scholarly journals Establish a predictive model for high-risk de novo metastatic prostate cancer patients by machine learning.

2019 ◽  
Vol 5 (suppl) ◽  
pp. 13-13
Author(s):  
Po-Jung SU ◽  
Yu-Ann Fang ◽  
Yung-Chun Chang ◽  
Yung-Chia Kuo ◽  
Yung-Chang Lin
Keyword(s):  
Prostate Cancer ◽  
Machine Learning ◽  
High Risk ◽  
Cancer Patients ◽  
Metastatic Prostate Cancer ◽  
De Novo ◽  
Risk Group ◽  
High Risk Group ◽  
Recursive Feature Elimination ◽  
Risk Patients

13 Background: For de novo metastatic prostate cancer (mPC)) patients, their prognosis may be really different. Some of these patients response very well to hormone therapy with durable survival, but others may be not. For those poor prognosis patients, if we could predict them as high risk patients when diagnosed, and provide aggressive upfront chemotherapy or novel hormonal therapy, they might get better treatment outcomes. Methods: We used data of prostate cancer patients from 2000 to 2016 in Chang Gung Research Database. There are 799 de novo mPC patients with castration. We predicted the possibility for these patients progressed to metastatic castration-resistant prostate cancer (mCRPC) in 1 year and find the high risk group patients. Then we figured out the best features for prediction from the best classifier with Recursive Feature Elimination. Results: The de nove mPC patients who pregressed to mCRPC in 1 year, whose mOS is 21.9 months is worse than who progressed to mCRPC beyond 1 year significantly, whose mOS is 80.7 months. (adjusted hazard ratio[aHR]: 6.43, P<0.001). The overall performance of machine learning by XGBoost is the best in all predictive models for high risk patients. (AUC=0.7000, Accuracy=0.7143). We excluded the features with missing data over 50%, then put all other features in the model. (AUC=0.7042, Accuracy=0.7239). But we got the best performance with only 11 features, including age, time from diagnosis to castration, nadir PSA, hemoglobin, eosinophil/white blood cell ratio, alkaline phosphatase, alanine transaminase, blood urea nitrogen, creatinine, prothrombin time, and secondary primary cancer, by Recursive Feature Elimination. (AUC=0.7131, Accuracy=0.7267). Conclusions: We found the predictive model has better predictive accuracy and shorter manuscript time with less features selected by Recursive Feature Elimination.We can predict high risk group in de novo mPC patients and make better clinical decision for treatment with this XGBoost model.

Revision of CHAARTED and LATTITUDE criteria among Japanese de novo metastatic prostate cancer patients.

2020 ◽  
Vol 38 (6_suppl) ◽  
pp. 132-132
Author(s):  
Shinichi Sakamoto ◽  
Yasutaka Yamada ◽  
Junryo Rii ◽  
Satoshi Yamamoto ◽  
Shuhei Kamada ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Risk Factors ◽  
High Risk ◽  
Cancer Patients ◽  
Metastatic Prostate Cancer ◽  
De Novo ◽  
Japanese Cohort ◽  
Significant Difference ◽  
Risk Patients ◽  
Independent Risk Factors

132 Background: Based on the high response rate to the standard androgen deprivation therapy (ADT), the Japanese cohort in LATTITUDE study failed to show the survival benefit by early Abiraterone. In order to identify the "true high-risk" patients, we studied the prognostic factors among Japanese de novo metastatic prostate cancer patients who fit CHAARTED and LATITUDE criteria. Methods: We retrospectively studied patients who fit CHAARTED (292 patients) and LATITUDE (294 patients) criteria from Japanese multi-institutions. All patients received ADT with bicalutamide as an initial treatment. Factors related to overall survival (OS) and progression-free survival (PFS) were statistically analyzed. Results: The median OS was 56 mo and 57 mo in patients who met the CHAARTED and the LATITUDE criteria, respectively. In patients who met CHAARTED criteria, LDH (HR2.6, p < 0.00001) and CRP (HR1.7, p = 0.042) were independent risk factors for OS. In patients who met LATTITUDE criteria, GS≥9 (HR1.7, p = 0.0378) and LDH (HR2.9, p < 0.0001) were independent risk factors for OS. Modified CHAARTED criteria by adding LDH and CRP showed a significant difference in OS (HR2.8, p < 0.0001) with a comparative median OS (30 mo) to placebo of CHAARTED trial (32 mo). Modified LATTITUDE criteria by adding GS≥9 and LDH, showed a significant difference in OS (HR2.7, p < 0.0001) with a comparative median OS (33 mo) to placebo of LATTITUDE trial (34 mo). Conclusions: Modified criteria may potentially elucidate the true "high-volume" and "high-risk" patients in the Japanese cohort who require early intensive therapy.[Table: see text]

scholarly journals Optimizing External Beam Radiotherapy as per the Risk Group of Localized Prostate Cancer: A Nationwide Multi-Institutional Study (KROG 18-15)

