RESUMO
Selecting informative features, such as accurate biomarkers for disease diagnosis, prognosis and response to treatment, is an essential task in the field of bioinformatics. Medical data often contain thousands of features and identifying potential biomarkers is challenging due to small number of samples in the data, method dependence and non-reproducibility. This paper proposes a novel ensemble feature selection method, named Filter and Wrapper Stacking Ensemble (FWSE), to identify reproducible biomarkers from high-dimensional omics data. In FWSE, filter feature selection methods are run on numerous subsets of the data to eliminate irrelevant features, and then wrapper feature selection methods are applied to rank the top features. The method was validated on four high-dimensional medical datasets related to mental illnesses and cancer. The results indicate that the features selected by FWSE are stable and statistically more significant than the ones obtained by existing methods while also demonstrating biological relevance. Furthermore, FWSE is a generic method, applicable to various high-dimensional datasets in the fields of machine intelligence and bioinformatics.
Assuntos
Transtornos Mentais , Neoplasias , Humanos , Algoritmos , Inteligência Artificial , Biomarcadores , Neoplasias/diagnóstico , Neoplasias/genéticaRESUMO
The COVID-19 pandemic led to a major disruption to health services across the world. The aim of this population-based study was to assess the downstream effects of the pandemic on diagnostic tests and treatment activities related to prostate cancer (PC). The Australian Government Department of Health Medicare Benefits Schedule and the Pharmaceutical Benefits Scheme databases were queried from January 2010 to June 2022. Two interrupted time series were performed Pre-COVID (January 2010 to February 2020) and peri-COVID (March 2020 to June 2022). Temporal modeling was performed to account for seasonal variation. Pre-COVID-19, monthly prostate-specific antigen (PSA) testing showed a declining trend and testing decreased by 81 tests per 100 000 annually. A single-month 38% drop in PSA testing was observed in April 2020; this corresponded to Australia's first wave. No change was observed in the rate of prostate biopsies. Peri-COVID-19 outbreaks, there was a slight shift toward the use of long-acting androgen deprivation therapy (ADT) at 4% with a predilection still for short-acting agents. with no registered change in the overall volume of radiotherapy or surgery. There were no deficits in the number of diagnostic and treatment activities for men with PC. Aside from a slight shift toward long-acting ADT use during the pandemic, no other patterns were observed. The longer-term impact such as missed diagnosis or late presentation affecting chances of survival due to COVID-19 is yet to be ascertained.
Assuntos
COVID-19 , Neoplasias da Próstata , Idoso , Masculino , Humanos , Neoplasias da Próstata/epidemiologia , Neoplasias da Próstata/terapia , Neoplasias da Próstata/patologia , Antígeno Prostático Específico , Próstata/patologia , Análise de Séries Temporais Interrompida , Pandemias , Antagonistas de Androgênios , Prostatectomia , Austrália/epidemiologia , COVID-19/epidemiologia , Programas Nacionais de SaúdeRESUMO
Lymphangiogenesis is a precursor to lymphovascular invasion, and may therefore signal a higher risk of metastasis and mortality in primary cutaneous melanoma. This retrospective longitudinal study aimed to evaluate whether emergent lymphangiogenesis, as measured through co-expression of endothelial proteins with the proliferation marker Ki67, was associated with poorer prognosis in a cohort of patients with single primary cutaneous melanoma. We screened all patients with a single locally invasive primary cutaneous melanoma who received sentinel lymph node biopsy at a tertiary dermatology centre in Brisbane, Australia between 1994 and 2007. Primary melanoma sections were stained via Opal multiplex immunofluorescence, and categorized according to the presence of Ki67 within either CD31+ or D2-40+ endothelial cells. Multivariate Cox regression modelling was used to evaluate associations between endothelial Ki67 positivity and clinical outcomes, with adjustment for age, sex, Breslow depth, ulceration, and anatomical location. Overall, 264 patients were available for analysis, with a median follow-up duration of 7.1 years. The presence of D2-40+ /Ki67+ co-expression was associated with greater melanoma-specific mortality (adjusted hazard ratio [HR]: 2.03; 95% confidence interval [CI]: 1.33-3.10; p = 0.001) and recurrence (adjusted HR: 1.70; 95% CI: 1.33-3.10; p = 0.001) relative to absence. CD31+ /Ki67+ co-expression was not prognostic in this cohort. Lymphatic proliferation, as measured through D2-40+ /Ki67+ co-expression, predicted greater melanoma-specific mortality and recurrence in this cohort of primary cutaneous melanoma.
