung cancer.

Introduction: Next-generation sequencing (NGS) is currently widely used for biomarker studies and molecular profiling to identify concurrent alterations that can lead to the better characterization of a tumor's molecular landscape. However, further evaluation of technical aspects related to the detection of gene rearrangements and copy number alterations is warranted. Methods: There were 12 ALK rearrangement-positive tumor specimens from patients with non-small cell lung cancer (NSCLC) previously detected via fluorescence in situ hybridization (FISH), immunohistochemistry (IHC), and an RNA-based NGS assay, and 26 MET high gene copy number (GCN) cases detected by FISH, selected for this retrospective study. All 38 pre-characterized cases were reassessed utilizing the PGDx™ elio™ tissue complete assay, a 505 gene targeted NGS panel, to evaluate concordance with these conventional diagnostic techniques. Results: The detection of ALK rearrangements using the DNA-based NGS assay demonstrated excellent sensitivity with the added benefit of characterizing gene fusion partners and genomic breakpoints. MET copy number alterations were also detected; however, some discordances were observed likely attributed to differences in algorithm, reporting thresholds and gene copy number state. TMB was also assessed by the assay and correlated to the presence of NSCLC driver alterations and was found to be significantly lower in cases with NGS-confirmed canonical driver mutations compared with those without (p=0.0019). Discussion: Overall, this study validates NGS as an accurate approach for detecting structural variants while also highlighting the need for further optimization to enable harmonization across methodologies for amplifications.

Leukemic Involvement Is a Common Feature in Waldenström Macroglobulinemia at Diagnosis.

Waldenström Macroglobulinemia (WM) is a lymphoplasmacytic lymphoma with bone marrow (BM) involvement and IgM monoclonal gammopathy. To date, no studies have focused specifically on peripheral blood (PB) involvement. In this study, 100 patients diagnosed with WM according to the World Health Organization (WHO) criteria were included based on the demonstration of MYD88mut in BM and the availability of PB multiparametric flow cytometry (MFC) analysis. Leukemic involvement by MFC was detected in 50/100 patients. A low percentage of mature small lymphocytes in PB smears was observed in only 15 cases. MYD88mut by AS-qPCR was detected in PB in 65/100 cases. In cases with leukemic expression by MFC, MYD88mut was detected in all cases, and IGH was rearranged in 44/49 cases. In 21/50 patients without PB involvement by MFC, molecular data were consistent with circulating disease (MYD88mut by AS-qPCR 3/50, IGH rearranged 6/50, both 12/50). Therefore, PB involvement by standard techniques was detected in 71/100 patients. MYD88mut was detected in PB by dPCR in 9/29 triple negative cases. Overall, 80% of the patients presented PB involvement by any technique. Our findings support the role of PB MFC in the evaluation of patients with IgM monoclonal gammopathy and provide reliable information on correlation with molecular features. The development of a feasible MFC assay may stand as an objective tool in the classification of mature B cell neoplasms presenting with IgM monoclonal gammopathy.

Y-chromosome in the olfactory neuroepithelium as a potential biomarker of depression in women with male offspring: an exploratory study.

The persistence of fetal cells in the mother (fetal microchimerism (FMc)) has been described in maternal tissues essential to the newborn. FMc is associated with several diseases that start or worsen in pregnancy or postpartum. This exploratory study reports-for the first time-the presence of FMc in the olfactory neuroepithelium (ON) of both healthy and depressed women with male offspring. However, depressed women had fewer microchimeric cells (digital PCR). The existence of FMc in the ON could facilitate mother-child bonding. These findings open new pathways to study FMc in the ON, female depression, and mother-child bonding.

Automated quantification of stromal tumour infiltrating lymphocytes is associated with prognosis in breast cancer.