Cancers ◽  
2021 ◽  
Vol 13 (11) ◽  
pp. 2732
Author(s):  
Seo Hee Choi ◽  
Young Seok Kim ◽  
Jesang Yu ◽  
Taek-Keun Nam ◽  
Jae-Sung Kim ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
High Risk ◽  
Cancer Patients ◽  
Predictive Power ◽  
Risk Group ◽  
External Beam Radiotherapy ◽  
High Risk Group ◽  
Risk Classification ◽  
Low Risk ◽  
External Beam

Purpose: This nationwide multi-institutional study analyzed the patterns of care and outcomes of external beam radiotherapy (EBRT) in localized prostate cancer patients. We compared various risk classification tools and assessed the need for refinements in current radiotherapy (RT) schemes. Methods and Materials: We included non-metastatic prostate cancer patients treated with primary EBRT from 2001 to 2015 in this study. Data of 1573 patients from 17 institutions were analyzed and re-grouped using a risk stratification tool with the highest predictive power for biochemical failure-free survival (BCFFS). We evaluated BCFFS, overall survival (OS), and toxicity rates. Results: With a median follow-up of 75 months, 5- and 10-year BCFFS rates were 82% and 60%, and 5- and 10-year OS rates were 95% and 83%, respectively. NCCN risk classification revealed the highest predictive power (AUC = 0.556, 95% CI 0.524–0.588; p < 0.001). Gleason score, iPSA < 12 ng/mL, intensity-modulated RT (IMRT), and ≥179 Gy1.5 (EQD2, 77 Gy) were independently significant for BCFFS (all p < 0.05). IMRT and ≥179 Gy1.5 were significant factors in the high-risk group, whereas ≥170 Gy1.5 (EQD2, 72 Gy) was significant in the intermediate-risk group and no significant impact of dose was observed in the low-risk group. Both BCFFS and OS improved significantly when ≥179 Gy1.5 was delivered using IMRT and hypofractionation in the high-risk group without increasing toxicities. Conclusions: With NCCN risk classification, dose escalation with modern high-precision techniques might increase survivals in the high-risk group, but not in the low-risk group, although mature results of prospective studies are awaited.

Long-term outcomes of intensity-modulated radiation therapy combined with neoadjuvant hormonal therapy for Japanese patients with non-metastatic prostate cancer.

2018 ◽  
Vol 36 (6_suppl) ◽  
pp. 49-49
Author(s):  
Rihito Aizawa ◽  
Kenji Takayama ◽  
Kiyonao Nakamura ◽  
Takahiro Inoue ◽  
Takashi Kobayashi ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
High Risk ◽  
Metastatic Prostate Cancer ◽  
Risk Group ◽  
Intensity Modulated Radiation Therapy ◽  
Japanese Patients ◽  
High Risk Group ◽  
Long Term Outcomes ◽  
Very High

49 Background: This study aimed to evaluate long-term outcomes of intensity-modulated radiation therapy (IMRT) combined with neoadjuvant (NA) hormonal therapy (HT) in Japanese patients with non-metastatic prostate cancer (NMPC). Methods: We retrospectively analyzed the data of 485 patients with T1-T4N0M0 adenocarcinoma of the prostate treated with IMRT combined with NA-HT. Of these patients, 32, 113, 250, and 90 patients were categorized into the low-, intermediate-, high-, and very high-risk groups, respectively, according to the NCCN risk classification. NA-HT was administered over a median duration of 6 months. In principle, 74 or 78 Gy in 2 Gy per-fraction were delivered to the prostate and seminal vesicles according to the risk. We did not administer adjuvant HT (A-HT) for any patient following the completion of IMRT. Salvage HT (S-HT) commenced when prostate-specific antigen (PSA) values exceeded 4 ng/mL. Results: The median follow-up period was 103.4 months, and the median PSA value at the initiation of S-HT was 5.1 ng/mL. In the low-risk group, the 8-year biochemical relapse-free survival, prostate cancer-specific survival, overall survival, and S-HT-free (SHTF) rates were 89.7%, 100.0%, 100.0%, and 96.7%, respectively. Those were 83.7%, 100.0%, 96.0%, and 94.3% for the intermediate-risk group, 64.5%, 97.8%, 87.0%, and 79.4% for the high-risk group, and 47.7%, 96.6%, 89.7%, and 53.3% for the very high-risk group, respectively. The estimated 8-year cumulative incidence rates of late gastrointestinal and genitourinary (grades 2–3) toxicity were 7.2% and 21.8%, respectively. We observed no grade 4 or higher toxicity. Conclusions: High-dose IMRT, combined with NA-HT and without A-HT under the early S-HT policy, achieved excellent survival outcomes with acceptable morbidities for a Japanese cohort with NMPC. Moreover, especially for high, and very high-risk patients, this approach could be a viable alternative to the uniform provision of long-term A-HT because more than the half of the patients maintained SHTF status over a period of 8-year after IMRT. Prospective trials are warranted to validate the findings of this study.

