Abstract 1944: Prognostic biomarkers for gallbladder cancer: A machine learning approach
Linsey JacksonLoretta AlloteyValles KennethGavin R. OliverAsha NairD. O’BrienRondell P. GrahamMitesh J. BoradArjun P. AthreyaLewis R. Roberts
1
Citation
0
Reference
10
Related Paper
Citation Trend
Abstract:
Abstract Gallbladder cancer (GBC) is one of the deadliest cancers, with a 5-year-survival-rate of less than 5 percent for late-stage disease. The response rate to chemotherapy among GBC patients is generally poor. Recent research has attempted to identify diagnostic, prognostic, and predictive biomarkers, however, currently, no biomarkers can accurately diagnose GBC and predict patients’ prognosis. Integrative analysis of molecular and clinical characterization has not been fully established, and minimal improvement has been made to the survival of these patients, in part due to the heterogeneity of GBC. Machine learning techniques have been proven to empower analysis of big data in oncology, allowing for improvement in the generation of biomarkers to predict patient outcomes. Using machine learning, we can utilize high-throughput RNA sequencing with clinicopathologic data to develop a predictive tool for GBC prognosis. Current predictive models for GBC outcomes often utilize clinical data only, with the highest C-statistic reported being 0.71. C-statistic values over 0.7 generally indicate good models, however 0.8 is the threshold for strong predictive models. We aim to build a superior algorithm to predict overall survival in GBC patients with advanced disease, using machine learning approaches to prioritize biomarkers for GBC prognosis. We have identified over 80 fresh frozen GBC tissue samples from Mayo Clinic Rochester, Dongsan Medical Center in Daegu, Korea, University of the Witwatersrand, in Johannesburg, South Africa, Lithuanian University of Health Science in Vilnius, Lithuania, and University of Calgary in Calgary, Canada, from patients enrolled between 2012 and 2021. We will perform next-generation RNA sequencing on these tissue samples. The patients’ clinical, pathologic and survival data will be abstracted from the medical record uniformly across sites. Feature engineering and dimensionality reduction will be performed. Then random forests, support vector machines, and gradient boosting machines will be applied to train the data. Variable importance will prioritize multi-omic markers. Standard 5-fold cross validation will be used to assess performance of each ML algorithm. If overall survival can be better predicted with the addition patients’ transcriptional sequencing data compared to using clinical profiles alone, we can gain a greater understanding of key biomarkers driving the tumor phenotype. Citation Format: Linsey Jackson, Loretta Allotey, Valles Kenneth, Gavin Oliver, Asha Nair, Daniel O'Brien, Rondell Graham, Mitesh Borad, Arjun Athreya, Lewis Roberts. Prognostic biomarkers for gallbladder cancer: A machine learning approach [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 1944.Keywords:
Gallbladder Cancer
Predictive modelling
CTによる膀胱腫瘍浸潤度判定をより客観的なものとする目的で, 新たに理想膀胱外壁線および腫瘍根部径 (W)-縦径 (H) 比を設定して各浸潤度別に比較検討し, 以下の検討結果をえた. (1) CTによる形態診断で, 小乳頭状型, 乳頭状有茎性型, 乳頭状無茎性型を示したものはすべて Stage B1以下であつた. 広基結節型を示した23例中19例は, CTによる判定通り広基結節型 Stage B2以上であつたが, 残りの4例は摘出標本では乳頭状無茎性型 Stage B1であつた. (2) 体位変換時の腫瘍変位性は, 乳頭状有茎性型形態を示したもののみに認められ, そのすべてが Stage B1以下であつた. (3) 理想膀胱外壁線外への腫瘍突出は広基結節型を示した Stage C 以上の全例に認められた. また, 従来膀胱壁外には突出しないとされてきた Stage B2の6例中4例に認められた. 突出した腫瘍根部の外壁を比較すると Stage B2ではその突出部の性状は平滑であつたが, Stage C 以上の場合は不整であつた. (4) W/H比に関しては, 乳頭状型を呈した Stage B1以下と広基結節型を呈した Stage B2以上は1.2で明瞭に判別できた.以上より作成したCTによる膀胱腫瘍浸潤度判定基準により, Stage B1以下では37例中26例 (70%), Stage B2以上では19例中16例 (84%). 特に膀胱内注入物質として空気を用いた場合, Stage B2以上において15例中15例 (100%) と非常に高い一致率が得られた.本判定基準による膀胱腫瘍浸潤度のCT診断は, 従来は極めて困難であつた深層浸潤性腫瘍の各 Stage の判別診断を可能とし, 臨床上極めて有用なものと考える.
Cite
Citations (0)
Abstract
Cite
Citations (0)
Predictive modelling
Strengths and weaknesses
Guideline
Cite
Citations (12)
Guru-shishya parampara (with due respect to its importance as an established form of knowledge-transfer system and its historical references) is in a way a register of a life-cycle of a trained (neo-classical) dancer. This system has a history of exchange for those specialists who claim the designation of a guru and all who register themselves as shishya under specific gurus. This chapter attempts a critical understanding of the so-called sacred duty of transmission of knowledge as a wat to ensure livelihood and survival. With the help of the case study of Amala Shankar (1919–2020) and her modern institution, the chapter looks at the Uday Shankar India Culture Centre as the alternate space for creating a value for the system of knowledge transfer beyond the traditional guru-shishya parampara.
