LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 102

Search options

  1. Article ; Online: Association of Patient Experience of Care and Radiation Therapy Initiation Among Women With Early-Stage Breast Cancer.

    Halpern, Michael T / McNeel, Timothy S / Kozono, David / Mollica, Michelle A

    Practical radiation oncology

    2023  Volume 13, Issue 5, Page(s) 434–443

    Abstract: Purpose: For women diagnosed with early-stage breast cancer, lumpectomy followed by radiation therapy (RT) has been a guideline-recommended treatment. However, lumpectomy followed by hormonal therapy is also an approved treatment for certain women. It ... ...

    Abstract Purpose: For women diagnosed with early-stage breast cancer, lumpectomy followed by radiation therapy (RT) has been a guideline-recommended treatment. However, lumpectomy followed by hormonal therapy is also an approved treatment for certain women. It is unclear what patient-driven factors are related to decisions to receive RT. This study examined relationships between patient-reported experience of care, an important dimension of health care quality, and receipt of RT after lumpectomy.
    Methods and materials: We used National Cancer Institute Surveillance, Epidemiology, and End Results data linked to the CMS Medicare Consumer Assessment of Healthcare Providers and Systems patient surveys (SEER-CAHPS) to examine experiences of care among women diagnosed with local/regional stage breast cancer 2000 to 2017 who received lumpectomy, were enrolled in fee-for-service Medicare, completed a CAHPS survey ≤18 months after diagnosis, and survived for this study period. Experience of care was assessed by patient-provided scores for physicians, doctor communication, care coordination, and other aspects of care. Multivariable logistic regression models assessed associations of receipt of external beam RT with care experience and patient sociodemographic and clinical characteristics.
    Results: The study population included 824 women; 655 (79%) received RT. Women with higher experience of care scores for their personal doctor were significantly more likely to have received any RT (odds ratio [OR], 1.18; P = .033). Nonsignificant trends were observed for associations of increased RT with higher CAHPS measures of doctor communications (OR, 1.15; P = .055) and care coordination (OR, 1.24; P = .051). In contrast, women reporting higher scores for Part D prescription drug plans were significantly less likely to have received RT (OR, 0.78; P = .030).
    Conclusions: Patient experience of care was significantly associated with receipt of RT after lumpectomy among women with breast cancer. Health care organization leaders may want to consider incorporating experience of care into quality improvement initiatives and other activities that aim to improve patient decision-making, care, and outcomes.
    MeSH term(s) Humans ; Female ; Aged ; United States ; Breast Neoplasms/radiotherapy ; SEER Program ; Medicare ; Quality of Health Care ; Patient Outcome Assessment
    Language English
    Publishing date 2023-05-06
    Publishing country United States
    Document type Journal Article
    ZDB-ID 2655748-4
    ISSN 1879-8519 ; 1879-8500
    ISSN (online) 1879-8519
    ISSN 1879-8500
    DOI 10.1016/j.prro.2023.04.011
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  2. Article ; Online: The clinician's guide to radiotherapy complications.

    Fendler, Wojciech / Tomasik, Bartłomiej / Atkins, Katelyn / Stawiski, Konrad / Chałubińska-Fendler, Justyna / Kozono, David

    Polish archives of internal medicine

    2022  Volume 132, Issue 1

    Abstract: Radiotherapy is one of the oldest cancer treatment modalities, used for over 100 years. As its efficacy has been steadily increasing due to the introduction of novel treatment methods, adverse events (AEs) still pose a major obstacle limiting the ... ...