Clinical impact of LncRNA XIST and LncRNA NEAT1 for diagnosis of high-risk group breast cancer patients

2021 ◽  
pp. 100709
Author(s):  
Menha Swellam ◽  
Hekmat M EL Magdoub ◽  
May A Shawki ◽  
Marwa Adel ◽  
Mona M Hefny ◽  
...  
Keyword(s):  
Breast Cancer ◽  
High Risk ◽  
Cancer Patients ◽  
Risk Group ◽  
High Risk Group ◽  
Clinical Impact ◽  
Breast Cancer Patients ◽  
Lncrna Xist ◽  
Lncrna Neat1

scholarly journals Echocardiography and EuroSCORE II for the stratification of low-gradient severe aortic stenosis and preserved left ventricular ejection fraction

2021 ◽  
Author(s):  
Yan Fan ◽  
Hong Shen ◽  
Brandon Stacey ◽  
David Zhao ◽  
Robert J. Applegate ◽  
...  
Keyword(s):  
High Risk ◽  
Left Ventricular Ejection Fraction ◽  
Risk Group ◽  
Severe Aortic Stenosis ◽  
Left Ventricular ◽  
High Risk Group ◽  
Low Risk ◽  
Left Ventricular Ejection ◽  
Ventricular Ejection Fraction ◽  
Risk Patients

AbstractThe purpose of this study was to explore the utility of echocardiography and the EuroSCORE II in stratifying patients with low-gradient severe aortic stenosis (LG SAS) and preserved left ventricular ejection fraction (LVEF ≥ 50%) with or without aortic valve intervention (AVI). The study included 323 patients with LG SAS (aortic valve area ≤ 1.0 cm2 and mean pressure gradient < 40 mmHg). Patients were divided into two groups: a high-risk group (EuroSCORE II ≥ 4%, n = 115) and a low-risk group (EuroSCORE II < 4%, n = 208). Echocardiographic and clinical characteristics were analyzed. All-cause mortality was used as a clinical outcome during mean follow-up of 2 ± 1.3 years. Two-year cumulative survival was significantly lower in the high-risk group than the low-risk patients (62.3% vs. 81.7%, p = 0.001). AVI tended to reduce mortality in the high-risk patients (70% vs. 59%; p = 0.065). It did not significantly reduce mortality in the low-risk patients (82.8% with AVI vs. 81.2%, p = 0.68). Multivariable analysis identified heart failure, renal dysfunction and stroke volume index (SVi) as independent predictors for mortality. The study suggested that individualization of AVI based on risk stratification could be considered in a patient with LG SAS and preserved LVEF.

Accuracy of the CARG chemotherapy toxicity risk prediction tool in older Indian patients with cancer.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e24023-e24023
Author(s):  
Shreya Gattani ◽  
Vanita Noronha ◽  
Anant Ramaswamy ◽  
Renita Castelino ◽  
Vandhita Nair ◽  
...  
Keyword(s):  
High Risk ◽  
Cancer Patients ◽  
Risk Prediction ◽  
Risk Group ◽  
High Risk Group ◽  
Low Risk ◽  
Chemotherapy Toxicity ◽  
Patients With Cancer ◽  
Indian Patients ◽  
Grade 3

