Cancer Informatics最新文献

{"title":"Cervical Transformation Zone Segmentation and Classification based on Improved Inception-ResNet-V2 Using Colposcopy Images.","authors":"Srikanta Dash,&nbsp;Prabira Kumar Sethy,&nbsp;Santi Kumari Behera","doi":"10.1177/11769351231161477","DOIUrl":"https://doi.org/10.1177/11769351231161477","url":null,"abstract":"<p><p>The second most frequent malignancy in women worldwide is cervical cancer. In the transformation(transitional) zone, which is a region of the cervix, columnar cells are continuously converting into squamous cells. The most typical location on the cervix for the development of aberrant cells is the transformation zone, a region of transforming cells. This article suggests a 2-phase method that includes segmenting and classifying the transformation zone to identify the type of cervical cancer. In the initial stage, the transformation zone is segmented from the colposcopy images. The segmented images are then subjected to the augmentation process and identified with the improved inception-resnet-v2. Here, multi-scale feature fusion framework that utilizes 3 × 3 convolution kernels from Reduction-A and Reduction-B of inception-resnet-v2 is introduced. The feature extracted from Reduction-A and Reduction -B is concatenated and fed to SVM for classification. This way, the model combines the benefits of residual networks and Inception convolution, increasing network width and resolving the deep network's training issue. The network can extract several scales of contextual information due to the multi-scale feature fusion, which increases accuracy. The experimental results reveal 81.24% accuracy, 81.24% sensitivity, 90.62% specificity, 87.52% precision, 9.38% FPR, and 81.68% F1 score, 75.27% MCC, and 57.79% Kappa coefficient.</p>","PeriodicalId":35418,"journal":{"name":"Cancer Informatics","volume":"22 ","pages":"11769351231161477"},"PeriodicalIF":2.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/ad/c1/10.1177_11769351231161477.PMC10064461.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9234977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of an eHealth Tool for Capturing and Analyzing the Immune-related Adverse Events (irAEs) in Cancer Treatment.","authors":"Saeed Moradian,&nbsp;Shive Ghasemi,&nbsp;Babak Boutorabi,&nbsp;Zakieh Sharifian,&nbsp;Fay Dastjerdi,&nbsp;Catriona Buick,&nbsp;Charlotte T Lee,&nbsp;Samantha J Mayo,&nbsp;Plinio P Morita,&nbsp;Doris Howell","doi":"10.1177/11769351231178587","DOIUrl":"https://doi.org/10.1177/11769351231178587","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Introduction: &lt;/strong&gt;Immunotherapy has revolutionized the treatment of many different types of cancer, but it is associated with a myriad of immune-related adverse events (irAEs). Patient-reported outcome (PRO) measures have been identified as valuable tools for continuously collecting patient-centered data and are frequently used in oncology trials. However, few studies still research an ePRO follow-up approach on patients treated with Immunotherapy, potentially reflecting a lack of support services for this population.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;The team co-developed a digital platform (V-Care) using ePROs to create a new follow-up pathway for cancer patients receiving immunotherapy. To operationalize the first 3 phases of the CeHRes roadmap, we employed multiple methods that were integrated throughout the development process, rather than being performed in a linear fashion. The teams employed an agile approach in a dynamic and iterative manner, engaging key stakeholders throughout the process.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The development of the application was categorized into 2 phases: \"user interface\" (UI) and \"user experience\" (UX) designs. In the first phase, the pages of the application were segmented into general categories, and feedback from all stakeholders was received and used to modify the application. In phase 2, mock-up pages were developed and sent to the Figma website. Moreover, the Android Package Kit (APK) of the application was installed and tested multiple times on a mobile phone to proactively detect and fix any errors. After resolving some technical issues and adjusting errors on the Android version to improve the user experience, the iOS version of the application was developed.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Discussion: &lt;/strong&gt;By incorporating the latest technological developments, V-Care has enabled cancer patients to have access to more comprehensive and personalized care, allowing them to better manage their condition and be better informed about their health decisions. These advances have also enabled healthcare professionals to be better equipped with the knowledge and tools to provide more effective and efficient care. In addition, the advances in V-Care technology have allowed patients to connect with their healthcare providers more easily, providing a platform to facilitate communication and collaboration. Although usability testing is necessary to evaluate the efficacy and user experience of the app, it can be a significant investment of time and resources.