Unlocking the complete blood count as a risk stratification tool for breast cancer using machine learning: a large scale retrospective study.

Optimizing early breast cancer (BC) detection requires effective risk assessment tools. This retrospective study from Brazil showcases the efficacy of machine learning in discerning complex patterns within routine blood tests, presenting a globally accessible and cost-effective approach for risk evaluation. We analyzed complete blood count (CBC) tests from 396,848 women aged 40-70, who underwent breast imaging or biopsies within six months after their CBC test. Of these, 2861 (0.72%) were identified as cases: 1882 with BC confirmed by anatomopathological tests, and 979 with highly suspicious imaging (BI-RADS 5). The remaining 393,987 participants (99.28%), with BI-RADS 1 or 2 results, were classified as controls. The database was divided into modeling (including training and validation) and testing sets based on diagnostic certainty. The testing set comprised cases confirmed by anatomopathology and controls cancer-free for 4.5-6.5 years post-CBC. Our ridge regression model, incorporating neutrophil-lymphocyte ratio, red blood cells, and age, achieved an AUC of 0.64 (95% CI 0.64-0.65). We also demonstrate that these results are slightly better than those from a boosting machine learning model, LightGBM, plus having the benefit of being fully interpretable. Using the probabilistic output from this model, we divided the study population into four risk groups: high, moderate, average, and low risk, which obtained relative ratios of BC of 1.99, 1.32, 1.02, and 0.42, respectively. The aim of this stratification was to streamline prioritization, potentially improving the early detection of breast cancer, particularly in resource-limited environments. As a risk stratification tool, this model offers the potential for personalized breast cancer screening by prioritizing women based on their individual risk, thereby indicating a shift from a broad population strategy.

Image dataset of urine test results on petri dishes for deep learning classification.

Recent advancements in image analysis and interpretation technologies using computer vision techniques have shown potential for novel applications in clinical microbiology laboratories to support task automation aiming for faster and more reliable diagnostics. Deep learning models can be a valuable tool in the screening process, helping technicians spend less time classifying no-growth results and quickly separating the categories of tests that deserve further analysis. In this context, creating datasets with correctly classified images is fundamental for developing and improving such models. Therefore, a dataset of urine test Petri dishes images was collected following a standardized process, with controlled conditions of positioning and lighting. Image acquisition was conducted by applying a hardware chamber equipped with a led lightning source and a smartphone camera with 12 MP resolution. A software application was developed to support image classification and handling. Experienced microbiologists classified the images according to the positive, negative, and uncertain test results. The resulting dataset contains a total of 1500 images and can support the development of deep learning algorithms to classify urine exams according to their microbial growth.

The Anti-Tumor Effects of Adipose Tissue Mesenchymal Stem Cell Transduced with HSV-Tk Gene on U-87-Driven Brain Tumor.

Glioblastoma (GBM) is an infiltrative tumor that is difficult to eradicate. Treating GBM with mesenchymal stem cells (MSCs) that have been modified with the HSV-Tk suicide gene has brought significant advances mainly because MSCs are chemoattracted to GBM and kill tumor cells via a bystander effect. To use this strategy, abundantly present adipose-tissue-derived mesenchymal stem cells (AT-MSCs) were evaluated for the treatment of GBM in mice. AT-MSCs were prepared using a mechanical protocol to avoid contamination with animal protein and transduced with HSV-Tk via a lentiviral vector. The U-87 glioblastoma cells cultured with AT-MSC-HSV-Tk died in the presence of 25 or 50 µM ganciclovir (GCV). U-87 glioblastoma cells injected into the brains of nude mice generated tumors larger than 3.5 mm2 after 4 weeks, but the injection of AT-MSC-HSV-Tk cells one week after the U-87 injection, combined with GCV treatment, drastically reduced tumors to smaller than 0.5 mm2. Immunohistochemical analysis of the tumors showed the presence of AT-MSC-HSV-Tk cells only within the tumor and its vicinity, but not in other areas of the brain, showing chemoattraction between them. The abundance of AT-MSCs and the easier to obtain them mechanically are strong advantages when compared to using MSCs from other tissues.