Assuntos
Melanoma , Neoplasias Cutâneas , Humanos , Antígeno Ki-67 , Células Endoteliais , Estudos Longitudinais , Estudos Retrospectivos , Proliferação de CélulasRESUMO
BACKGROUND: Progesterone receptor (PGR) is a master regulator of uterine function through antagonistic and synergistic interplays with oestrogen receptors. PGR action is primarily mediated by activation functions AF1 and AF2, but their physiological significance is unknown. RESULTS: We report the first study of AF1 function in mice. The AF1 mutant mice are infertile with impaired implantation and decidualization. This is associated with a delay in the cessation of epithelial proliferation and in the initiation of stromal proliferation at preimplantation. Despite tissue selective effect on PGR target genes, AF1 mutations caused global loss of the antioestrogenic activity of progesterone in both pregnant and ovariectomized models. Importantly, the study provides evidence that PGR can exert an antioestrogenic effect by genomic inhibition of Esr1 and Greb1 expression. ChIP-Seq data mining reveals intermingled PGR and ESR1 binding on Esr1 and Greb1 gene enhancers. Chromatin conformation analysis shows reduced interactions in these genes' loci in the mutant, coinciding with their upregulations. CONCLUSION: AF1 mediates genomic inhibition of ESR1 action globally whilst it also has tissue-selective effect on PGR target genes.
Assuntos
Progesterona , Receptores de Progesterona , Animais , Cromatina/metabolismo , Endométrio/metabolismo , Estrogênios/metabolismo , Estrogênios/farmacologia , Feminino , Furilfuramida/metabolismo , Furilfuramida/farmacologia , Camundongos , Gravidez , Progesterona/metabolismo , Progesterona/farmacologia , Receptores de Estrogênio/genética , Receptores de Estrogênio/metabolismo , Receptores de Progesterona/genética , Receptores de Progesterona/metabolismo , Útero/metabolismoRESUMO
The current methods for diagnosis of acute and chronic infections are complex and skill-intensive. For complex clinical biofilm infections, it can take days from collecting and processing a patient's sample to achieving a result. These aspects place a significant burden on healthcare providers, delay treatment, and can lead to adverse patient outcomes. We report the development and application of a novel multi-excitation Raman spectroscopy-based methodology for the label-free and non-invasive detection of microbial pathogens that can be used with unprocessed clinical samples directly and provide rapid data to inform diagnosis by a medical professional. The method relies on the differential excitation of non-resonant and resonant molecular components in bacterial cells to enhance the molecular finger-printing capability to obtain strain-level distinction in bacterial species. Here, we use this strategy to detect and characterize the respiratory pathogens Pseudomonas aeruginosa and Staphylococcus aureus as typical infectious agents associated with cystic fibrosis. Planktonic specimens were analyzed both in isolation and in artificial sputum media. The resonance Raman components, excited at different wavelengths, were characterized as carotenoids and porphyrins. By combining the more informative multi-excitation Raman spectra with multivariate analysis (support vector machine) the accuracy was found to be 99.75% for both species (across all strains), including 100% accuracy for drug-sensitive and drug-resistant S. aureus. The results demonstrate that our methodology based on multi-excitation Raman spectroscopy can underpin the development of a powerful platform for the rapid and reagentless detection of clinical pathogens to support diagnosis by a medical expert, in this case relevant to cystic fibrosis. Such a platform could provide translatable diagnostic solutions in a variety of disease areas and also be utilized for the rapid detection of anti-microbial resistance.