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;The V-Care platform can be used to investigate the reported symptoms experienced by cancer patients receiving Immune checkpoint inhibitors (ICIs) and to compare them with the results from clinical trials. Furthermore, the project will utilize ePRO tools to collect symptoms from patients and provide insight into whether the reported symptoms are linked to the treatment.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Clinical relevance: &lt;/strong&gt;V-Care ","PeriodicalId":35418,"journal":{"name":"Cancer Informatics","volume":"22 ","pages":"11769351231178587"},"PeriodicalIF":2.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/0a/23/10.1177_11769351231178587.PMC10259133.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9636113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Determinants of Time-to-Death of Chronic Lymphocytic Leukemia Patients at Felege Hiwot Referral Hospital, Bahir Dar, Ethiopia.","authors":"Gedam Derbew Addisia,&nbsp;Awoke Seyoum Tegegne,&nbsp;Denekew Bitew Belay,&nbsp;Mahider Abere Kassaw,&nbsp;Mitiku Wale Muluneh,&nbsp;Koyachew Bitew Abebe,&nbsp;Bezanesh Melese Masresha,&nbsp;Solomon Sisay Mulugeta,&nbsp;Setegn Muche Fentaw,&nbsp;Dejen Gedamu Damtie","doi":"10.1177/11769351231183849","DOIUrl":"https://doi.org/10.1177/11769351231183849","url":null,"abstract":"Background: Leukemia is a group of cancers that usually begin in the bone marrow and results in a large number of abnormal white blood cells. Chronic Lymphocytic Leukemia is the most prevalent leukemia in Western countries, with an estimated incidence rate of less than 1 to 5.5 per 100 000 people, and average age at diagnosis of 64 to 72 years. It is more common in men among Chronic Lymphocytic Leukemia patients in Ethiopia’s hospitals at Felege Hiwot Referal Hospital. Methods: A retrospective cohort research design was employed to acquire critical information from patients’ medical records in order to achieve the study’s purpose. The study comprised the medical records of 312 Chronic Lymphocytic Leukemia who were followed from January 1, 2018 to December 31, 2020. A Cox proportional hazard model was used to determine the risk factors for time to death in Chronic Lymphocytic Leukemia patients. Results: Accordingly the Cox proportional hazard model, age (Hazard Ratio = 11.36; P < .001), sex of male (Hazard Ratio = 1.04; P = .004), married status (Hazard Ratio = 0.03; P = .003), medium stages of Chronic Lymphocytic Leukemia (Hazard Ratio = 1.29; P = .024), high stages of Chronic Lymphocytic Leukemia (Hazard Ratio = 1.99; P < .001), presence of anemia (Hazard Ratio =0.09; P = .005), platelets (Hazard Ratio = 2.11; P = .007), hemoglobin (Hazard Ratio = 0.02; P < .001), lymphocytes (Hazard Ratio = 0.29; P = .006), red blood cell (Hazard Ratio = 0.02; P < .001), which patients with Chronic Lymphocytic Leukemia had a significant relationship with time to death. Conclusions: Age, sex, Chronic Lymphocytic Leukemia stage, anemia, platelets, hemoglobin, lymphocytes, and red blood cells were all statistically significant determinants in the time to death of Chronic Lymphocytic Leukemia patients, according to the data. As a result, healthcare providers should pay particular attention to and emphasize the identified characteristics, as well as provide frequent counseling on how to enhance the health of Chronic Lymphocytic Leukemia patients.","PeriodicalId":35418,"journal":{"name":"Cancer Informatics","volume":"22 ","pages":"11769351231183849"},"PeriodicalIF":2.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/ca/70/10.1177_11769351231183849.PMC10328045.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9814077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Erratum to \"TP53 and its Regulatory Genes as Prognosis of Cutaneous Melanoma\".","authors":"","doi":"10.1177/11769351231202605","DOIUrl":"https://doi.org/10.1177/11769351231202605","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.1177/11769351231177267.].</p>","PeriodicalId":35418,"journal":{"name":"Cancer Informatics","volume":"22 ","pages":"11769351231202605"},"PeriodicalIF":2.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/70/fe/10.1177_11769351231202605.PMC10503288.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10286536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Immunogenetic Profiles and Associations of Breast, Cervical, Ovarian, and Uterine Cancers.","authors":"Lisa M James,&nbsp;Apostolos P Georgopoulos","doi":"10.1177/11769351221148588","DOIUrl":"https://doi.org/10.1177/11769351221148588","url":null,"abstract":"<p><p>It is increasingly recognized that the human immune response influences cancer risk, progression, and survival; consequently, there is growing interest in the role of human leukocyte antigen (HLA), genes that play a critical role in initiating the immune response, on cancer. Recent evidence documented clustering of cancers based on immunogenetic profiles such that breast and ovarian cancers clustered together as did uterine and