α- L-iduronidase gene-based therapy using the phiC31 system to treat mucopolysaccharidose type I mice.

BACKGROUND: Mucopolysaccharidose type I (MPSI) is a lysosomal monogenic disease caused by mutations in the gene for α- L-iduronidase (IDUA). MPSI patients need a constant supply of IDUA to alleviate progression of the disease. IDUA gene transfer using integrative vectors might provide a definitive solution and support advancement to clinical trials, although studies have not yet been satisfactory. To achieve a stable IDUA gene expression in vivo, phiC31 was tested in the present study. METHODS: Several plasmid vectors were constructed and IDUA-/- mice were treated with cyclophosphamide and transfected with these vectors hydrodynamically via tail veins. IDUA expression was monitored over time. Treated and nontreated mice underwent an open-field test at age 8 months, and IDUA activity and glycosaminoglycan (GAG) content of tissues were evaluated. RESULTS: High levels of IDUA activity were detected initially (>1000 U/ml), although these levels decayed over time. The reinjection of vectors produced a similar profile of IDUA decay. Three out of six treated mice had IDUA activity in the livers, and also showed lower GAG content, reduced lysosomes and better locomotion. To investigate unsustained IDUA production, wild-type mice were submitted to the same gene therapy procedure, which generated a similar profile of IDUA decay. Anti-IDUA antibody was detected in the sera of these animals. In addition, we also found three methylated sites in the cytomegalovirus promoter region. CONCLUSIONS: phiC31-mediated gene therapy resulted in an important improvement in IDUA-/- mice, including locomotion, although the obstacles that need to be overcome to enable long-term gene therapy for MPSI are also noted.

Mesenchymal stem cells do not prevent antibody responses against human α-L-iduronidase when used to treat mucopolysaccharidosis type I.

Mucopolysaccharidosis type I (MPSI) is an autosomal recessive disease that leads to systemic lysosomal storage, which is caused by the absence of α-L-iduronidase (IDUA). Enzyme replacement therapy is recognized as the best therapeutic option for MPSI; however, high titers of anti-IDUA antibody have frequently been observed. Due to the immunosuppressant properties of MSC, we hypothesized that MSC modified with the IDUA gene would be able to produce IDUA for a long period of time. Sleeping Beauty transposon vectors were used to modify MSC because these are basically less-immunogenic plasmids. For cell transplantation, 4×10(6) MSC-KO-IDUA cells (MSC from KO mice modified with IDUA) were injected into the peritoneum of KO-mice three times over intervals of more than one month. The total IDUA activities from MSC-KO-IDUA before cell transplantation were 9.6, 120 and 179 U for the first, second and third injections, respectively. Only after the second cell transplantation, more than one unit of IDUA activity was detected in the blood of 3 mice for 2 days. After the third cell transplantation, a high titer of anti-IDUA antibody was detected in all of the treated mice. Anti-IDUA antibody response was also detected in C57Bl/6 mice treated with MSC-WT-IDUA. The antibody titers were high and comparable to mice that were immunized by electroporation. MSC-transplanted mice had high levels of TNF-alpha and infiltrates in the renal glomeruli. The spreading of the transplanted MSC into the peritoneum of other organs was confirmed after injection of 111In-labeled MSC. In conclusion, the antibody response against IDUA could not be avoided by MSC. On the contrary, these cells worked as an adjuvant that favored IDUA immunization. Therefore, the humoral immunosuppressant property of MSC is questionable and indicates the danger of using MSC as a source for the production of exogenous proteins to treat monogenic diseases.

Impact of angiogenic therapy in the treatment of critical lower limb ischemia in an animal model.