e24023 Background: Clinical judgement alone is inadequate in accurately predicting chemotherapy toxicity in older adult cancer patients. Hurria and colleagues developed and validated, the CARG score (range, 0–17) as a convenient and reliable tool for predicting chemotherapy toxicity in older cancer patients in America, however, its applicability in Indian patients is unknown. Methods: An observational retrospective and prospective study between 2018 and 2020 was conducted in the Department of Medical Oncology at Tata Memorial Hospital, Mumbai, India. The study was approved by the institutional ethics committee (IEC-III; Project No. 900596) and registered in the Clinical Trials Registry of India (CTRI/2020/04/024675). Written informed consent was obtained in the prospective part of the study. Patients aged ≥ 60 years and planned for systemic therapy were evaluated in the geriatric oncology clinic and their CARG score was calculated. Patients were stratified into low (0-4), intermediate (5-9) and high risk (10-17) based on the CARG scores. The CARG score was provided to the treating physicians, along with the results of the geriatric assessment. Chemotherapy-related toxicities were captured from the electronic medical record and graded as per the NCI CTCAE, version 4.0. Results: We assessed 130 patients, with a median age 69 years (IQR, 60 to 84); 72% patients were males. The common malignancies included gastrointestinal (52%) and lung (30%). Approximately 78% patients received polychemotherapy and 53% received full dose chemotherapy. Based on the CARG score, 28 (22%) patients belonged to low risk, 80 (61%) to intermediate risk and 22 (17%) to the high risk category. The AU-ROC of the CARG score in predicting grade 3-5 toxicities was 0.61 (95% CI, 0.51-0.71). The sensitivity and specificity of the CARG score in predicting grade 3-5 toxicities were 60.8% and 78.6%. Grade 3-5 toxicities occurred in 6/28 patients (21%) in the low risk group, compared to 62/102 patients (61%) in the intermediate /high risk group, p = 0.0002. There was also a significant difference in the time to development of grade 3-5 toxicities, which occurred at a median of 2.5 cycles (IQR, 1-3.8) in the intermediate /high risk group and at a median of 6 cycles (IQR, 3.5-8) in the low risk group, p = 0.0011. Conclusions: In older Indian patients with cancer, the CARG score reliably stratifies patients into low risk and intermediate/high risk categories, predicting both the occurrence and the time to occurrence of grade 3-5 toxicities from chemotherapy. The CARG score may aid the oncologist in estimating the risk-benefit ratio of chemotherapy. An important limitation was that we provided the CARG score to the treating oncologists prior to the start of chemotherapy, which may have resulted in alterations in the chemotherapy regimen and dose and may have impacted the CARG risk prediction model. Clinical trial information: CTRI/2020/04/024675.

scholarly journals Pre-hospital risk assessment in suspected non-ST-elevation acute coronary syndrome: A prospective observational study

2018 ◽  
Vol 9 (1_suppl) ◽  
pp. 5-12 ◽  
Author(s):  
Dominique N van Dongen ◽  
Rudolf T Tolsma ◽  
Marion J Fokkert ◽  
Erik A Badings ◽  
Aize van der Sluis ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
High Risk ◽  
Risk Stratification ◽  
Risk Group ◽  
High Risk Group ◽  
Low Risk ◽  
Heart Score ◽  
Coronary Syndrome ◽  
Risk Patients ◽  
St Elevation

Background: Pre-hospital risk stratification of non-ST-elevation acute coronary syndrome (NSTE-ACS) by the complete HEART score has not yet been assessed. We investigated whether pre-hospital risk stratification of patients with suspected NSTE-ACS using the HEART score is accurate in predicting major adverse cardiac events (MACE). Methods: This is a prospective observational study, including 700 patients with suspected NSTE-ACS. Risk stratification was performed by ambulance paramedics, using the HEART score; low risk was defined as HEART score ⩽ 3. Primary endpoint was occurrence of MACE within 45 days after inclusion. Secondary endpoint was myocardial infarction or death. Results: A total of 172 patients (24.6%) were stratified as low risk and 528 patients (75.4%) as intermediate to high risk. Mean age was 53.9 years in the low risk group and 66.7 years in the intermediate to high risk group ( p<0.001), 50% were male in the low risk group versus 60% in the intermediate to high risk group ( p=0.026). MACE occurred in five patients in the low risk group (2.9%) and in 111 (21.0%) patients at intermediate or high risk ( p<0.001). There were no deaths in the low risk group and the occurrence of acute myocardial infarction in this group was 1.2%. In the high risk group six patients died (1.1%) and 76 patients had myocardial infarction (14.4%). Conclusions: In suspected NSTE-ACS, pre-hospital risk stratification by ambulance paramedics, including troponin measurement, is accurate in differentiating between low and intermediate to high risk. Future studies should investigate whether transportation of low risk patients to a hospital can be avoided, and whether high risk patients benefit from immediate transfer to a hospital with early coronary angiography possibilities.