cervical cancers. Here we extend that line of research to evaluate the HLA profile of those 4 cancers and their associations. Specifically, we evaluated the associations between the frequencies of 127 HLA alleles and the population prevalences of breast, ovarian, cervical, and uterine cancer in 14 countries in Continental Western Europe. Factor analysis and hierarchical clustering were used to evaluate groupings of cancers based on their immunogenetic profiles. The results documented highly similar immunogenetic profiles for breast and ovarian cancers that were characterized predominantly by protective HLA effects. In addition, highly similar immunogenetic profiles for cervical and uterine cancers were observed that were, conversely, characterized by susceptibility effects. In light of the role of HLA in host immune system protection against non-self antigens, these findings suggest that certain cancers may be associated with similar contributory factors such as viral oncoproteins or neoantigens.</p>","PeriodicalId":35418,"journal":{"name":"Cancer Informatics","volume":"22 ","pages":"11769351221148588"},"PeriodicalIF":2.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/47/11/10.1177_11769351221148588.PMC9846304.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10585897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prevalence of Breast Cancer Subtypes Among Different Ethnicities and Bangladeshi Women: Demographic, Clinicopathological, and Integrated Cancer Informatics Analysis.","authors":"Diganta Islam,&nbsp;Md Shihabul Islam,&nbsp;Sanjida Islam Dorin,&nbsp;Jesmin","doi":"10.1177/11769351221148584","DOIUrl":"https://doi.org/10.1177/11769351221148584","url":null,"abstract":"<p><strong>Background: </strong>The molecular subtyping of breast cancer is related to estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2). The present study aimed to systematically analyze the expression, function, and prognostic value of ER, PR, HER2, and their prevalence in different ethnic groups and among Bangladeshi breast cancer (BC) patients.</p><p><strong>Method: </strong>This study included 25 BC patients and 25 healthy controls, aged between 25 and 70 years. The study characteristics were compared using the ANOVA and Chi-square tests. Also, the multi-Omics dataset of 775 BC patients from TCGA was analyzed for ER, PR, and HER2 in breast cancer subtypes and compared among different ethnicities.</p><p><strong>Results: </strong>For most BD breast cancer cases, the age at diagnosis was ⩾40 years, had only a histopathological diagnosis (<i>P</i>-value .004), and no history of mammography or other pathological tests. For treatment, had only chemotherapy (<i>P</i>-value .004) and no hormone therapy (<i>P</i>-value <.001). The majority of patients (>60%) were of stage-II cancer and TNBC (40%) subtype. The BC ethnicity-stratified data of ER, PR, and HER2 indicated a strong correlation across all ethnicities (<i>P</i>-value 4.99e-35; <i>P</i>-value 3.79e-18). The subtypes stratified data indicated a higher percentage of Luminal A (58.3%) in Caucasians whereas Luminal B (24.3%) and HER2 (25.2%) subtypes were found higher in Asians and TNBC (36.0%) were found in Africans. However, a significantly higher frequency of TNBC (52.2%) compared to Asians (14.8%) was found in BD patients (<i>P</i>-value <.001). The overall survival analysis of BC subtypes demonstrated that Luminal B (<i>P</i>-value .005) and HER2 enriched (<i>P</i>-value .015) were significantly more aggressive and were dominant in the Asian population.</p><p><strong>Conclusion: </strong>A significant association was found between BC subtypes with different ethnicities and Bangladeshi women and these findings might aid in the prevention, management, and raising of awareness against risk factors in the near future.</p>","PeriodicalId":35418,"journal":{"name":"Cancer Informatics","volume":"22 ","pages":"11769351221148584"},"PeriodicalIF":2.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/f5/b1/10.1177_11769351221148584.PMC9850134.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10635591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prevalence of Iron Deficiency and its Association With Breast Cancer in Premenopausal Compared to Postmenopausal Women in Al Ahsa, Saudi Arabia.","authors":"Mohammad Al Khamees,&nbsp;Aymen A Alqurain,&nbsp;Abdulmonem A Alsaleh,&nbsp;Yousef A Alhashem,&nbsp;Nida AlSaffar,&nbsp;Noura N Alibrahim,&nbsp;Fardus A Aljunibi,&nbsp;Zaheda Alradwan,&nbsp;Nesreen Almohammade,&nbsp;Bader AlAlwan","doi":"10.1177/11769351231172589","DOIUrl":"https://doi.org/10.1177/11769351231172589","url":null,"abstract":"<p><p>Iron is an essential cofactor needed for normal functions of various enzymes and its depletion lead to increase DNA damage, genomic instability, deteriorate innate, adaptive immunity, and promote tumor development. It is also linked to tumorigenesis of breast cancer cells through enhancing mammary tumor growth and metastasis. There is insufficient data describing this association in Saudi Arabia. This study aims to determine the prevalence of iron deficiency and its