scholarly journals The Performance of Different Artificial Intelligence Models in Predicting Breast Cancer among Individuals Having Type 2 Diabetes Mellitus

Cancers ◽  
2019 ◽  
Vol 11 (11) ◽  
pp. 1751 ◽  
Author(s):  
Meng-Hsuen Hsieh ◽  
Li-Min Sun ◽  
Cheng-Li Lin ◽  
Meng-Ju Hsieh ◽  
Chung Hsu ◽  
...  

Objective: Early reports indicate that individuals with type 2 diabetes mellitus (T2DM) may have a greater incidence of breast malignancy than patients without T2DM. The aim of this study was to investigate the effectiveness of three different models for predicting risk of breast cancer in patients with T2DM of different characteristics. Study design and methodology: From 2000 to 2012, data on 636,111 newly diagnosed female T2DM patients were available in the Taiwan’s National Health Insurance Research Database. By applying their data, a risk prediction model of breast cancer in patients with T2DM was created. We also collected data on potential predictors of breast cancer so that adjustments for their effect could be made in the analysis. Synthetic Minority Oversampling Technology (SMOTE) was utilized to increase data for small population samples. Each datum was randomly assigned based on a ratio of about 39:1 into the training and test sets. Logistic Regression (LR), Artificial Neural Network (ANN) and Random Forest (RF) models were determined using recall, accuracy, F1 score and area under the receiver operating characteristic curve (AUC). Results: The AUC of the LR (0.834), ANN (0.865), and RF (0.959) models were found. The largest AUC among the three models was seen in the RF model. Conclusions: Although the LR, ANN, and RF models all showed high accuracy predicting the risk of breast cancer in Taiwanese with T2DM, the RF model performed best.

Author(s):  
Hui-Ju Tsai ◽  
Chia-Ying Li ◽  
Wen-Chi Pan ◽  
Tsung-Chieh Yao ◽  
Huey-Jen Su ◽  
...  

This study determines whether surrounding greenness is associated with the incidence of type 2 diabetes Mellitus (T2DM) in Taiwan. A retrospective cohort study determines the relationship between surrounding greenness and the incidence of T2DM during the study period of 2001–2012 using data from the National Health Insurance Research Database. The satellite-derived normalized difference vegetation index (NDVI) from the global MODIS database in the NASA Earth Observing System is used to assess greenness. Cox proportional hazard models are used to determine the relationship between exposure to surrounding greenness and the incidence of T2DM, with adjustment for potential confounders. A total of 429,504 subjects, including 40,479 subjects who developed T2DM, were identified during the study period. There is an inverse relationship between exposure to surrounding greenness and the incidence of T2DM after adjustment for individual-level covariates, comorbidities, and the region-level covariates (adjusted HR = 0.81, 95% CI: 0.79–0.82). For the general population of Taiwan, greater exposure to surrounding greenness is associated with a lower incidence of T2DM.


The Breast ◽  
2013 ◽  
Vol 22 ◽  
pp. S60
Author(s):  
Natalia Botnariuc ◽  
Larisa Sofroni ◽  
Vasile Jovmir ◽  
Diana Tcaciuc ◽  
Valentina Stratan ◽  
...  

2020 ◽  
Vol 2 (2) ◽  
pp. 149-157
Author(s):  
Engracia Arceo ◽  
Genevieve Dizon ◽  
Micah Angela Salunga ◽  
Madonna Valenzuela ◽  
Nestor Sibug ◽  
...  

2014 ◽  
Vol 23 (2) ◽  
pp. 76-83 ◽  
Author(s):  
Adedayo A. Onitilo ◽  
Rachel V. Stankowski ◽  
Richard L. Berg ◽  
Jessica M. Engel ◽  
Ingrid Glurich ◽  
...  

2012 ◽  
Vol 18 (5) ◽  
pp. 1246-1256 ◽  
Author(s):  
Bing Pan ◽  
Hui Ren ◽  
Yubin He ◽  
Xiaofeng Lv ◽  
Yijing Ma ◽  
...  