Stromal tumour infiltrating lymphocytes (sTIL) in haematoxylin and eosin (H&E) stained sections has been linked to better outcomes and better responses to neoadjuvant therapy in triple-negative and HER2-positive breast cancer (TNBC and HER2 +). However, the infiltrate includes different cell populations that have specific roles in the tumour immune microenvironment. Various studies have found high concordance between sTIL visual quantification and computational assessment, but specific data on the individual prognostic impact of plasma cells or lymphocytes within sTIL on patient prognosis is still unknown. In this study, we validated a deep-learning breast cancer sTIL scoring model (smsTIL) based on the segmentation of tumour cells, benign ductal cells, lymphocytes, plasma cells, necrosis, and 'other' cells in whole slide images (WSI). Focusing on HER2 + and TNBC patient samples, we assessed the concordance between sTIL visual scoring and the smsTIL in 130 WSI. Furthermore, we analysed 175 WSI to correlate smsTIL with clinical data and patient outcomes. We found a high correlation between sTIL values scored visually and semi-automatically (R = 0.76; P = 2.2e-16). Patients with higher smsTIL had better overall survival (OS) in TNBC (P = 0.0021). In the TNBC cohort, smsTIL was as an independent prognostic factor for OS. As part of this work, we introduce a new segmentation dataset of H&E-stained WSI.

Characterization and spatial distribution of the immune cell infiltrate in triple-negative breast cancer: a novel classification based on plasma cells and CD8+ T cells.

Stromal tumor-infiltrating lymphocytes (sTILs) are a robust prognostic and predictive biomarker in triple-negative breast carcinoma. However, the sTIL compartment comprises different cell populations. The aim of the study is to characterize the distribution of T cells (CD3+ and CD8+), B cells, and plasma cells and explore their association with outcome in the surgical specimen of 62 patients. Furthermore, programmed death ligand 1 expression and the presence of tertiary lymphoid structures (TLSs) are explored. Patients with higher sTILs achieve better progression-free survival (PFS) (P = .0013), and tumors have more plasma cells in the infiltrate. Specifically, higher counts of T cells (both CD3+ and CD8+) have better PFS (P = .002 and P = .0086, respectively) as it is observed in tumors with higher infiltration of CD8+ T cells in the tumor core (P = .035). Higher infiltration by B cells and plasma cells shows a positive tendency toward increased PFS (P = .06 and P = .058). Programmed death ligand 1 (SP142) is positive in 56% of tumors. Tumors with at least 1 TLS (42%) show higher CD8+ T cell infiltration in the tumor core and the sTIL value doubles compared to tumors devoid of TLSs [sTIL mean: 36 ± 11% and 18 ± 5% (CI [Confidence Interval]: 95%), respectively]. Our study demonstrates that the characterization of the immune cell infiltration is as relevant as its distribution. Moreover, the importance of considering different immune cell types for classification is emphasized. Therefore, a new classification of triple-negative breast carcinoma immune infiltration with CD8+ T cell and plasma cell densities in the tumor core and infiltrative margin is proposed.

Pre-existing tumor host immunity characterization in resected non-small cell lung cancer.