scholarly journals Saliva pH Changes in Patients with High and Low Caries Risk After Consuming Organic (Sucrose) and Non-Organic (Maltitol) Sugar

2020 ◽  
Vol 12 (2) ◽  
Author(s):  
Widowati W ◽  
Akbar SH ◽  
Tin MH
Keyword(s):  
High Risk ◽  
Risk Group ◽  
High Risk Group ◽  
Low Risk ◽  
Caries Risk ◽  
Ph Changes ◽  
Ph Values ◽  
High Caries Risk ◽  
Risk Patients ◽  
Snack Consumption

Introduction: Enamel demineralization is associated with decrease in saliva pH due to fermentation of sugar by oral commensal. Thus, exploring the changing pattern of saliva pH is meaningful in dental caries prevention. The aim of this study was to compare the changing pattern of saliva pH after consuming different types of sweeteners (sucrose and maltitol). Methods: It was a case-control study involving 14 male patients attending IIUM dental clinic who were selected with the intention of getting seven patients with high caries risk ( DMFT ≥6) and seven patients with low caries risk (DMFT ≤3) with initial saliva pH interval of 6.5 to7.5. Patients were asked to consume snacks containing 8 gram sucrose and 8 gram maltitol as sweeteners. The changing pH values of the saliva were measured by Waterproof pHTestr 10BNC (Oakton, Vernon Hills, USA) seven times consecutively at 0 (before snack consumption), and at 5, 10, 15, 20, 30 and 60 minutes after snack consumption. The pH values of saliva of patients with low and high caries risk after consuming sucrose and maltitol were statistically analized by using Anova and Tukey-HSD tests at α = 0.05. Result: There were significant differences in saliva pH changes between low-risk group and high-risk group after consuming sucrose and maltitol. Conclusion: The changing patterns of saliva pH in high-risk patients were lower than those of low-risk patients after consuming two types of snacks containing sucrose and maltitol.

Adjuvant Chemotherapy Guidance for pT1-3N0-1 Breast Cancer Patients with HR+, HER2- subtype: a study based on SEER database

2021 ◽  
Author(s):  
juanjuan Qiu ◽  
Li Xu ◽  
Yu Wang ◽  
Jia Zhang ◽  
Jiqiao Yang ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Prognostic Factors ◽  
High Risk ◽  
Cancer Patients ◽  
Risk Group ◽  
High Risk Group ◽  
Low Risk ◽  
Rank Test ◽  
Breast Cancer Patients ◽  
Group Score

Abstract Background Although the results of gene testing can guide early breast cancer patients with HR+, HER2- to decide whether they need chemotherapy, there are still many patients worldwide whose problems cannot be solved well by genetic testing. Methods 144 735 patients with HR+, HER2-, pT1-3N0-1 breast cancer from the Surveillance, Epidemiology, and End Results database were included from 2010 to 2015. They were divided into chemotherapy (n = 38 392) and no chemotherapy (n = 106 343) group, and after propensity score matching, 23 297 pairs of patients were left. Overall survival (OS) and breast cancer-specific survival (BCSS) were tested by Kaplan–Meier plot and log-rank test and Cox proportional hazards regression model was used to identify independent prognostic factors. A nomogram was constructed and validated by C-index and calibrate curves. Patients were divided into high- or low-risk group according to their nomogram score using X-tile. Results Patients receiving chemotherapy had better OS before and after matching (p < 0.05) but BCSS was not significantly different between patients with and without chemotherapy after matching: hazard ratio (HR) 1.005 (95%CI 0.897, 1.126). Independent prognostic factors were included to construct the nomogram to predict BCSS of patients without chemotherapy. Patients in the high-risk group (score > 238) can get better OS HR 0.583 (0.507, 0.671) and BCSS HR 0.791 (0.663, 0.944) from chemotherapy but the low-risk group (score ≤ 238) cannot. Conclusion The well-validated nomogram and a risk stratification model was built. Patients in the high-risk group should receive chemotherapy while patients in low-risk group may be exempt from chemotherapy.

Sign in / Sign up

Export Citation Format

Share Document