Assuntos
Staphylococcus aureus Resistente à Meticilina , Escarro , Antibacterianos , Bactérias , Pseudomonas aeruginosa , Análise Espectral Raman/métodos , Escarro/microbiologia , Staphylococcus aureus/químicaRESUMO
The accurate prediction of physicochemical properties of condensed systems is a longstanding goal of theoretical (quantum) chemistry. Ionic liquids comprising entirely of ions provide a unique challenge in this respect due to the diverse chemical nature of available ions and the complex interplay of intermolecular interactions among them, thus resulting in the wide variability of physicochemical properties, such as thermodynamic, transport, and spectroscopic properties. It is well understood that intermolecular forces are directly linked to physicochemical properties of condensed systems, and therefore, an understanding of this relationship would greatly aid in the design and synthesis of functionalized materials with tailored properties for an application at hand. This review aims to give an overview of how electronic structure properties obtained from quantum chemical methods such as interaction/binding energy and its fundamental components, dipole moment, polarizability, and orbital energies, can help shed light on the energetic, physical, and spectroscopic properties of semi-Coulomb systems such as ionic liquids. Particular emphasis is given to the prediction of their thermodynamic, transport, spectroscopic, and solubilizing properties.
RESUMO
Accurate prediction of intermolecular interactions plays a pivotal role in many areas of chemistry and biology including (but not limited to) the design of pharmaceuticals, solid electrolytes and food additives. Here we present the application of the recently developed spin-ratio scaled MP2 method (termed SRS-MP2) to six different datasets covering a wide range of interaction types from strong hydrogen bonding to van der Waals dispersion and π-π stacking. The method achieves a remarkably low mean absolute error of 1.6 kJ mol-1 across all interaction types including semi-Coulombic systems such as organic ionic salts. The new SRS-MP2 method offers high level of accuracy for studying intermolecular interactions commonly found in molecular systems of chemical and biological relevance without the need for including additional terms in the formulation. This finding represents a new paradigm in the development of wavefunction-based methods for intermolecular interactions.
RESUMO
The accurate calculation of intermolecular interactions is important to our understanding of properties in large molecular systems. The high computational cost of the current "gold standard" method, coupled cluster with singles and doubles and perturbative triples (CCSD(T), limits its application to small- to medium-sized systems. Second-order Møller-Plesset perturbation (MP2) theory is a cheaper alternative for larger systems, although at the expense of its decreased accuracy, especially when treating van der Waals complexes. In this study, a new modification of the spin-component scaled MP2 method was proposed for a wide range of intermolecular complexes including two well-known datasets, S22 and S66, and a large dataset of ionic liquids consisting of 174 single ion pairs, IL174. It was found that the spin ratio, ϵΔs=EINTOSEINTSS, calculated as the ratio of the opposite-spin component to the same-spin component of the interaction correlation energy fell in the range of 0.1 and 1.6, in contrast to the range of 3-4 usually observed for the ratio of absolute correlation energy, ϵs=EOSESS, in individual molecules. Scaled coefficients were found to become negative when the spin ratio fell in close proximity to 1.0, and therefore, the studied intermolecular complexes were divided into two groups: (1) complexes with ϵΔs< 1 and (2) complexes with ϵΔs≥ 1. A separate set of coefficients was obtained for both groups. Exclusion of counterpoise correction during scaling was found to produce superior results due to decreased error. Among a series of Dunning's basis sets, cc-pVTZ and cc-pVQZ were found to be the best performing ones, with a mean absolute error of 1.4 kJ mol-1 and maximum errors below 6.2 kJ mol-1. The new modification, spin-ratio scaled second-order Møller-Plesset perturbation, treats both dispersion-driven and hydrogen-bonded complexes equally well, thus validating its robustness with respect to the interaction type ranging from ionic to neutral species at minimal computational cost.