    Abstract Radiotherapy is one of the oldest cancer treatment modalities, used for over 100 years. As its efficacy has been steadily increasing due to the introduction of novel treatment methods, adverse events (AEs) still pose a major obstacle limiting the therapeutic benefits in some patients and negatively impacting treatment outcomes. In light of the technological progress, the focus has been shifted from improving the efficacy to safeguarding patients from the most severe AEs through improvements of safety and accuracy of radiation delivery. Currently, with radiation therapy being an effective treatment associated with frequent therapeutic success and leading to increased and prolonged survival, the problem of treatment‑related AEs is growing as there are numerous survivors whose health and quality of life may be adversely affected. Due to the limited access to radiation oncologists, patients presenting with AEs are often referred to other professionals for advice, and as survivorship prolongs, the AEs may aggravate current patient comorbidities or reveal undiagnosed diseases. Thus, it is important that doctors other than oncologists be familiar with the fundamentals of radiation therapy-related AEs and their management. In this review, we present the most common and severe AEs of radiotherapy associated with damage to the nervous, respiratory, cardiovascular, gastrointestinal, and urogenital systems. We also describe the pathogenesis of these AEs, and provide guidelines for prevention, risk assessment, diagnosis, and treatment. Novel findings and future perspectives in this field are also elucidated, including examples of ongoing clinical trials aimed not only at improving treatment outcomes but also at reducing the risk of radiotherapy complications in cancer treatment survivors.
    MeSH term(s) Humans ; Quality of Life ; Radiotherapy/adverse effects ; Treatment Outcome
    Language English
    Publishing date 2022-01-28
    Publishing country Poland
    Document type Journal Article ; Review
    ZDB-ID 123500-x
    ISSN 1897-9483 ; 0032-3772
    ISSN (online) 1897-9483
    ISSN 0032-3772
    DOI 10.20452/pamw.16190
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  3. Article ; Online: Serum miRNA-based signature indicates radiation exposure and dose in humans: A multicenter diagnostic biomarker study.

    Nowicka, Zuzanna / Tomasik, Bartłomiej / Kozono, David / Stawiski, Konrad / Johnson, Thomas / Haas-Kogan, Daphne / Ussowicz, Marek / Chowdhury, Dipanjan / Fendler, Wojciech

    Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology

    2023  Volume 185, Page(s) 109731

    Abstract: Purpose: Mouse and non-human primate models showed that serum miRNAs may be used to predict the biological impact of radiation doses. We hypothesized that these results can be translated to humans treated with total body irradiation (TBI), and that ... ...

    Abstract Purpose: Mouse and non-human primate models showed that serum miRNAs may be used to predict the biological impact of radiation doses. We hypothesized that these results can be translated to humans treated with total body irradiation (TBI), and that miRNAs may be used as clinically feasible biodosimeters.
    Methods: To test this hypothesis, serial serum samples were obtained from 25 patients (pediatric and adults) who underwent allogeneic stem-cell transplantation and profiled for miRNA expression using next-generation sequencing. miRNAs with diagnostic potential were quantified with qPCR and used to build logistic regression models with lasso penalty to reduce overfitting, identifying samples drawn from patients who underwent total body irradiation to a potentially lethal dose.
    Results: Differential expression results were consistent with previous studies in mice and non-human primates. miRNAs with detectable expression in this and two prior animal sets allowed for distinction of the irradiated from non-irradiated samples in mice, macaques and humans, validating the miRNAs as radiation-responsive through evolutionarily conserved transcriptional regulation mechanisms. Finally, we created a model based on the expression of miR-150-5p, miR-30b-5p and miR-320c normalized to two references and adjusted for patient age with an AUC of 0.9 (95%CI:0.83-0.97) for identifying samples drawn after irradiation; a separate model differentiating between high and low radiation dose achieved AUC of 0.85 (95%CI: 0.74-0.96).
    Conclusions: We conclude that serum miRNAs reflect radiation exposure and dose for humans undergoing TBI and may be used as functional biodosimeters for precise identification of people exposed to clinically significant radiation doses.
    MeSH term(s) Adult ; Humans ; Mice ; Animals ; Child ; MicroRNAs/genetics ; Radiation Exposure ; Whole-Body Irradiation ; Dose-Response Relationship, Radiation ; Biomarkers
    Chemical Substances MicroRNAs ; Biomarkers
    Language English
    Publishing date 2023-06-08
    Publishing country Ireland
    Document type Multicenter Study ; Journal Article
    ZDB-ID 605646-5
    ISSN 1879-0887 ; 0167-8140
    ISSN (online) 1879-0887
    ISSN 0167-8140
    DOI 10.1016/j.radonc.2023.109731
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  4. Article ; Online: Surgical management of non-small cell lung cancer with limited metastatic disease involving only the brain.

