scholarly journals Pan-cancer identification of clinically relevant genomic subtypes using outcome-weighted integrative clustering

2020 ◽  
Author(s):  
Arshi Arora ◽  
Adam B. Olshen ◽  
Venkatraman E. Seshan ◽  
Ronglai Shen
Keyword(s):  
Cancer Patient ◽  
Clustering Algorithm ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Unsupervised Clustering ◽  
Patient Stratification ◽  
Cell Of Origin ◽  
Weighted Clustering ◽  
Molecular Phenotypes ◽  
Major Factors

ABSTRACTMolecular phenotypes of cancer are complex and influenced by a multitude of factors. Conventional unsupervised clustering of heterogeneous cancer patient populations is inevitably driven by the dominant variation from major factors such as cell-of-origin or histology. Drawing from ideas in supervised text classification, we developed survClust, an outcome-weighted clustering algorithm for integrative patient stratification. We show survClust outperforms unsupervised clustering in identifying cancer patient subpopulations characterized by specific genomic phenotypes with more aggressive clinical behavior. The algorithm and tools we developed have direct utility toward clinically relevant patient stratification based on tumor genomics to inform clinical decision-making.

scholarly journals Pan-cancer identification of clinically relevant genomic subtypes using outcome-weighted integrative clustering

2020 ◽  
Vol 12 (1) ◽  
Author(s):  
Arshi Arora ◽  
Adam B. Olshen ◽  
Venkatraman E. Seshan ◽  
Ronglai Shen
Keyword(s):  
Clustering Algorithm ◽  
Clinical Decision Making ◽  
Unsupervised Clustering ◽  
The Cancer Genome Atlas ◽  
Cell Of Origin ◽  
Large Patient ◽  
Mutation Burden ◽  
A Genome ◽  
Cancer Types ◽  
Pan Cancer

Abstract Background Comprehensive molecular profiling has revealed somatic variations in cancer at genomic, epigenomic, transcriptomic, and proteomic levels. The accumulating data has shown clearly that molecular phenotypes of cancer are complex and influenced by a multitude of factors. Conventional unsupervised clustering applied to a large patient population is inevitably driven by the dominant variation from major factors such as cell-of-origin or histology. Translation of these data into clinical relevance requires more effective extraction of information directly associated with patient outcome. Methods Drawing from ideas in supervised text classification, we developed survClust, an outcome-weighted clustering algorithm for integrative molecular stratification focusing on patient survival. survClust was performed on 18 cancer types across multiple data modalities including somatic mutation, DNA copy number, DNA methylation, and mRNA, miRNA, and protein expression from the Cancer Genome Atlas study to identify novel prognostic subtypes. Results Our analysis identified the prognostic role of high tumor mutation burden with concurrently high CD8 T cell immune marker expression and the aggressive clinical behavior associated with CDKN2A deletion across cancer types. Visualization of somatic alterations, at a genome-wide scale (total mutation burden, mutational signature, fraction genome altered) and at the individual gene level, using circomap further revealed indolent versus aggressive subgroups in a pan-cancer setting. Conclusions Our analysis has revealed prognostic molecular subtypes not previously identified by unsupervised clustering. The algorithm and tools we developed have direct utility toward patient stratification based on tumor genomics to inform clinical decision-making. The survClust software tool is available at https://github.com/arorarshi/survClust.

scholarly journals INNV-34. PATTERNS OF FAILURE AND DEVELOPMENT OF A NOVEL PROGNOSTIC SCORING SYSTEM IN ELDERLY PATIENTS WITH GLIOBLASTOMA – FOLLOW UP ON 10 YEAR ANALYSIS OF THE BC CANCER AGENCY POPULATION