INTRODUCTION: Neoadjuvant and adjuvant immune checkpoint blockade (ICB) have recently become standard of care in resectable non-small cell lung cancer (NSCLC). Yet, biomarkers that inform patients who benefit from this approach remain largely unknown. Here, we interrogated the tumor immune microenvironment (TIME) in early-stage NSCLC patients that underwent up-front surgery. METHODS: A total of 185 treatment-naïve patients with early-stage NSCLC, that underwent up-front surgical treatment between 2006 and 2018 at Hospital del Mar were included. 124 lung adenocarcinomas (LUADs), and 61 squamous cell carcinoma (LUSCs) were included in a tissue microarray. Immunohistochemistry for CD3, CD4, CD8, CD68, CD80, CD103, FOXP3, PD-1, PD-L1, PD-L2 and HLA class II were evaluated by digital image analysis (QuPath software). TIME was categorized into four groups using PD-L1 expression in tumor cells (<1 % or ≥1 %) and tumor resident memory (CD103+) immune cells (using the median as cut-off). We explored the association between different TIME dimensions and patient's clinicopathological features and outcomes. RESULTS: We found increased levels of T cell markers (CD3+, CD4+, CD8+ cells), functional immune markers (FOXP3+ cells) as well as, higher HLA-II tumor membrane expression in LUADs compared to LUSCs (p < 0.05 for all). In contrast, LUSCs displayed higher percentage of intratumor macrophages (CD68+ cells) as well as, higher PD-L1 and PD-L2 tumor membrane expression (p < 0.05 for all). Unsupervised analysis revealed three different tumor subsets characterized by membrane tumor expression of PD-L1, PD-L2 and HLA-class II. Enrichment of T cells (CD3+, CD8+ cells), regulatory T cells (FOXP3+ cells) and macrophages (CD68+ cells) was observed in the CD103+/PD-L1+ group (p < 0.05 for all). Multivariate analysis showed that infiltration by CD103+ immune cells was associated with improved OS (p = 0.009). CONCLUSIONS: TIME analysis in resected NSCLC highlighted differences by histology, PD-L1 expression and molecular subgroups. Biomarker studies using IHC might aid to individually tailor adjuvant treatment in early-stage NSCLC.

Characterization of genetic variants in the EGLN1/PHD2 gene identified in a European collection of patients with erythrocytosis.

Hereditary erythrocytosis is a rare hematologic disorder characterized by an excess of red blood cell production. Here we describe a European collaborative study involving a collection of 2,160 patients with erythrocytosis sequenced in ten different laboratories. We focused our study on the EGLN1 gene and identified 39 germline missense variants including one gene deletion in 47 probands. EGLN1 encodes the PHD2 prolyl 4-hydroxylase, a major inhibitor of hypoxia-inducible factor. We performed a comprehensive study to evaluate the causal role of the identified PHD2 variants: (i) in silico studies of localization, conservation, and deleterious effects; (ii) analysis of hematologic parameters of carriers identified in the UK Biobank; (iii) functional studies of the protein activity and stability; and (iv) a comprehensive study of PHD2 splicing. Altogether, these studies allowed the classification of 16 pathogenic or likely pathogenic mutants in a total of 48 patients and relatives. The in silico studies extended to the variants described in the literature showed that a minority of PHD2 variants can be classified as pathogenic (36/96), without any differences from the variants of unknown significance regarding the severity of the developed disease (hematologic parameters and complications). Here, we demonstrated the great value of federating laboratories working on such rare disorders in order to implement the criteria required for genetic classification, a strategy that should be extended to all hereditary hematologic diseases.

Gal-1 Expression Analysis in the GLIOCAT Multicenter Study: Role as a Prognostic Factor and an Immune-Suppressive Biomarker.

Glioblastoma (GBM) is the most frequent primary malignant brain tumor and has a dismal prognosis. Unfortunately, despite the recent revolution of immune checkpoint inhibitors in many solid tumors, these have not shown a benefit in overall survival in GBM patients. Therefore, new potential treatment targets as well as diagnostic, prognostic, and/or predictive biomarkers are needed to improve outcomes in this population. The ß-galactoside binding protein Galectin-1 (Gal-1) is a protein with a wide range of pro-tumor functions such as proliferation, invasion, angiogenesis, and immune suppression. Here, we evaluated Gal-1 expression by immunohistochemistry in a homogenously treated cohort of GBM (the GLIOCAT project) and correlated its expression with clinical and molecular data. We observed that Gal-1 is a negative prognostic factor in GBM. Interestingly, we observed higher levels of Gal-1 expression in the mesenchymal/classical subtypes compared to the less aggressive proneural subtype. We also observed a Gal-1 expression correlation with immune suppressive signatures of CD4 T-cells and macrophages, as well as with several GBM established biomarkers, including SHC1, PD-L1, PAX2, MEOX2, YKL-40, TCIRG1, YWHAG, OLIG2, SOX2, Ki-67, and SOX11. Moreover, Gal-1 levels were significantly lower in grade 4 IDH-1 mutant astrocytomas, which have a better prognosis. Our results confirm the role of Gal-1 as a prognostic factor and also suggest its value as an immune-suppressive biomarker in GBM.