    Kumar, Arvind / Kumar, Sanjeevani / Potter, Alexandra L / Raman, Vignesh / Kozono, David E / Lanuti, Michael / Jeffrey Yang, Chi-Fu

    The Journal of thoracic and cardiovascular surgery

    2023  Volume 167, Issue 2, Page(s) 466–477.e2

    Abstract: Objective: The optimal primary site treatment modality for non-small cell lung cancer with brain oligometastases is not well established. This study sought to evaluate the long-term survival of patients with non-small cell lung cancer with isolated ... ...

    Abstract Objective: The optimal primary site treatment modality for non-small cell lung cancer with brain oligometastases is not well established. This study sought to evaluate the long-term survival of patients with non-small cell lung cancer with isolated brain metastases undergoing multimodal therapy with or without thoracic surgery.
    Methods: Patients with cT1-3, N0-1, M1b-c non-small cell lung cancer with synchronous limited metastatic disease involving only the brain treated with brain stereotactic radiosurgery or neurosurgical resection in the National Cancer Database (2010-2017) were included. Long-term overall survival of patients who underwent multimodal therapy including thoracic surgery ("Thoracic Surgery") versus systemic therapy with or without radiation to the lung ("No Thoracic Surgery") was evaluated using Kaplan-Meier analysis, Cox proportional hazards modeling, and propensity score matching.
    Results: Of the 1240 patients with non-small cell lung cancer with brain-only metastases who received brain stereotactic radiosurgery or neurosurgery and met study inclusion criteria, 270 (21.8%) received primary site resection. The Thoracic Surgery group had improved overall survival compared with the No Thoracic Surgery group in Kaplan-Meier analysis (P < .001) and after multivariable-adjusted Cox proportional hazards modeling (P < .001). In a propensity score-matched analysis of 175 patients each in the Thoracic Surgery and No Thoracic Surgery groups, matching on 13 common prognostic variables, thoracic surgery was associated with better survival (P = .012).
    Conclusions: In this national analysis, patients with cT1-3, N0-1, M1b-c non-small cell lung cancer with isolated limited brain metastases had better overall survival after multimodal therapy including thoracic surgery compared with systemic therapy without surgery. Multimodal thoracic treatment including surgery can be considered for carefully selected patients with non-small cell lung cancer and limited brain metastases.
    MeSH term(s) Humans ; Carcinoma, Non-Small-Cell Lung/surgery ; Lung Neoplasms/pathology ; Treatment Outcome ; Retrospective Studies ; Brain Neoplasms/surgery ; Brain Neoplasms/pathology ; Brain Neoplasms/secondary ; Brain/pathology ; Radiosurgery ; Neoplasm Staging
    Language English
    Publishing date 2023-04-29
    Publishing country United States
    Document type Journal Article
    ZDB-ID 3104-5
    ISSN 1097-685X ; 0022-5223
    ISSN (online) 1097-685X
    ISSN 0022-5223
    DOI 10.1016/j.jtcvs.2023.04.034
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  5. Article ; Online: A process to reanalyze clinical DNA sequencing data for biomarker matching in the Lung-MAP Master Protocol.

    Neal, Joel W / Minichiello, Katherine / Brennick, Ryan / Huang, Richard S P / Hiemenz, Matthew C / Amler, Cornel / Patel, Jyoti / Herbst, Roy / Reckamp, Karen L / Borghaei, Hossein / Highleyman, Louise / Redman, Mary W / Pasquina, Lincoln W / Kozono, David E

    The oncologist

    2024  

    Abstract: For cancer clinical trials that require central confirmation of tumor genomic profiling, exhaustion of tissue from standard-of-care testing may prevent enrollment. For Lung-MAP, a master protocol that requires results from a defined centralized clinical ... ...