RESUMO
An important advantage of pattern-based chemosensor sets is their potential to detect and differentiate a large number of analytes with only few sensors. Here we test this principle at a conceptual limit by analyzing a large set of metal ion analytes covering essentially the entire periodic table, employing fluorescent DNA-like chemosensors on solid support. A tetrameric "oligodeoxyfluoroside" (ODF) library of 6561 members containing metal-binding monomers was screened for strong responders to 57 metal ions in solution. Our results show that a set of 9 chemosensors could successfully discriminate the 57 species, including alkali, alkaline earth, post-transition, transition, and lanthanide metals. As few as 6 ODF chemosensors could detect and differentiate 50 metals at 100 µM; sensitivity for some metals was achieved at midnanomolar ranges. A blind test with 50 metals further confirmed the discriminating power of the ODFs.
Assuntos
Corantes Fluorescentes/química , Metais Pesados/análise , Corantes Fluorescentes/síntese química , Estrutura MolecularRESUMO
Lymphadenopathy in an immunosuppressed patient raises the quintessential diagnostic dilemma: infection or malignancy? We present the case of a transplant recipient on anti-rejection prophylaxis admitted with acute fever, malaise and a swollen right axillary node. The patient had pancytopenia and tested positive for Epstein-Barr virus; nodal core biopsy demonstrated atypical plasma cell infiltration, immediately raising suspicion for post-transplant lymphoproliferative disorder. However, excisional biopsy and Bartonella henselae serology clarified a final diagnosis of cat-scratch disease-a potentially fatal zoonosis requiring a disparate treatment regimen. Here, we explore this patient's investigations, hospital course and recovery, with an emphasis on recognizing and differentiating these diagnostic mimics in post-transplant practice.
RESUMO
The intricate relationship between cancer and cardiovascular diseases (CVD), notably heart failure (HF), is gaining attention in the medical field. This literature review explores the intricate interplay between cancer and CVD, particularly HF, emphasizing their significant impact on global mortality and comorbidity. While preventive measures have contributed to reducing their incidence, challenges persist in predicting and managing cancer-related complications. This review article delves into various risk factors associated with both cancer and HF, including lifestyle factors, genetic predispositions, and immune system dysregulation. It highlights emerging evidence suggesting a direct interaction between cancer and HF, with studies indicating an elevated risk of mortality from cancer in patients with HF and vice versa. Pathological mechanisms such as inflammation, oxidative stress, and tissue hypoxia are implicated in cancer-induced cardiac dysfunction, underscoring the need for comprehensive clinical investigations and ethical considerations in patient care. The review also discusses the potential role of biomarkers in risk assessment, early detection of cardiotoxicity, and understanding common pathophysiological links between cancer and HF, paving the way for multifaceted preventive and therapeutic approaches.
RESUMO
Mitral annular calcification (MAC) is relatively common in clinical practice. Females are more often affected than males. Patients with end-stage renal disease have MAC relatively more commonly than the general population. Patients with MAC often develop conduction system disturbances, including advanced atrioventricular blocks. They are also more likely to develop various arrhythmias, including atrial fibrillation. Caseous mitral annulus calcification is a variant of MAC that often looks like a cardiac tumor on an echocardiogram and needs to be differentiated.