Angiogenic therapies for critical limb ischemia were tested in a mouse model. The mice were anesthetized and their femoral arteries were ligated. The animals were treated with bone marrow mononuclear cells (BMMCs) alone, BMMCs combined with plasmid vector encoding granulocyte macrophage colony-stimulating factor (GM-CSF), received no treatment, or no intervention (controls). The degree of ischemia was monitored for 4 weeks using a visual scale. Muscle atrophy and strength were assessed at 4 weeks postoperatively; the mice were then killed. In treated animals, total necrosis of the limb was not found, the weight of the gastrocnemius and quadriceps muscles was significantly higher, functional ability and tissue regeneration were significantly increased, and muscle impairment and adipocyte presence were significantly reduced compared with untreated animals. At inducing angiogenesis, the BMMCs alone was more effective than BMMCs combined with plasmid vector encoding GM-CSF. Treated animals showed increased angiogenesis compared with ischemic untreated ones.

Genetic modification of mesenchymal stem cells.

Mesenchymal stem cells (MSC) are currently considered the most promising type of adult stem cells for therapeutic applications, because they can be easily isolated from the bone marrow and other tissues, and manipulated for different applications. The genetic transformation of MSC using genes that enhance their homing ability, as well as their proliferation and survival capacities when transplanted to sites of injury, is an important alternative to improve MSC function, especially for tissue regeneration. This chapter describes protocols for the transformation of MSC using plasmid vectors by lipofection and electroporation, as well as retroviral vectors representing viral transformations.

Treatment of adult MPSI mouse brains with IDUA-expressing mesenchymal stem cells decreases GAG deposition and improves exploratory behavior.

BACKGROUND: Mucopolysaccharidosis type I (MPSI) is caused by a deficiency in alpha-L iduronidase (IDUA), which leads to lysosomal accumulation of the glycosaminoglycans (GAGs) dermatan and heparan sulfate. While the currently available therapies have good systemic effects, they only minimally affect the neurodegenerative process. Based on the neuroprotective and tissue regenerative properties of mesenchymal stem cells (MSCs), we hypothesized that the administration of MSCs transduced with a murine leukemia virus (MLV) vector expressing IDUA to IDUA KO mouse brains could reduce GAG deposition in the brain and, as a result, improve neurofunctionality, as measured by exploratory activity. METHODS: MSCs infected with an MLV vector encoding IDUA were injected into the left ventricle of the brain of 12- or 25-month-old IDUA KO mice. The behavior of the treated mice in the elevated plus maze and open field tests was observed for 1 to 2 months. Following these observations, the brains were removed for biochemical and histological analyses. RESULTS: After 1 or 2 months of observation, the presence of the transgene in the brain tissue of almost all of the treated mice was confirmed using PCR, and a significant reduction in GAG deposition was observed. This reduction was directly reflected in an improvement in exploratory activity in the open field and the elevated plus maze tests. Despite these behavioral improvements and the reduction in GAG deposition, IDUA activity was undetectable in these samples. Overall, these results indicate that while the initial level of IDUA was not sustainable for a month, it was enough to reduce and maintain low GAG deposition and improve the exploratory activity for months. CONCLUSIONS: These data show that gene therapy, via the direct injection of IDUA-expressing MSCs into the brain, is an effective way to treat neurodegeneration in MPSI mice.

Evidence of lysosomal membrane permeabilization in mucopolysaccharidosis type I: rupture of calcium and proton homeostasis.

