Background Machine learning tools identify patients with blood counts indicating greater likelihood of colorectal cancer and warranting colonoscopy referral. Aims To validate a machine learning colorectal cancer detection model on a US community-based insured adult population. Methods Eligible colorectal cancer cases (439 females, 461 males) with complete blood counts before diagnosis were identified from Kaiser Permanente Northwest Region's Tumor Registry. Control patients (n = 9108) were randomly selected from KPNW's population who had no cancers, received at C1 blood count, had continuous enrollment from 180 days prior to the blood count through 24 months after the count, and were aged 40-89. For each control, one blood count was randomly selected as the pseudo-colorectal cancer diagnosis date for matching to cases, and assigned a ''calendar year'' based on the count date. For each calendar year, 18 controls were randomly selected to match the general enrollment's 10-year age groups and lengths of continuous enrollment. Prediction performance was evaluated by area under the curve, specificity, and odds ratios. Results Area under the receiver operating characteristics curve for detecting colorectal cancer was 0.80 ± 0.01. At 99% specificity, the odds ratio for association of a high-risk detection score with colorectal cancer was 34.7 (95% CI 28.9-40.4). The detection model had the highest accuracy in identifying right-sided colorectal cancers. Conclusions ColonFlag Ò identifies individuals with tenfold higher risk of undiagnosed colorectal cancer at curable stages (0/I/II), flags colorectal tumors 180-360 days prior to usual clinical diagnosis, and is more accurate at identifying right-sided (compared to left-sided) colorectal cancers.
It has only recemiy ~¢omc clear that genetic imprinting pla~ an important role in human cmbwogcnefis and in proccsr~ leading to the development of pediatric cancers and other haman discuss. Osin8 a uniqu~ human ti~ue, the andro~netic complete hydatidiform mole. we cstablishc.d that the maternally inherited allele of the imprinted H 19 8¢ne is espr~sc.d. Our f~ults al~ show that the paternal allele of the haman IGF-II 8en¢. a gear suspected to ~ parentally imprinted in humans, is expre~d.
Some patients express various features of cystic fibrosis (CF) even though essential characteristics of the disease might be absent. Such patients may suffer from respiratory disease without pancreatic insufficiency and normal sweat chloride levels. Others may present as male infertility because of congenital bilateral aplasia of the vas deferens (CBAVD) with no other signs of CF. The 5T allele, a DNA variant in a noncoding region of the cystic fibrosis transmembrane conductance regulator (CFTR) gene that reduces the level of the normal CFTR transcripts, was found in increased frequency among male patients with CBAVD. The purpose of this study was to investigate the possibility that the 5T allele is associated with dysfunction of organs other than the male reproductive system, leading to CF or atypical CF. Analysis of the 5T allele was performed on 148 subjects (29 with CF, 61 with atypical CF, and 58 with CBAVD) carrying 232 chromosomes with unidentified CFTR mutations, and on 142 non-CF chromosomes from healthy subjects of Ashkenazi origin. The frequency of the 5T allele among chromosomes from patients of Jewish Ashkenazi origin with CF and atypical CF (six of 33; 18%) was significantly higher than the frequency in the normal Ashkenazi population (eight of 142; 6%; p = 0.03). Analysis of the clinical presentation of the five patients with CF and the 12 patients with atypical CF carrying the 5T allele indicated that most patients suffered from respiratory disease presenting as asthma like symptoms, nasal polyposis, chronic sinusitis, chronic bronchitis, or bronchiectasis. Six patients had pancreatic insufficiency, two with meconium ileus. Sweat Cl- levels ranged from normal to elevated. Of the six male patients with respiratory disease who were old enough to be evaluated for fertility status, five were fertile and one had pancreatic insufficiency. Among male patients with CBAVD, 41% suffered from respiratory symptoms. Thus, the 5T allele is a variant with partial penetrance causing disease with an extreme variability of clinical presentation: from normal healthy fertile subjects or male patients with CBAVD to those with atypical or typical clinical phenotype of CF.
The H-19 gene in mice is maternally imprinted and its ectopic expression causes prenatal lethality. We have recently identified H-19 transcript in differentiating human placental cells and showed that its expression increases concomitantly with differentiation of cytotrophoblasts in vitro. Placental and embryonal specimens were collected from conception products derived from normal first and second trimester pregnancy terminations. We investigated the abundance of H-19 mRNA throughout placental development in vivo and compared it to the expression of other genes linked to placental differentiation. Furthermore, the expression of H-19 transcript in different organs of human fetuses, aborted during the second trimester, was examined by RNA isolation from separated fetal organs. Since IGF-2 is known to play an important role in embryogenesis, identical blots were hybridized with IGF-2 probe. H-19 expression in human placenta from the different trimesters of pregnancy remains practically constant. A high amount of H-19 gene product was found in the fetoplacental unit with the highest level measured in the adrenal gland. These findings argue that H-19 gene may play a role in human embryogenesis.