2019 ◽  
Vol 19 (3) ◽  
Author(s):  
Irma Yanti Rangkuti ◽  
Poppy Anjelisa Zaitun Hasibuan ◽  
Tri Widyawati ◽  
M. Ichwan

Abstrak. Latar Belakang. Kanker payudara merupakan penyakit berlebihnya pertumbuhan atau tidak terkendalinya perkembangan sel kanker payudara. Kanker merupakan suatu penyakit yang disebabkan kelainan genetik berupa mutasi DNA yang menyebakan hilangnya kontrol pertumbuhan. Gangguan genetik ini menyebabkan terganggunya siklus sel dan apoptosis. Metformin merupakan suatu antihiperglikemik yang digunakan pada pasien diabetes melitus tipe 2. Penurunan risiko kanker terjadi pada pasien diabetes melitus tipe 2 yang menggunakan metformin. Uji sitotoksik untuk agen anti kanker merupakan uji skrining awal untuk menilai potensi efek anti kanker. Tujuan penelitian ini adalah untuk mengetahui efek sitotoksik metformin hidroklorida terhadap pertumbuhan sel kanker payudara T47D. Metode: Penelitian ini merupakan penelitian eksperimental uji invitro terhadap sel kanker payudara T47D yang dipaparkan metformin HCl konsentrasi 5000; 2500; 1250; 312.5 dan 156,25 μM selama 24 jam. Sebagai pembanding digunakan paclitaxel konsentrasi 1000; 500; 250; 31,25 dan 15,625 nM. Uji sitotoksik menggunakan metode MTT untuk menentukan IC50.Data dianalaisis menggunakan analisa probit. Hasil : IC50  metformin HCl adalah 13457.3 ± 1096,5 μM. IC50 paclitaxel adalah 1577.2 ± 115.3 nM. Efek anti kanker metformin lebih kecil dibanding paclitaxel. Kata Kunci: Metformin HCl, T47D, uji sitotoksik, IC50 Abstract. Breast cancer is a disease in which there is excessive growth or uncontrolled development of breast tissue cells. Cancer is a disease caused by genetic disorders caused by DNA mutations that cause loss of growth control. This genetic disorder affects the cell cycle and cell apoptosis and causes the formation of cancer. Metformin is an antihyperglycemic in type 2 diabetes mellitus patient. The decrease in cancer risk occured in patients with type 2 diabetes mellitus who used metformin. Cytotoxic test for agent anti cancer  is screening test to investigate the potency cancer effect of substance. The goal of this study was determining the cytotoxic effect of metformin hydrochloride to T47D breast cancer cell. The method : This sudy was experimental study, invitro test to T47D breast cancer cell using metformin HCl 5000; 2500; 1250; 312.5; and 156.25 μM for 24 hours. Paclitaxel used as postiive control with concentration were 1000; 500; 250; 31,25 and 15,625 nM. Cytotoxic test using MTT method to determine IC50. Data were analyzed using probit analysis using SPSS 22 version. The result of cytotoxic test showed that IC50 metformin HCl was 13457.3 ± 1096,5 μM. While IC50 paclitaxel as control was 1577.2 ± 115.3 nM. The effect of cancer metformin HCl was lower than paclitaxel.Keywords: Metformin HCl, T47D, cytotoxic test, IC50