Mucopolysaccharidosis type I (MPS I) is caused by a deficiency of alpha-iduronidase (IDUA), which leads to intralysosomal accumulation of glysosaminoglycans. Patients with MPS I present a wide range of clinical manifestations, but the mechanisms by which these alterations occur are still not fully understood. Genotype-phenotype correlations have not been well established for MPS I; hence, it is likely that secondary and tertiary alterations in cellular metabolism and signaling may contribute to the physiopathology of the disease. The aim of this study was to analyze Ca(2+) and H(+) homeostasis, lysosomal leakage of cysteine proteases, and apoptosis in a murine model of MPS I. After exposition to specific drugs, cells from Idua-/- mice were shown to release more Ca(2+) from the lysosomes and endoplasmic reticulum than Idua+/+ control mice, suggesting a higher intraorganelle store of this ion. A lower content of H(+) in the lysosomes and in the cytosol was found in cells from Idua-/- mice, suggesting an alteration of pH homeostasis. In addition, Idua-/- cells presented a higher activity of cysteine proteases in the cytosol and an increased rate of apoptotic cells when compared to the control group, indicating that lysosomal membrane permeabilization might occur in this model. Altogether, our results suggest that secondary alterations-as changes in Ca(2+) and H(+) homeostasis and lysosomal membrane permeabilization-may contribute for cellular damage and death in the physiopathology of MPS I.

Synergistic effect of vascular endothelial growth factor and granulocyte colony-stimulating factor double gene therapy in mouse limb ischemia.

BACKGROUND: Vascular endothelial growth factor (VEGF) has mostly been tested to treat ischemic diseases, although the outcomes obtained are not satisfactory. Our hypothesis is that the local transient expression of VEGF and stem cell mobilizer granulocyte colony-stimulating factor (G-CSF) genes in ischemic limbs can complement their activities and be more efficient for limb recovery. METHODS: Limb ischemia was surgically induced in mice and 50 microg of VEGF and/or G-CSF genes were locally transferred by electroporation. After 3-4 weeks, evidence of necrosis by visual inspection, capillary density, muscle mass, muscle force and hematopoietic cell mobilization were evaluated. RESULTS: After 4 weeks, 70% and 90% of the animals of the ischemic group (IG) and VEGF-treated group (VG), respectively, presented limb necrosis, in contrast to only 10% observed in the group of mice treated with both VEGF and G-CSF genes (VGG). Recovery of muscle mass and muscle force was higher than 60% in the VGG compared to the non-ischemic group. The mobilization of Sca1+ cells and neutrophils was also higher in the VGG, which may explain the lower level of necrosis observed in this group (22%, in contrast to 70% in the IG). Capillary density and degree of fibrosis were determined in weeks 3 and 4, and also showed a clear benefit as a result of the use of the G-CSF and VEGF genes together. CONCLUSIONS: Gene therapy using VEGF and G-CSF demonstrated a synergistic effect promoting vessel and tissue repair in mouse hind limb ischemia.

Granulocyte-macrophage colony-stimulating factor gene based therapy for acute limb ischemia in a mouse model.

BACKGROUND: Granulocyte-colony-stimulating factor (GM-CSF) is a pleiotropic factor for hematopoiesis that stimulates myeloblasts, monoblasts and mobilization of bone marrow stem cells. Therefore, the GM-CSF gene is a potential candidate for vessel formation and tissue remodeling in the treatment of ischemic diseases. METHODS: A new mouse limb ischemia was established by surgery and gene transfer was performed by injection of 100 microg of a plasmid carrying GM-CSF. Muscle force and weight, histology, capillary density, circulating stem cells and monocytes were determined after 3-4 weeks. RESULTS: More than 60% of nontreated ischemic animals showed gangrene below the heel after 4 weeks, whereas the GM-CSF gene-treated animals showed only darkening of nails or toes. These animals demonstrated a full recovery of the affected muscles in terms of weight, force and muscle fiber structure, but the muscles of nontreated ischemic animals lost approximately 50% weight, 86% force and their regular structure. When the GM-CSF gene was injected into the contralateral limb, only partial loss was observed, demonstrating a distant effect of GM-CSF. The capillary density in the GM-CSF-treated group was 52% higher in relation to the nontreated group. Blood analysis by flow cytometry showed that the GM-CSF-treated group had 10-20% higher levels of circulating monocytes and Sca-1(+). CONCLUSIONS: We conclude that the direct administration of GM-CSF gene in limb ischemia had a strong therapeutic effect because it promoted the recovery of muscle mass, force and structure by mobilizing therapeutic cells and augmenting the number of vessels.