    Abstract For cancer clinical trials that require central confirmation of tumor genomic profiling, exhaustion of tissue from standard-of-care testing may prevent enrollment. For Lung-MAP, a master protocol that requires results from a defined centralized clinical trial assay to assign patients to a therapeutic substudy, we developed a process to repurpose existing commercial vendor raw genomic data for eligibility: genomic data reanalysis (GDR). Molecular results for substudy assignment were successfully generated for 369 of the first 374 patients (98.7%) using GDR for Lung-MAP, with a median time from request to result of 9 days. During the same period, 691 of 791 (87.4%) tissue samples received successfully yielded results, in a median of 14 days beyond sample acquisition. GDR is a scalable bioinformatic pipeline that expedites reanalysis of existing data for clinical trials in which validated integral biomarker testing is required for participation.
    Language English
    Publishing date 2024-04-10
    Publishing country England
    Document type Journal Article
    ZDB-ID 1409038-7
    ISSN 1549-490X ; 1083-7159
    ISSN (online) 1549-490X
    ISSN 1083-7159
    DOI 10.1093/oncolo/oyae062
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  6. Article ; Online: Edge roughness quantifies impact of physician variation on training and performance of deep learning auto-segmentation models for the esophagus.

    Yan, Yujie / Kehayias, Christopher / He, John / Aerts, Hugo J W L / Fitzgerald, Kelly J / Kann, Benjamin H / Kozono, David E / Guthier, Christian V / Mak, Raymond H

    Scientific reports

    2024  Volume 14, Issue 1, Page(s) 2536

    Abstract: Manual segmentation of tumors and organs-at-risk (OAR) in 3D imaging for radiation-therapy planning is time-consuming and subject to variation between different observers. Artificial intelligence (AI) can assist with segmentation, but challenges exist in ...

    Abstract Manual segmentation of tumors and organs-at-risk (OAR) in 3D imaging for radiation-therapy planning is time-consuming and subject to variation between different observers. Artificial intelligence (AI) can assist with segmentation, but challenges exist in ensuring high-quality segmentation, especially for small, variable structures, such as the esophagus. We investigated the effect of variation in segmentation quality and style of physicians for training deep-learning models for esophagus segmentation and proposed a new metric, edge roughness, for evaluating/quantifying slice-to-slice inconsistency. This study includes a real-world cohort of 394 patients who each received radiation therapy (mainly for lung cancer). Segmentation of the esophagus was performed by 8 physicians as part of routine clinical care. We evaluated manual segmentation by comparing the length and edge roughness of segmentations among physicians to analyze inconsistencies. We trained eight multiple- and individual-physician segmentation models in total, based on U-Net architectures and residual backbones. We used the volumetric Dice coefficient to measure the performance for each model. We proposed a metric, edge roughness, to quantify the shift of segmentation among adjacent slices by calculating the curvature of edges of the 2D sagittal- and coronal-view projections. The auto-segmentation model trained on multiple physicians (MD1-7) achieved the highest mean Dice of 73.7 ± 14.8%. The individual-physician model (MD7) with the highest edge roughness (mean ± SD: 0.106 ± 0.016) demonstrated significantly lower volumetric Dice for test cases compared with other individual models (MD7: 58.5 ± 15.8%, MD6: 67.1 ± 16.8%, p < 0.001). A multiple-physician model trained after removing the MD7 data resulted in fewer outliers (e.g., Dice ≤ 40%: 4 cases for MD1-6, 7 cases for MD1-7, N
    MeSH term(s) Humans ; Deep Learning ; Artificial Intelligence ; Thorax ; Algorithms ; Tomography, X-Ray Computed ; Image Processing, Computer-Assisted/methods
    Language English
    Publishing date 2024-01-30
    Publishing country England
    Document type Journal Article
    ZDB-ID 2615211-3
    ISSN 2045-2322 ; 2045-2322
    ISSN (online) 2045-2322
    ISSN 2045-2322
    DOI 10.1038/s41598-023-50382-z
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  7. Article ; Online: Fate and Efficacy of Engineered Allogeneic Stem Cells Targeting Cell Death and Proliferation Pathways in Primary and Brain Metastatic Lung Cancer.