RESUMO
BACKGROUND: Data on disparities in outcomes and risk factors in Asian patients with advanced chronic kidney disease admitted for heart failure are scare. METHODS: This was a retrospective cohort study that utilized data from the National Inpatient Sample between January 2016 and December 2019. Patients who had a primary diagnosis of acute decompensated heart failure and a concomitant diagnosis of advanced CKD were included. The primary outcome of interest was in-hospital mortality. Secondary outcomes include hospital cost, length of stay, and other clinical outcomes. Weighted multivariable logistic regression was used to adjust for comorbidities. RESULTS: There were 251,578 cases of ADHF with advanced CKD, out of which 2.6 % were from individuals of Asian ethnicity. Asian patients exhibited a higher burden of comorbidities in comparison to other UREM patients, but a lower burden than White patients. Regardless of differences in comorbidity burden, Asian patients exhibited a higher likelihood of experiencing severe consequences. After adjusting for comorbidies, White (OR:1.11; 95 % CI 1.03-1.20;0.009) patients had higher odds of mortality than Asian patients. However, Blacks (OR: 0.58; 95 % CI 0.53 to 0.63; p < 0.001) and Hispanics (OR: 0.69; 95 % CI 0.62 to 0.78; p < 0.001) had lower odds of mortality. CONCLUSION: This first population-based studies shows that Asian patients with advanced CKD admitted for ADHF have greater comorbidity burden and poorer outcomes Black and Hispanic patients. This data underscores the importance of comprehensive approaches in phenotyping, and ethnic specific interventions.
Assuntos
Insuficiência Cardíaca , Mortalidade Hospitalar , Insuficiência Renal Crônica , Humanos , Masculino , Feminino , Insuficiência Cardíaca/etnologia , Insuficiência Cardíaca/epidemiologia , Insuficiência Cardíaca/mortalidade , Estudos Retrospectivos , Idoso , Insuficiência Renal Crônica/etnologia , Insuficiência Renal Crônica/epidemiologia , Mortalidade Hospitalar/tendências , Estados Unidos/epidemiologia , Pessoa de Meia-Idade , Fatores de Risco , Doença Aguda , Comorbidade , Idoso de 80 Anos ou mais , Vigilância da População/métodos , Asiático/estatística & dados numéricos , Povo Asiático/estatística & dados numéricosRESUMO
Cardiovascular disease remains a leading global health challenge, necessitating advanced diagnostic approaches. This review explores the integration of artificial intelligence (AI) in multimodal cardiac imaging, tracing its evolution from early X-rays to contemporary techniques such as CT, MRI, and nuclear imaging. AI, particularly machine learning and deep learning, significantly enhances cardiac diagnostics by estimating biological heart age, predicting disease risk, and optimizing heart failure management through adaptive algorithms without explicit programming or feature engineering. Key contributions include AI's transformative role in non-invasive coronary artery disease diagnosis, arrhythmia detection via wearable devices, and personalized treatment strategies. Despite substantial progress, challenges including data standardization, algorithm validation, regulatory approval, and ethical considerations must be addressed to fully harness AI's potential. Collaborative efforts among clinicians, scientists, industry stakeholders, and regulatory bodies are essential for the safe and effective deployment of AI in cardiac imaging, promising enhanced diagnostics and personalized patient care.
RESUMO
Scrotal-inguino-retroperitoneal (SIR) lymphocele is a rare complication following kidney transplant. This entity is characterized by a tract originating in the retroperitoneal space, through the inguinal canal and scrotum following lymph hydrodissection. Systematic review investigating SIR lymphocele yielded cases with open fenestration of the sac into the peritoneum as treatment. We described a case report of a male in his 60s with a functioning kidney transplant and SIR lymphocele, which was successfully managed in the short term with percutaneous drainage of the collection. However, the collection recurred and computed tomography scan showed a multiloculated collection that prompted surgical management. Intraoperatively, the encapsulated fluid-filled tract was excised and a drain was placed, which was removed 48 h later. The patient wore a hernia belt for 6 weeks as support. He had no recurrence of his lymphocele following serial reviews for 9 months now.