Evaluation of the host immune response assay SeptiCyte RAPID for potential triage of COVID-19 patients.

Tools for the evaluation of COVID-19 severity would help clinicians with triage decisions, especially the decision whether to admit to ICU. The aim of this study was to evaluate SeptiCyte RAPID, a host immune response assay (Immunexpress, Seattle USA) as a triaging tool for COVID-19 patients requiring hospitalization and potentially ICU care. SeptiCyte RAPID employs a host gene expression signature consisting of the ratio of expression levels of two immune related mRNAs, PLA2G7 and PLAC8, measured from whole blood samples. Blood samples from 146 adult SARS-CoV-2 (+) patients were collected within 48 h of hospital admission in PAXgene blood RNA tubes at Hospital del Mar, Barcelona, Spain, between July 28th and December 1st, 2020. Data on demographics, vital signs, clinical chemistry parameters, radiology, interventions, and SeptiCyte RAPID were collected and analyzed with bioinformatics methods. The performance of SeptiCyte RAPID for COVID-19 severity assessment and ICU admission was evaluated, relative to the comparator of retrospective clinical assessment by the Hospital del Mar clinical care team. In conclusion, SeptiCyte RAPID was able to stratify COVID-19 cases according to clinical severity: critical vs. mild (AUC = 0.93, p < 0.0001), critical vs. moderate (AUC = 0.77, p = 0.002), severe vs. mild (AUC = 0.85, p = 0.0003), severe vs. moderate (AUC = 0.63, p = 0.05). This discrimination was significantly better (by AUC or p-value) than could be achieved by CRP, lactate, creatine, IL-6, or D-dimer. Some of the critical or severe cases had "early" blood draws (before ICU admission; n = 33). For these cases, when compared to moderate and mild cases not in ICU (n = 37), SeptiCyte RAPID had AUC = 0.78 (p = 0.00012). In conclusion, SeptiCyte RAPID was able to stratify COVID-19 cases according to clinical severity as defined by the WHO COVID-19 Clinical Management Living Guidance of January 25th, 2021. Measurements taken early (before a patient is considered for ICU admission) suggest that high SeptiScores could aid in predicting the need for later ICU admission.

Machine Learning Improves Risk Stratification in Myelofibrosis: An Analysis of the Spanish Registry of Myelofibrosis.

Myelofibrosis (MF) is a myeloproliferative neoplasm (MPN) with heterogeneous clinical course. Allogeneic hematopoietic cell transplantation remains the only curative therapy, but its morbidity and mortality require careful candidate selection. Therefore, accurate disease risk prognostication is critical for treatment decision-making. We obtained registry data from patients diagnosed with MF in 60 Spanish institutions (N = 1386). These were randomly divided into a training set (80%) and a test set (20%). A machine learning (ML) technique (random forest) was used to model overall survival (OS) and leukemia-free survival (LFS) in the training set, and the results were validated in the test set. We derived the AIPSS-MF (Artificial Intelligence Prognostic Scoring System for Myelofibrosis) model, which was based on 8 clinical variables at diagnosis and achieved high accuracy in predicting OS (training set c-index, 0.750; test set c-index, 0.744) and LFS (training set c-index, 0.697; test set c-index, 0.703). No improvement was obtained with the inclusion of MPN driver mutations in the model. We were unable to adequately assess the potential benefit of including adverse cytogenetics or high-risk mutations due to the lack of these data in many patients. AIPSS-MF was superior to the IPSS regardless of MF subtype and age range and outperformed the MYSEC-PM in patients with secondary MF. In conclusion, we have developed a prediction model based exclusively on clinical variables that provides individualized prognostic estimates in patients with primary and secondary MF. The use of AIPSS-MF in combination with predictive models that incorporate genetic information may improve disease risk stratification.