Cite
Citations (0)
Heart disease is a major cause of death worldwide, making early diagnosis and prevention essential. Predictive models have gained significant attention in recent years, with several algorithms being employed to develop these models. However, there are challenges in implementing heart disease prediction models, including data quality, model accuracy, ethical concerns, and limited data. Therefore, this project aims to develop a heart disease prediction model and analyse different algorithms used in disease prediction. In order to increase the predictive accuracy of machine learning algorithms, this study compares six algorithms, including KNN (K-Nearest Neighbour), Decision Tree, Random Forest, Support Vector Machines, Logistic Regression, and Neural Network. 13 attributes, including age, sex, and cholesterol, are used, and ensemble methods like boosting and bagging are used. The accuracy, recall, f1 score, and precision of each algorithm are calculated to determine the most accurate model. Additionally, this study identifies the limitations of heart disease prediction models and their implications for patient diagnosis and treatment, by developing and analysing heart disease prediction models. In conclusion, while heart disease prediction models have the potential to be financially feasible and be useful in the future, their current limitations and challenges mean that they cannot be relied upon as the sole means of diagnosis or treatment decisions Key Words: Heart Diseases, Machine Learning Algorithms, Logistic Regression, Random Forest, Decision Tree.
Predictive modelling
Boosting
Ensemble Learning
Cite
Citations (1)
This research paper addresses the problem of machine systems' failure prediction. This work is innovative in that it uses machine learning approaches to create a failure prediction model that is accurate for prognostic health management (PHM) in all machine systems: vibration based, and non-vibration based. The authors have employed a variety of well-known machine learning methods: Naïve Bayes (NB), Generalized Linear Model (GLM), Logistic Regression (LR), Decision Trees (DT), Random Forests (RF), and Gradient Boosted Tree (GBT) on Machine Predictive Maintenance Classification Dataset available on Kaggle. DT has given the highest accuracy i.e., 97.3%. The research paper offered insightful information about the suitability of various classifiers for failure prediction in machine systems and highlighted the best-performing classifier among the examined ones based on their predictive accuracy, enabling practitioners in PHM to make well-informed decisions.
Predictive modelling
Cite
Citations (0)
Third stage
Cite
Citations (56)
Cite
Citations (0)
地方性甲状腺腫は臨床, 病理学的に複雑な経過を示し, 疫学的, 病理学的発生論や治療の選択に多くの難題が残されている. 著者は本症の病期検討および妥当な病期分類がこれらの検索, 解明にきわめて有用であると着目し, 甲状腺剔出を行なった地方性甲状腺腫336例を臨床, 病理学的に精査し下記の結果をえた. 1) 地方性甲状腺腫は臨床的, 病理学的経過からStage 1;過形成期, Stage 2;腫大期, Stage 3;結節形成期と分類できた. 2) 本症は病期の進行に伴い病悩期間は長くなり, 甲状腺腫は増大し種々の局所圧迫症状をみるが, 合併症がなければ全身的, 臨床生化学的所見はほぼ正常である. 3) 臨床, 病理学的に本症はStage 1からStage 2さらにStage 3に進行し, Stage 3は終末期である. 4) 病変の占居部位はStage 1では両葉性, Stage 2では両葉性と単葉性がほぼ等しく, Stage 3では単葉性が多い点からもStageの進行度を裏付けられる. 5) 336例のうち男性39例, 女性297例, 男女比1:7.6で, 発生のピークは女性では20才から30才代, 男性は30才から40才代であった. 6) 手術適応例は若年者より成人に多く, 女性は男性より著しく多い. ヨード治療の効果が若年者ほど良好で, 男性は女性よりもヨード感受性が高いためである. 7) Stage 3の9.4%に甲状腺機能亢進症 (4.03%), 腺腫 (1.34%), 甲状腺癌 (4.03%) などの共存疾患がみられた. 8) ヨード治療はStage 1では効果的であるがStage 2では無効でStage 3に進行し, 種々の合併症を起こすこともあり, Stage 2における手術が望ましい.
Cite
Citations (0)
腎細胞癌50例 (stage 1が12例, stage 2が15例, stage 3Aが5例, stage 3Bが2例, stage 3Cが1例, stage 4Aが1例, stage 4Bが14例) の腎動脈撮影時における静脈像所見について検討を行つた.腎動脈撮影で腎静脈本幹が描出されたものは, 50例中21例 (42%) で, 正常腎の腎静脈描出率83% (30例中25例) より低かつた. また患側別では, 右側が28例中9例 (32%), 左側が22例中12例 (55%) であり, 右腎静脈は左腎静脈と比較して描出率が低かつた. 一方, high stage (stage 3およびstage 4)は, low stage (stage 1およびstage 2) に比べて, 腎静脈描出率が低かつたが, high stageのうち腎静脈腫瘍血栓を除けば, 腎静脈描出率は low stage のそれと同程度であつた.腎動静脈瘻は50例中6例 (12%) に認めたが, そのうち腎静脈腫瘍血栓は3例 (50%) と高率に合併していたが, その予後は必ずしも悪くない傾向であつた.腎静脈腫瘍血栓を認めた13例中, 腎動脈撮影で striated vascular pattern は10例 (77%) に描出された.側副静脈は50例中11例 (22%) に認めたが, そのうち腎静脈腫瘍血栓の合併は5例 (45%) で, 残り6例は腎静脈腫瘍血栓が認められないにもかかわらず, 側副静脈が描出されており, 腎静脈腫瘍血栓と側副静脈描出の関連性は少ないと考えられた.
Cite
Citations (0)