2019 ◽  
Vol 21 (Supplement_6) ◽  
pp. vi137-vi137
Author(s):  
Jonathan Zeng ◽  
Kimberly DeVries ◽  
Andra Krauze
Keyword(s):  
Decision Making ◽  
Scoring System ◽  
Clinical Decision Making ◽  
Radiographic Progression ◽  
Clinical Decision ◽  
Patient Stratification ◽  
Patterns Of Failure ◽  
Resection Status ◽  
Cancer Agency

Abstract PURPOSE Glioblastomas (GBM) are the most common primary brain tumour recurring in most patients despite maximal management. Patient selection for appropriate treatment modality remains challenging resulting in heterogeneity in management. We examined the patterns of failure and developed a scoring system for patient stratification to optimise clinical decision making. METHODS 822 adults (BC Cancer Agency registry) diagnosed 2005–2015 age ≥60 with histologically confirmed GBM ICD-O-3 codes (9440/3, 9441/3, 9442/3) were reviewed. Univariate and Kaplan-Meier analysis were performed. Performance status (PS), age and resection status were assigned a score, cummulative maximal (favorable) score of 10 and minimum (unfavorable) score of 3. Patterns of failure were further analysed in the subset of patients with radiographic follow-up. RESULTS PS score of 3(KPS >80, ECOG 0/1), 2 (KPS 60–70, ECOG 2), 1 (KPS < 60, ECOG 3/4) (median OS 11, 6, 3 months respectively), age score and resection status were prognostic for OS with PS resulting in the most significant curve separation (p< 0.0001). Biopsy as compared to STR/GTR resulted in poorer OS in patients over 70 (age score 1/2) but had less impact in patients younger than 70 (age scores 3/4). The median OS for cumulative scores of 9/10 (123 patients), 7/8 (286 patients), 5/6 (313 patients), and 3/4 (55 patients) were 14, 8, 4 and 2 months respectively (p< 0.0001) allowing for stratification into 4 prognostic groups. 133 patients had >3 MRIs following diagnosis allowing for clinical and radiographic analysis of progression. Clinical/radiographic progression occurred within 3 months (29%/45%), 6 months (50%/66%), 9 months (70%/81%). Progression type (radiographic, clinical, both was not associated with OS. CONCLUSION Our novel prognostic scoring system is effective in achieving patient stratification and may guide clinical decision making. Early radiographic progression appears to precede clinical deterioration and may represent true progression in the elderly.

scholarly journals Orthodontic treatment time: can it be shortened?

2018 ◽  
Vol 23 (6) ◽  
pp. 90-105 ◽  
Author(s):  
Ricardo Moresca
Keyword(s):  
Orthodontic Treatment ◽  
Clinical Decision Making ◽  
Tooth Movement ◽  
Treatment Time ◽  
Treatment Options ◽  
Clinical Decision ◽  
Orthodontic Appliances ◽  
Factors Influencing ◽  
Determining Factors ◽  
Major Factors

Abstract Introduction: In the literature, no consensus has been reached about orthodontic treatment time. Similarly, the determining factors of the latter have not yet been completely elucidated. Objective: The aim of the present article was to deepen the discussion on the major factors influencing orthodontic treatment time, as well as to present some strategies that have proven effective in controlling and shortening it. Method: Based on evidences found in the literature, the method focussed in providing the basis for clinical decision-making. Conclusions: Treatment time varies according to the type of malocclusion and treatment options. Orthodontist’s influence, patient’s characteristics and compliance are all decisive in determining treatment time, while the effects provided by orthodontic appliances and methods used to speed tooth movement up seem little effective.

scholarly journals AliClu - Temporal sequence alignment for clustering longitudinal clinical data

2019 ◽  
Vol 19 (1) ◽  
Author(s):  
Kishan Rama ◽  
Helena Canhão ◽  
Alexandra M. Carvalho ◽  
Susana Vinga
Keyword(s):  
Clinical Data ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Transition Time ◽  
Current Therapy ◽  
Patient Stratification ◽  
Biologic Drugs ◽  
Discrete State ◽  
Validation Parameters ◽  
Time Information