Aims: Identification, a priori, of those at high risk of progression from pre-diabetes to diabetes may enable targeted delivery of interventional programmes while avoiding the burden of prevention and treatment in those at low risk. We studied whether the use of a machine-learning model can improve the prediction of incident diabetes utilizing patient data from electronic medical records. Methods: A machine-learning model predicting the progression from pre-diabetes to diabetes was developed using a gradient boosted trees model. The model was trained on data from The Health Improvement Network (THIN) database cohort, internally validated on THIN data not used for training, and externally validated on the Canadian AppleTree and the Israeli Maccabi Health Services (MHS) data sets. The model's predictive ability was compared with that of a logistic-regression model within each data set. Results: A cohort of 852 454 individuals with pre-diabetes (glucose ≥ 100 mg/dL and/or HbA1c ≥ 5.7) was used for model training including 4.9 million time points using 900 features. The full model was eventually implemented using 69 variables, generated from 11 basic signals. The machine-learning model demonstrated superiority over the logistic-regression model, which was maintained at all sensitivity levelscomparing AUC [95% CI] between the models; in the THIN data set (0.865 [0.860,0.869] vs 0.778 [0.773,0.784] P < .05), the AppleTree data set (0.907 [0.896, 0.919] vs 0.880 [0.867, 0.894] P < .05) and the MHS data set (0.925 [0.923, 0.927] vs 0.876 [0.872, 0.879] P < .05).Conclusions: Machine-learning models preserve their performance across populations in diabetes prediction, and can be integrated into large clinical systems, leading to judicious selection of persons for interventional programmes. K E Y W O R D Selectronic medical records, machine learning, pre-diabetes
Individuals with colorectal cancer (CRC) have a tendency to intestinal bleeding which may result in mild to severe iron deficiency anemia, but for many colon cancer patients hematological abnormalities are subtle. The fecal occult blood test (FOBT) is used as a pre-screening test whereby those with a positive FOBT are referred to colonscopy. We sought to determine if information contained in the complete blood count (CBC) report coud be processed automatically and used to predict the presence of occult colorectal cancer (CRC) in the setting of a large health services plan. Using the health records of the Maccabi Health Services (MHS) we reviewed CBC reports for 112,584 study subjects of whom 133 were diagnosed with CRC in 2008 and analysed these with the MeScore tool. The odds ratio for being diagnosed with CRC in 2008 was calculated with regards to the MeScore, using cutoff levels of 97% and 99% percentiles. For individuals in the highest one percentile, the odds ratio for CRC was 21.8 (95% CI 13.8 to 34.2). For the majority of the individuals with cancer, CRC was not suspected at the time of the blood draw. Frequent use of anticoagulants, the presence of other gastrointestinal pathologies and non-GI malignancies were assocaitged with false positive MeScores. The MeScore can help identify individuals in the population who would benefit most from CRC screening, including those with no clinical signs or symptoms of CRC.
The role of different extracellular matrix (ECM)-degrading enzymes in the normal functioning of the placenta is well documented. Heparan sulphate proteoglycan (HSPG) is an integral constituent of the placental and decidual ECM. Because this proteoglycan specifically interacts with various macromolecules in the ECM, its degradation may disassemble the matrix. Hence, in the case of the placenta, this may facilitate normal placentation and trophoblast invasion. Crude placental specimens were collected from first and third trimester placentas. Heparanase (endo-beta-glucuronidase) was isolated and purified by ammonium sulphate precipitation followed by sequential chromatographies on carboxymethyl-, heparin- and ConA-Sepharose columns. The placental enzyme was further characterized for its molecular weight and specific inhibition by heparin, and was shown to resemble heparanase expressed by highly metastatic tumor cells and activated cells of the immune system. In order to locate the source of heparanase activity in the placenta, primary cytotrophoblast cultures were established. Intact cells, as well as conditioned medium and cell lysates, were analysed for heparanase activity using metabolically sulphate-labelled ECM as a natural substrate. Heparanase was highly active in lysates of cytotrophoblasts. This activity was also expressed by intact cytotrophoblasts seeded on ECM, but no activity could be detected in the culture medium. Incubation of the cytotrophoblasts in contact with ECM resulted in release of ECM-bound basic fibroblast growth factor (bFGF). We propose that the cytotrophoblastic heparanase facilitates placentation, through cytotrophoblast extravasation and localized neovascularization.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.