    Moleirinho, Susana / Kitamura, Yohei / Borges, Paulo S G N / Auduong, Sophia / Kilic, Seyda / Deng, David / Kanaya, Nobuhiko / Kozono, David / Zhou, Jing / Gray, Jeffrey J / Revai-Lechtich, Esther / Zhu, Yanni / Shah, Khalid

    Stem cells translational medicine

    2023  Volume 12, Issue 7, Page(s) 444–458

    Abstract: Primary and metastatic lung cancer is a leading cause of cancer-related death and novel therapies are urgently needed. Epidermal growth factor receptor (EGFR) and death receptor (DR) 4/5 are both highly expressed in primary and metastatic non-small cell ... ...

    Abstract Primary and metastatic lung cancer is a leading cause of cancer-related death and novel therapies are urgently needed. Epidermal growth factor receptor (EGFR) and death receptor (DR) 4/5 are both highly expressed in primary and metastatic non-small cell lung cancer (NSCLC); however, targeting these receptors individually has demonstrated limited therapeutic benefit in patients. In this study, we created and characterized diagnostic and therapeutic stem cells (SC), expressing EGFR-targeted nanobody (EV) fused to the extracellular domain of death DR4/5 ligand (DRL) (EVDRL) that simultaneously targets EGFR and DR4/5, in primary and metastatic NSCLC tumor models. We show that EVDRL targets both cell surface receptors, and induces caspase-mediated apoptosis in a broad spectrum of NSCLC cell lines. Utilizing real-time dual imaging and correlative immunohistochemistry, we show that allogeneic SCs home to tumors and when engineered to express EVDRL, alleviate tumor burden and significantly increase survival in primary and brain metastatic NSCLC. This study reports mechanistic insights into simultaneous targeting of EGFR- and DR4/5 in lung tumors and presents a promising approach for translation into the clinical setting.
    MeSH term(s) Humans ; Lung Neoplasms/drug therapy ; Lung Neoplasms/metabolism ; Carcinoma, Non-Small-Cell Lung/drug therapy ; Carcinoma, Non-Small-Cell Lung/metabolism ; ErbB Receptors/genetics ; ErbB Receptors/metabolism ; ErbB Receptors/therapeutic use ; Cell Death ; Brain Neoplasms/therapy ; Cell Proliferation ; Brain/pathology ; Hematopoietic Stem Cell Transplantation
    Chemical Substances ErbB Receptors (EC 2.7.10.1)
    Language English
    Publishing date 2023-06-13
    Publishing country England
    Document type Journal Article
    ZDB-ID 2642270-0
    ISSN 2157-6580 ; 2157-6580
    ISSN (online) 2157-6580
    ISSN 2157-6580
    DOI 10.1093/stcltm/szad033
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  8. Article: Smart Radiotherapy Biomaterials for Image-Guided In Situ Cancer Vaccination.

    Ainsworth, Victoria / Moreau, Michele / Guthier, Romy / Zegeye, Ysaac / Kozono, David / Swanson, William / Jandel, Marian / Oh, Philmo / Quon, Harry / Hobbs, Robert F / Yasmin-Karim, Sayeda / Sajo, Erno / Ngwa, Wilfred

    Nanomaterials (Basel, Switzerland)

    2023  Volume 13, Issue 12

    Abstract: Recent studies have highlighted the potential of smart radiotherapy biomaterials (SRBs) for combining radiotherapy and immunotherapy. These SRBs include smart fiducial markers and smart nanoparticles made with high atomic number materials that can ... ...

    Abstract Recent studies have highlighted the potential of smart radiotherapy biomaterials (SRBs) for combining radiotherapy and immunotherapy. These SRBs include smart fiducial markers and smart nanoparticles made with high atomic number materials that can provide requisite image contrast during radiotherapy, increase tumor immunogenicity, and provide sustained local delivery of immunotherapy. Here, we review the state-of-the-art in this area of research, the challenges and opportunities, with a focus on in situ vaccination to expand the role of radiotherapy in the treatment of both local and metastatic disease. A roadmap for clinical translation is outlined with a focus on specific cancers where such an approach is readily translatable or will have the highest impact. The potential of FLASH radiotherapy to synergize with SRBs is discussed including prospects for using SRBs in place of currently used inert radiotherapy biomaterials such as fiducial markers, or spacers. While the bulk of this review focuses on the last decade, in some cases, relevant foundational work extends as far back as the last two and half decades.
    Language English
    Publishing date 2023-06-12
    Publishing country Switzerland
    Document type Journal Article ; Review
    ZDB-ID 2662255-5
    ISSN 2079-4991
    ISSN 2079-4991
    DOI 10.3390/nano13121844
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  9. Article: Radiation-induced circulating microRNAs linked to echocardiography parameters after radiotherapy.