Abstract Background Patient stratification is a critical task in clinical decision making since it can allow physicians to choose treatments in a personalized way. Given the increasing availability of electronic medical records (EMRs) with longitudinal data, one crucial problem is how to efficiently cluster the patients based on the temporal information from medical appointments. In this work, we propose applying the Temporal Needleman-Wunsch (TNW) algorithm to align discrete sequences with the transition time information between symbols. These symbols may correspond to a patient’s current therapy, their overall health status, or any other discrete state. The transition time information represents the duration of each of those states. The obtained TNW pairwise scores are then used to perform hierarchical clustering. To find the best number of clusters and assess their stability, a resampling technique is applied. Results We propose the AliClu, a novel tool for clustering temporal clinical data based on the TNW algorithm coupled with clustering validity assessments through bootstrapping. The AliClu was applied for the analysis of the rheumatoid arthritis EMRs obtained from the Portuguese database of rheumatologic patient visits (Reuma.pt). In particular, the AliClu was used for the analysis of therapy switches, which were coded as letters corresponding to biologic drugs and included their durations before each change occurred. The obtained optimized clusters allow one to stratify the patients based on their temporal therapy profiles and to support the identification of common features for those groups. Conclusions The AliClu is a promising computational strategy to analyse longitudinal patient data by providing validated clusters and by unravelling the patterns that exist in clinical outcomes. Patient stratification is performed in an automatic or semi-automatic way, allowing one to tune the alignment, clustering, and validation parameters. The AliClu is freely available at https://github.com/sysbiomed/AliClu.

scholarly journals Management of Cancer-Associated Thrombosis: An Evolving Area

Cancers ◽  
2020 ◽  
Vol 12 (10) ◽  
pp. 2999
Author(s):  
Corinne Frere ◽  
Jean M. Connors ◽  
Dominique Farge
Keyword(s):  
Cancer Patient ◽  
Clinical Decision Making ◽  
Oral Anticoagulants ◽  
Direct Oral Anticoagulants ◽  
Clinical Decision ◽  
Patient Centered ◽  
Patient Values ◽  
The Individual ◽  
The Right ◽  
Cancer Associated Thrombosis

The management of cancer-associated thrombosis (CAT) is an evolving area. With the use of direct oral anticoagulants as a new option in the management of CAT, clinicians now face several choices for the individual cancer patient with venous thromboembolism. A personalized approach, matching the right drug to the right patient, based on drug properties, efficacy and safety, side effect profile of each drug, and patient values and preference, will probably supplant the one size fits all approach of use of only low-molecular-weight heparin in the near future. We herein present eight translational, clinical research, and review articles on recent advances in the management of CAT published in the Special Issue “Treatment for Cancer-Associated Thrombosis” of Cancers. For now, a multidisciplinary patient-centered approach involving a close cooperation between oncologists and other specialists is warranted to guide clinical decision making and optimize the treatment of VTE in cancer patient.

scholarly journals Clinical Decision-Making: Developing a 4 C Model Using Graph Theoretic Approach

2020 ◽  
Vol 7 (1) ◽  
pp. 30
Author(s):  
Rajesh P. Mishra ◽  
Nidhi Mundra ◽  
Girish Upreti ◽  
Marcela Villa-Marulanda
Keyword(s):  
Decision Making ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Theoretic Model ◽  
Specific Situation ◽  
Theoretic Approach ◽  
Graph Theoretic ◽  
Treatment Processes ◽  
Graph Theoretic Approach ◽  
Major Factors