RESUMO
Interpretable machine learning models for gene expression datasets are important for understanding the decision-making process of a classifier and gaining insights on the underlying molecular processes of genetic conditions. Interpretable models can potentially support early diagnosis before full disease manifestation. This is particularly important yet, challenging for mental health. We hypothesise this is due to extreme heterogeneity issues which may be overcome and explained by personalised modelling techniques. Thus far, most machine learning methods applied to gene expression datasets, including deep neural networks, lack personalised interpretability. This paper proposes a new methodology named personalised constrained neuro fuzzy inference (PCNFI) for learning personalised rules from high dimensional datasets which are structurally and semantically interpretable. Case studies on two mental health related datasets (schizophrenia and bipolar disorders) have shown that the relatively short and simple personalised fuzzy rules provided enhanced interpretability as well as better classification performance compared to other commonly used machine learning methods. Performance test on a cancer dataset also showed that PCNFI matches previous benchmarks. Insights from our approach also indicated the importance of two genes (ATRX and TSPAN2) as possible biomarkers for early differentiation of ultra-high risk, bipolar and healthy individuals. These genes are linked to cognitive ability and impulsive behaviour. Our findings suggest a significant starting point for further research into the biological role of cognitive and impulsivity-related differences. With potential applications across bio-medical research, the proposed PCNFI method is promising for diagnosis, prognosis, and the design of personalised treatment plans for better outcomes in the future.
Assuntos
Transtorno Bipolar , Lógica Fuzzy , Humanos , Detecção Precoce de Câncer , Redes Neurais de Computação , Expressão Gênica , AlgoritmosRESUMO
Finding predictors of social and cognitive impairment in non-transition Ultra-High-Risk individuals (UHR) is critical in prognosis and planning of potential personalised intervention strategies. Social and cognitive functioning observed in youth at UHR for psychosis may be protective against transition to clinically relevant illness. The current study used a computational method known as Spiking Neural Network (SNN) to identify the cognitive and social predictors of transitioning outcome. Participants (90 UHR, 81 Healthy Control (HC)) completed batteries of neuropsychological tests in the domains of verbal memory, working memory, processing speed, attention, executive function along with social skills-based performance at baseline and 4 × 6-month follow-up intervals. The UHR status was recorded as Remitters, Converters or Maintained. SNN were used to model interactions between variables across groups over time and classify UHR status. The performance of SNN was examined relative to other machine learning methods. Higher interaction between social and cognitive variables was seen for the Maintained, than Remitter subgroup. Findings identified the most important cognitive and social variables (particularly verbal memory, processing speed, attention, affect and interpersonal social functioning) that showed discriminative patterns in the SNN models of HC vs UHR subgroups, with accuracies up to 80%; outperforming other machine learning models (56-64% based on 18 months data). This finding is indicative of a promising direction for early detection of social and cognitive impairment in UHR individuals that may not anticipate transition to psychosis and implicate early initiated interventions to stem the impact of clinical symptoms of psychosis.
RESUMO
Identifying prognostic biomarkers to predict clinical outcomes in stage I and II cutaneous melanomas could guide the clinical application of adjuvant and neoadjuvant therapies. We aimed to investigate the prognostic value of phosphorylated signal transducer and activator of transcription 5 (pSTAT5) as a biomarker in early-stage melanoma. This study evaluated all initially staged Ib and II melanoma patients undergoing sentinel node biopsy at a tertiary centre in Brisbane, Australia between 1994 and 2007, with survival data collected from the Queensland Cancer Registry. Primary melanoma tissue from 189 patients was analysed for pSTAT5 level through immunohistochemistry. Cox regression modelling, with adjustment for sex, age, ulceration, anatomical location, and Breslow depth, was applied to determine the association between pSTAT5 detection and melanoma-specific survival. Median duration of follow-up was 7.4 years. High pSTAT5 detection was associated with ulceration and increased tumour thickness. However, multivariate analysis indicated that high pSTAT5 detection was associated with improved melanoma-specific survival (hazard ratio: 0.15, 95% confidence interval: 0.03-0.67) as compared to low pSTAT5 detection. This association persisted when pSTAT5 detection was limited to immune infiltrate or the vasculature, as well as when sentinel node positivity was accounted for. In this cohort, staining for high-pSTAT5 tumours identified a subset of melanoma patients with increased survival outcomes as compared to low-pSTAT5 tumours, despite the former having higher-risk clinicopathological characteristics at diagnosis. pSTAT5 is likely an indicator of local immune activation, and its detection could represent a useful tool to stratify the risk of melanoma progression.