RESUMO
OBJECTIVES: Iron-deficiency anemia (IDA) is a common health problem worldwide, and up to 10% of adult patients with incidental IDA may have gastrointestinal cancer. A diagnosis of IDA can be established through a combination of laboratory tests, but it is often underrecognized until a patient becomes symptomatic. Based on advances in machine learning, we hypothesized that we could reduce the time to diagnosis by developing an IDA prediction model. Our goal was to develop 3 neural networks by using retrospective longitudinal outpatient laboratory data to predict the risk of IDA 3 to 6 months before traditional diagnosis. METHODS: We analyzed retrospective outpatient electronic health record data between 2009 and 2020 from an academic medical center in northern Texas. We included laboratory features from 30,603 patients to develop 3 types of neural networks: artificial neural networks, long short-term memory cells, and gated recurrent units. The classifiers were trained using the Adam Optimizer across 200 random training-validation splits. We calculated accuracy, area under the receiving operating characteristic curve, sensitivity, and specificity in the testing split. RESULTS: Although all models demonstrated comparable performance, the gated recurrent unit model outperformed the other 2, achieving an accuracy of 0.83, an area under the receiving operating characteristic curve of 0.89, a sensitivity of 0.75, and a specificity of 0.85 across 200 epochs. CONCLUSIONS: Our results showcase the feasibility of employing deep learning techniques for early prediction of IDA in the outpatient setting based on sequences of laboratory data, offering a substantial lead time for clinical intervention.
Assuntos
Neoplasias Encefálicas , Neoplasias Neuroepiteliomatosas , Neoplasias Encefálicas/genética , Neoplasias Encefálicas/patologia , Criança , Proteínas Fetais , Humanos , Proteínas Associadas aos Microtúbulos , Neoplasias Neuroepiteliomatosas/patologia , Proteínas Nucleares , Receptor Tipo 1 de Fator de Crescimento de Fibroblastos/genéticaRESUMO
We describe a previously unreported bronchopulmonary foregut malformation wherein a segment of a bronchus of the lower lobe of the left lung in a 4-year-old girl was entirely esophageal in structure. No communication was identified between the tracheobronchial tree and the esophagus by radiologic examination or at surgery. The esophagus-like bronchus was associated with an adjacent atretic bronchus and a downstream cavity in the lower lobe of the left lung. The child sought clinical attention because of recurrent pulmonary infections localized to the lower lobe of the lung. We posit that this esophagus-like bronchus is a novel noncommunicating bronchopulmonary foregut malformation.
Assuntos
Brônquios/anormalidades , Esôfago/anormalidades , Brônquios/patologia , Brônquios/cirurgia , Pré-Escolar , Esôfago/patologia , Esôfago/cirurgia , Feminino , Humanos , PneumonectomiaRESUMO
The cytosolic iron-sulfur (Fe-S) cluster assembly (CIA) pathway functions to incorporate inorganic Fe-S cofactors into a variety of proteins, including several DNA repair enzymes. However, the mechanisms regulating the CIA pathway are unknown. We describe here that the MAGE-F1-NSE1 E3 ubiquitin ligase regulates the CIA pathway through ubiquitination and degradation of the CIA-targeting protein MMS19. Overexpression or knockout of MAGE-F1 altered Fe-S incorporation into MMS19-dependent DNA repair enzymes, DNA repair capacity, sensitivity to DNA-damaging agents, and iron homeostasis. Intriguingly, MAGE-F1 has undergone adaptive pseudogenization in select mammalian lineages. In contrast, MAGE-F1 is highly amplified in multiple human cancer types and amplified tumors have increased mutational burden. Thus, flux through the CIA pathway can be regulated by degradation of the substrate-specifying MMS19 protein and its downregulation is a common feature in cancer and is evolutionarily controlled.
Assuntos
Proteínas de Transporte/metabolismo , Reparo do DNA/genética , Ferro/química , Proteínas Associadas aos Microtúbulos/metabolismo , Proteínas de Neoplasias/metabolismo , Enxofre/química , Fatores de Transcrição/metabolismo , Animais , Sistemas CRISPR-Cas , Linhagem Celular Tumoral , Dano ao DNA/genética , Células HEK293 , Células HeLa , Humanos , Proteínas Ferro-Enxofre/metabolismo , Neoplasias Pulmonares/patologia , Masculino , Camundongos , Camundongos Endogâmicos NOD , Camundongos SCID , Proteínas Associadas aos Microtúbulos/genética , Proteínas de Neoplasias/genética , UbiquitinaçãoRESUMO
The Melanoma Antigen Gene (MAGE) protein family is a large, highly conserved group of proteins that share a common MAGE homology domain. Intriguingly, many MAGE proteins are restricted in expression to reproductive tissues, but are aberrantly expressed in a wide variety of cancer types. Originally discovered as antigens on tumor cells and developed as cancer immunotherapy targets, recent literature suggests a more prominent role for MAGEs in driving tumorigenesis. This review will highlight recent developments into the function of MAGEs as oncogenes, their mechanisms of action in regulation of ubiquitin ligases, and outstanding questions in the field.
Assuntos
Antígenos de Neoplasias/metabolismo , Proteínas de Neoplasias/metabolismo , Neoplasias/metabolismo , Animais , Progressão da Doença , Humanos , Imunoterapia , Neoplasias/patologia , Neoplasias/terapia , Células-Tronco NeoplásicasRESUMO
AMP-activated protein kinase (AMPK) is a master sensor and regulator of cellular energy status. Upon metabolic stress, AMPK suppresses anabolic and promotes catabolic processes to regain energy homeostasis. Cancer cells can occasionally suppress the growth-restrictive AMPK pathway by mutation of an upstream regulatory kinase. Here, we describe a widespread mechanism to suppress AMPK through its ubiquitination and degradation by the cancer-specific MAGE-A3/6-TRIM28 ubiquitin ligase. MAGE-A3 and MAGE-A6 are highly similar proteins normally expressed only in the male germline but frequently re-activated in human cancers. MAGE-A3/6 are necessary for cancer cell viability and are sufficient to drive tumorigenic properties of non-cancerous cells. Screening for targets of MAGE-A3/6-TRIM28 revealed that it ubiquitinates and degrades AMPKα1. This leads to inhibition of autophagy, activation of mTOR signaling, and hypersensitization to AMPK agonists, such as metformin. These findings elucidate a germline mechanism commonly hijacked in cancer to suppress AMPK.