association with breast cancer among premenopausal and postmenopausal women referred for breast cancer screening center in Al Ahsa, Eastern Province of Saudi Arabia. Age, hemoglobin level, iron level, history of anemia, or iron deficiency were collected from patients' medical records. The included participants were grouped based on their age into premenopausal (<50 years) or postmenopausal (⩾50 years). The definition of low Hb implemented (Hb below 12 g/dL) and low total serum Iron levels (below 8 μmol/L). Logistic regression test was used to compute the association between having a positive cancer screening test (radiological or histocytological) and participant's lab results. The results are presented as odds ratios and 95% confidence intervals. Thrree hundred fifty-seven women were included, 77% (n = 274) of them were premenopausal. This group cases had more history of iron deficiency (149 [60%] vs 25 (30%), <i>P</i> = .001) compared to those in the postmenopausal group. The risk of having a positive radiological cancer screening test was associated with age (OR = 1.04, 95% CI 1.02-1.06), but negatively was associated with iron level (OR = 0.9, 95% CI 0.86-0.97) among the entire cohort. This study is the first to propose an association between iron deficiency and breast cancer among Saudi young females. This could suggest iron level as a new risk factor that may be used by clinicians to assess breast cancer risk.</p>","PeriodicalId":35418,"journal":{"name":"Cancer Informatics","volume":"22 ","pages":"11769351231172589"},"PeriodicalIF":2.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/dc/b1/10.1177_11769351231172589.PMC10201173.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9871493","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Patient Identification and Tumor Identification Management: Quality Program in a Cancer Multicentric Clinical Data Warehouse.","authors":"Karine Pallier,&nbsp;Olivier Prot,&nbsp;Simone Naldi,&nbsp;Francisco Silva,&nbsp;Thierry Denis,&nbsp;Olivier Giry,&nbsp;Sophie Leobon,&nbsp;Elise Deluche,&nbsp;Nicole Tubiana-Mathieu","doi":"10.1177/11769351231172609","DOIUrl":"https://doi.org/10.1177/11769351231172609","url":null,"abstract":"<p><strong>Background: </strong>The Regional Basis of Solid Tumor (RBST), a clinical data warehouse, centralizes information related to cancer patient care in 5 health establishments in 2 French departments.</p><p><strong>Purpose: </strong>To develop algorithms matching heterogeneous data to \"real\" patients and \"real\" tumors with respect to patient identification (PI) and tumor identification (TI).</p><p><strong>Methods: </strong>A graph database programed in java Neo4j was used to build the RBST with data from ~20 000 patients. The PI algorithm using the Levenshtein distance was based on the regulatory criteria identifying a patient. A TI algorithm was built on 6 characteristics: tumor location and laterality, date of diagnosis, histology, primary and metastatic status. Given the heterogeneous nature and semantics of the collected data, the creation of repositories (organ, synonym, and histology repositories) was required. The TI algorithm used the Dice coefficient to match tumors.</p><p><strong>Results: </strong>Patients matched if there was complete agreement of the given name, surname, sex, and date/month/year of birth. These parameters were assigned weights of 28%, 28%, 21%, and 23% (with 18% for year, 2.5% for month, and 2.5% for day), respectively. The algorithm had a sensitivity of 99.69% (95% confidence interval [CI] [98.89%, 99.96%]) and a specificity of 100% (95% CI [99.72%, 100%]). The TI algorithm used repositories, weights were assigned to the diagnosis date and associated organ (37.5% and 37.5%, respectively), laterality (16%) histology (5%), and metastatic status (4%). This algorithm had a sensitivity of 71% (95% CI [62.68%, 78.25%]) and a specificity of 100% (95% CI [94.31%, 100%]).</p><p><strong>Conclusion: </strong>The RBST encompasses 2 quality controls: PI and TI. It facilitates the implementation of transversal structuring and assessments of the performance of the provided care.</p>","PeriodicalId":35418,"journal":{"name":"Cancer Informatics","volume":"22 ","pages":"11769351231172609"},"PeriodicalIF":2.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/f9/25/10.1177_11769351231172609.PMC10201142.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9888090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Novel Biomarker Prediction for Lung Cancer Using Random Forest Classifiers.","authors":"Lavanya C,&nbsp;Pooja S,&nbsp;Abhay H Kashyap,&nbsp;Abdur Rahaman,&nbsp;Swarna Niranjan,&nbsp;Vidya Niranjan","doi":"10.1177/11769351231167992","DOIUrl":"https://doi.org/10.1177/11769351231167992","url":null,"abstract":"<p><p>Lung cancer is considered the most common and the deadliest cancer type. Lung cancer could be mainly of 2 types: small cell lung cancer and non-small cell lung cancer. Non-small cell lung cancer is affected by about 85% while small cell lung cancer is only about 14%. Over the last decade, functional genomics has arisen as a revolutionary tool for