2019 ◽  
Vol 19 (3) ◽  
Author(s):  
Irma Yanti Rangkuti

Abstrak. Latar Belakang. Kanker payudara merupakan penyakit berlebihnya pertumbuhan atau tidak terkendalinya perkembangan sel kanker payudara. Kanker merupakan suatu penyakit yang disebabkan kelainan genetik berupa mutasi DNA yang menyebakan hilangnya kontrol pertumbuhan. Gangguan genetik ini menyebabkan terganggunya siklus sel dan apoptosis. Metformin merupakan suatu antihiperglikemik yang digunakan pada pasien diabetes melitus tipe 2. Penurunan risiko kanker terjadi pada pasien diabetes melitus tipe 2 yang menggunakan metformin. Uji sitotoksik untuk agen anti kanker merupakan uji skrining awal untuk menilai potensi efek anti kanker. Tujuan penelitian ini adalah untuk mengetahui efek sitotoksik metformin hidroklorida terhadap pertumbuhan sel kanker payudara T47D. Metode: Penelitian ini merupakan penelitian eksperimental uji invitro terhadap sel kanker payudara T47D yang dipaparkan metformin HCl konsentrasi 5000; 2500; 1250; 312.5 dan 156,25 μM selama 24 jam. Sebagai pembanding digunakan paclitaxel konsentrasi 1000; 500; 250; 31,25 dan 15,625 nM. Uji sitotoksik menggunakan metode MTT untuk menentukan IC50.Data dianalaisis menggunakan analisa probit. Hasil : IC50  metformin HCl adalah 13457.3 ± 1096,5 μM. IC50 paclitaxel adalah 1577.2 ± 115.3 nM. Efek anti kanker metformin lebih kecil dibanding paclitaxel. Kata Kunci: Metformin HCl, T47D, uji sitotoksik, IC50 Abstract. Breast cancer is a disease in which there is excessive growth or uncontrolled development of breast tissue cells. Cancer is a disease caused by genetic disorders caused by DNA mutations that cause loss of growth control. This genetic disorder affects the cell cycle and cell apoptosis and causes the formation of cancer. Metformin is an antihyperglycemic in type 2 diabetes mellitus patient. The decrease in cancer risk occured in patients with type 2 diabetes mellitus who used metformin. Cytotoxic test for agent anti cancer  is screening test to investigate the potency cancer effect of substance. The goal of this study was determining the cytotoxic effect of metformin hydrochloride to T47D breast cancer cell. The method : This sudy was experimental study, invitro test to T47D breast cancer cell using metformin HCl 5000; 2500; 1250; 312.5; and 156.25 μM for 24 hours. Paclitaxel used as postiive control with concentration were 1000; 500; 250; 31,25 and 15,625 nM. Cytotoxic test using MTT method to determine IC50. Data were analyzed using probit analysis using SPSS 22 version. The result of cytotoxic test showed that IC50 metformin HCl was 13457.3 ± 1096,5 μM. While IC50 paclitaxel as control was 1577.2 ± 115.3 nM. The effect of cancer metformin HCl was lower than paclitaxel. Keywords: Metformin HCl, T47D, cytotoxic test, IC50


2019 ◽  
Author(s):  
Yun-Ju Lai ◽  
Yu-Yen Chen ◽  
Li-Jung Chen ◽  
Po-Wen Ku ◽  
Kuo-Chuan Hung ◽  
...  

Abstract Background: Using animal models and molecular biology researches, hyperuricemia has been shown to instruct renal arteriolopathy, arterial hypertension, and microvascular injury involving the renin-angiotensin system and resulting in renal function impairment. Nevertheless, the association between uric acid levels and the development of macroalbuminuria has been under-investigated in people with type 2 diabetes mellitus. Methods: Patients with type 2 diabetes and regular outpatient visits were recruited from a community hospital in Taiwan since January 2014. Demographics, lifestyle features, and medical history were gathered by well-trained interviewers. All participants underwent comprehensive physical examinations, including a biochemical assay of venous blood specimens and urine samples after an 8-hour overnight fast. Participants were followed until June 2018. The primary outcome was the macroalbuminuria incidence. Univariable and multivariable Cox regression analysis were employed to explore the relation between uric acid and incident macroalbuminuria. Uric acid cutoffs for incident macroalbuminuria were determined with the receiver operator characteristic curve. Results: We included 247 qualified subjects (mean age: 64.78 years old [standard deviation=11.29 years]; 138 [55.87%] men). During a 4.5-year follow-up duration, 20 subjects with incident macroalbuminuria were recognized. Serum uric acid was significantly associated with an increased risk of incident macroalbuminuria (adjusted hazard ratio=2.39; 95% confidence interval: 1.53-3.75; p<0.001) with potential confounders adjustment. The uric acid cutoff point was 6.9 mg/dL (area under the curve 0.708, sensitivity 60.0%, specificity 84.58%) for incident macroalbuminuria. Conclusions: Serum uric acid was associated with incident macroalbuminuria among people with type 2 diabetes.


2020 ◽  
Author(s):  
Yu-Cheng Kao ◽  
Tien-Hsing Chen ◽  
Chi-Hung Liu ◽  
Jawl-Shan Hwang ◽  
Ching-Chung Hsiao ◽  
...  