The purpose of this paper is to propose a graph-theoretic mathematical model to measure how conducive the environment of a hospital is for decision-making. We propose a 4-C model, developed from four interacting factors: confidence, complexity, capability, and customer. In this graph-theoretic model, abstract information regarding the system is represented by the directed edges of a graph (or digraph), which together depict how one factor affects another. The digraph yields a matrix model useful for computer processing. The net effect of different factors and their interdependencies on the hospital's decision-making environment is quantified and a single numerical index is generated. This paper categorizes all the major factors that influence clinical decision-making and attempts to provide a tool to study and measure their interactions with each other. Each factor and each interaction among factors are to be quantified by healthcare experts according to their best judgment of the magnitude of its effect in a local hospital environment.A hospital case study is used to demonstrate how the 4-C model works. The graph-theoretic approach allows for the inclusion of new factors and generation of alternative environments by a combination of both qualitative and quantitative modeling. The 4-C model can be used to create both a database and a simple numerical scale that help a hospital set customized guidelines, ranging from patient admittance procedures to diagnostic and treatment processes, according to its specific situation. Implementing this methodology systematically can allow a hospital to identify factors that will lead to improved decision-making as well as identifying operational factors that present roadblocks.

scholarly journals Optimising Patients For A Successful TKR And Choosing The Winners

2020 ◽  
Vol 8 (5_suppl5) ◽  
pp. 2325967120S0010
Author(s):  
Sanjeev Patnaik ◽  
Ranjan Kumar Sahoo
Keyword(s):  
Total Knee Replacement ◽  
Knee Replacement ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Major Surgery ◽  
Clinical Literature ◽  
Successful Clinical Outcome ◽  
Total Knee ◽  
Major Factors ◽  
End Stage

Total knee replacement (TKR) is one of the most successful operations in the history of orthopaedic surgery and its effectiveness in relieving pain and improving functionin patients with end-stage advanced arthritis of knee is undisputed . Despite its scientific reputation as mainly successful, only 81% to 89% of patients are actually satisfied with the final result as per clinical literature. Awareness of the existence as well as identification of predictors of Patient - Surgeon disagreement, should help improve the dialogue that goes on between patients and surgeons, thus improving the clinical decision-making processes and making expectations more realistic in an attempt to enhance patient outcomes. Focussing on 5 major factors can help to ensure that patient safety is maintained, and satisfaction following a major surgery like TKR is enhanced :- 1.Correct patient selection, after a meticulous history taking and clinical examination, 2. Setting appropriate expectations 3. Avoiding preventable complications, 4. Adhering to the finer points of the surgical operation and following a meticulous surgical technique and 5. Using pre - and post- operative pathways. All these factors will help to ensure maximum patient satisfaction and aid in successful clinical outcome following Total Knee Replacement.

scholarly journals An approach to rapidly assess sepsis through multi-biomarker host response using machine learning algorithm

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Abha Umesh Sardesai ◽  
Ambalika Sanjeev Tanak ◽  
Subramaniam Krishnan ◽  
Deborah A. Striegel ◽  
Kevin L. Schully ◽  
...  
Keyword(s):  
Machine Learning ◽  
Immune Response ◽  
Clinical Decision Making ◽  
Learning Algorithm ◽  
Clinical Decision ◽  
Host Immune Response ◽  
Supervised Machine Learning ◽  
Machine Learning Algorithm ◽  
Patient Stratification ◽  
Sepsis Management

AbstractSepsis is a life-threatening condition and understanding the disease pathophysiology through the use of host immune response biomarkers is critical for patient stratification. Lack of accurate sepsis endotyping impedes clinicians from making timely decisions alongside insufficiencies in appropriate sepsis management. This work aims to demonstrate the potential feasibility of a data-driven validation model for supporting clinical decisions to predict sepsis host-immune response. Herein, we used a machine learning approach to determine the predictive potential of identifying sepsis host immune response for patient stratification by combining multiple biomarker measurements from a single plasma sample. Results were obtained using the following cytokines and chemokines IL-6, IL-8, IL-10, IP-10 and TRAIL where the test dataset was 70%. Supervised machine learning algorithm naïve Bayes and decision tree algorithm showed good accuracy of 96.64% and 94.64%. These promising findings indicate the proposed AI approach could be a valuable testing resource for promoting clinical decision making.

Sign in / Sign up

Export Citation Format

Share Document