studying genetics and uncovering changes in gene expression. RNA-Seq has been applied to investigate the rare and novel transcripts that aid in discovering genetic changes that occur in tumours due to different lung cancers. Although RNA-Seq helps to understand and characterise the gene expression involved in lung cancer diagnostics, discovering the biomarkers remains a challenge. Usage of classification models helps uncover and classify the biomarkers based on gene expression levels over the different lung cancers. The current research concentrates on computing transcript statistics from gene transcript files with a normalised fold change of genes and identifying quantifiable differences in gene expression levels between the reference genome and lung cancer samples. The collected data is analysed, and machine learning models were developed to classify genes as causing NSCLC, causing SCLC, causing both or neither. An exploratory data analysis was performed to identify the probability distribution and principal features. Due to the limited number of features available, all of them were used in predicting the class. To address the imbalance in the dataset, an under-sampling algorithm Near Miss was carried out on the dataset. For classification, the research primarily focused on 4 supervised machine learning algorithms: Logistic Regression, KNN classifier, SVM classifier and Random Forest classifier and additionally, 2 ensemble algorithms were considered: XGboost and AdaBoost. Out of these, based on the weighted metrics considered, the Random Forest classifier showing 87% accuracy was considered to be the best performing algorithm and thus was used to predict the biomarkers causing NSCLC and SCLC. The imbalance and limited features in the dataset restrict any further improvement in the model's accuracy or precision. In our present study using the gene expression values (LogFC, P Value) as the feature sets in the Random Forest Classifier BRAF, KRAS, NRAS, EGFR is predicted to be the possible biomarkers causing NSCLC and ATF6, ATF3, PGDFA, PGDFD, PGDFC and PIP5K1C is predicted to be the possible biomarkers causing SCLC from the transcriptome analysis. It gave a precision of 91.3% and 91% recall after fine tuning. Some of the common biomarkers predicted for NSCLC and SCLC were CDK4, CDK6, BAK1, CDKN1A, DDB2.</p>","PeriodicalId":35418,"journal":{"name":"Cancer Informatics","volume":"22 ","pages":"11769351231167992"},"PeriodicalIF":2.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/c4/97/10.1177_11769351231167992.PMC10126698.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9718472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Trends in Subcutaneous Tumour Height and Impact on Measurement Accuracy.","authors":"Daniel Brough,&nbsp;Hope Amos,&nbsp;Karl Turley,&nbsp;Jake Murkin","doi":"10.1177/11769351231165181","DOIUrl":"https://doi.org/10.1177/11769351231165181","url":null,"abstract":"<p><p>Tumour volume is typically calculated using only length and width measurements, using width as a proxy for height in a 1:1 ratio. When tracking tumour growth over time, important morphological information and measurement accuracy is lost by ignoring height, which we show is a unique variable. Lengths, widths, and heights of 9522 subcutaneous tumours in mice were measured using 3D and thermal imaging. The average height:width ratio was found to be 1:3 proving that using width as a proxy for height overestimates tumour volume. Comparing volumes calculated with and without tumour height to the true volumes of excised tumours indeed showed that using the volume formula including height produced volumes 36X more accurate (based off of percentage difference). Monitoring the height:width relationship (prominence) across tumour growth curves indicated that prominence varied, and that height could change independent of width. Twelve cell lines were investigated individually; the scale of tumour prominence was cell line-dependent with relatively less prominent tumours (MC38, BL2, LL/2) and more prominent tumours (RENCA, HCT116) detected. Prominence trends across the growth cycle were also dependent on cell line; prominence was correlated with tumour growth in some cell lines (4T1, CT26, LNCaP), but not others (MC38, TC-1, LL/2). When pooled, invasive cell lines produced tumours that were significantly less prominent at volumes >1200 mm³ compared to non-invasive cell lines (<i>P</i> < .001). Modelling was used to show the impact of the increased accuracy gained by including height in volume calculations on several efficacy study outcomes. Variations in measurement accuracy contribute to experimental variation and irreproducibility of data, therefore we strongly advise researchers to measure height to improve accuracy in tumour studies.</p>","PeriodicalId":35418,"journal":{"name":"Cancer Informatics","volume":"22 ","pages":"11769351231165181"},"PeriodicalIF":2.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/2a/51/10.1177_11769351231165181.PMC10126793.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9718474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}