Abstract Background: Atorvastatin 40mg (ATOR 40) and ezetimibe 10mg/simvastatin 20mg (EZ-SIM 20) have comparable reductions of low-density lipoprotein cholesterol (LDL-C) but cardiovascular (CV) outcomes between these two therapies are unclear. Our real-world cohort study is to test the hypothesis of pleiotropic effects of purely higher dose statin on CV outcomes beyond comparable reductions of LDL-C, especially for extremely CV risk patients.Methods: Between January 1, 2007 and December 31, 2013, a total of 3372 patients with type 2 diabetes mellitus (T2DM) admitted due to acute coronary syndrome (ACS) or acute ischemic stroke (AIS) were selected as the study cohort from the Taiwan National Health Insurance Research Database. Clinical outcomes were evaluated by ATOR 40 group (n=1686) matched with EZ-SIM 20 group (n=1686). Primary composite outcome includes CV death, non-fatal myocardial infarction, and non-fatal stroke. Secondary composite outcome includes hospitalization for unstable angina (HUA), percutaneous coronary intervention (PCI), and coronary artery bypass grafting (CABG).Results: With a mean follow-up of 2.4 years, no significant difference of primary composite outcome was observed between ATOR 40 and EZ-SIM 20 groups (subdistribution hazard ratio [SHR], 1.09; 95% confidence interval [CI], 0.95–1.25). Nevertheless, ATOR 40 group had lower risks of HUA (SHR, 0.50; 95% CI, 0.35–0.72), PCI (SHR, 0.82; 95% CI, 0.69–0.97) and CABG (SHR, 0.62; 95% CI, 0.40–0.97) than EZ-SIM 20 group.Conclusions: For T2DM patients after ACS or AIS, ATOR 40 may have lower risks of HUA, PCI and CABG than EZ-SIM 20.


2020 ◽  
Vol 2020 ◽  
pp. 1-12 ◽  
Author(s):  
Yu-Pei Fan ◽  
Chien-Tung Wu ◽  
Jiun-Lu Lin ◽  
Chao A. Hsiung ◽  
Hsiao Yu Liu ◽  
...  

Purpose. To assess the relationship between metformin use and the severity of diabetic retinopathy (DR) in patients with type 2 diabetes mellitus (T2DM) and to investigate the effect of metformin dosage on reducing the incidence of DR. Methods. The study population included patients with newly diagnosed T2DM, who were aged ≥20 years and prescribed with antidiabetic drug therapy lasting ≥90 days, as identified using the National Health Insurance Research Database between 2000 and 2012. We matched metformin users and nonusers by a propensity score. Cox proportional hazard regression analyses were used to compute and compare the risk of developing nonproliferative diabetic retinopathy (NPDR) in metformin users and nonusers. Results. Overall, 10,044 T2DM patients were enrolled. Metformin treatment was associated with a lower risk of NPDR (aHR 0.76, 95% CI 0.68–0.87) and sight-threatening diabetic retinopathy (STDR, aHR 0.29, 95% CI 0.19–0.45); however, the reduction in risk was borderline significant for STDR progression among NPDR patients (aHR 0.54, 95% CI 0.28–1.01). Combination therapy of metformin and DPP-4i exhibited a stronger but inverse relationship with NPDR development (aHR 0.32, 95% CI 0.25–0.41), especially at early (<3 months) stages of metformin prescription. These inverse relationships were also evident at different metformin doses and in adapted Diabetes Complications Severity Index scores (aDCSI). Moreover, combination therapy of metformin with sulfonylureas was associated with an increased risk of NPDR. Conclusion. Metformin treatment in patients with T2DM was associated with a reduced risk of NPDR, and a potential trend was found for a reduced STDR risk in patients who had previously been diagnosed with NPDR. Combining metformin with DPP-4i seemingly had a significantly beneficial effect against NPDR risk, particularly when aDCSI scores were low, and when metformin was prescribed early after T2DM diagnosis. These results may recommend metformin for early treatment of T2DM.


Sign in / Sign up

Export Citation Format

Share Document