    Chałubińska-Fendler, Justyna / Nowicka, Zuzanna / Dróżdż, Izabela / Graczyk, Łukasz / Piotrowski, Grzegorz / Tomasik, Bartłomiej / Spych, Michał / Fijuth, Jacek / Papis-Ubych, Anna / Kędzierawski, Piotr / Kozono, David / Fendler, Wojciech

    Frontiers in oncology

    2023  Volume 13, Page(s) 1150979

    Abstract: Introduction: Patients treated with radiotherapy to the chest region are at risk of cardiac sequelae, however, identification of those with greatest risk of complications remains difficult. Here, we sought to determine whether short-term changes in ... ...

    Abstract Introduction: Patients treated with radiotherapy to the chest region are at risk of cardiac sequelae, however, identification of those with greatest risk of complications remains difficult. Here, we sought to determine whether short-term changes in circulating miRNA expression are related to measures of cardiac dysfunction in follow-up.
    Materials and methods: Two parallel patient cohorts were enrolled and followed up for 3 years after completion of RT to treat left-sided breast cancer. In the primary group (N=28) we used a a panel of 752 miRNAs to identify miRNAs associated with radiation and cardiac indices at follow up. In the second, independent cohort (N=56) we validated those candidate miRNAs with a targeted qPCR panel. In both cohorts. serum samples were collected before RT, 24h after the last dose and 1 month after RT; cardiac echocardiography was performed 2.5-3 year after RT.
    Results: Seven miRNAs in the primary group showed marked changes in serum miRNAs immediately after RT compared to baseline and associations with cardiopulmonary dose-volume histogram metrics. Among those miRNAs: miR-15b-5p, miR-22-3p, miR-424-5p and miR-451a were confirmed to show significant decrease of expression 24 hours post-RT in the validation cohort. Moreover, miR-29c, miR-451 and miR-424 were correlated with the end-diastolic diameter of the left ventricle, which was also confirmed in multivariable analysis adjusting for RT-associated factors.
    Conclusion: We identified a subset of circulating miRNAs predictive for cardiac function impairment in patients treated for left-sided breast cancer, although longer clinical observation could determine if these can be used to predict major clinical endpoints.
    Language English
    Publishing date 2023-05-18
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 2649216-7
    ISSN 2234-943X
    ISSN 2234-943X
    DOI 10.3389/fonc.2023.1150979
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  10. Article ; Online: Natural Language Processing Methods to Empirically Explore Social Contexts and Needs in Cancer Patient Notes.

    Derton, Abigail / Guevara, Marco / Chen, Shan / Moningi, Shalini / Kozono, David E / Liu, Dianbo / Miller, Timothy A / Savova, Guergana K / Mak, Raymond H / Bitterman, Danielle S

    JCO clinical cancer informatics

    2023  Volume 7, Page(s) e2200196

    Abstract: Purpose: There is an unmet need to empirically explore and understand drivers of cancer disparities, particularly social determinants of health. We explored natural language processing methods to automatically and empirically extract clinical ... ...

    Abstract Purpose: There is an unmet need to empirically explore and understand drivers of cancer disparities, particularly social determinants of health. We explored natural language processing methods to automatically and empirically extract clinical documentation of social contexts and needs that may underlie disparities.
    Methods: This was a retrospective analysis of 230,325 clinical notes from 5,285 patients treated with radiotherapy from 2007 to 2019. We compared linguistic features among White versus non-White, low-income insurance versus other insurance, and male versus female patients' notes. Log odds ratios with an informative Dirichlet prior were calculated to compare words over-represented in each group. A variational autoencoder topic model was applied, and topic probability was compared between groups. The presence of machine-learnable bias was explored by developing statistical and neural demographic group classifiers.
    Results: Terms associated with varied social contexts and needs were identified for all demographic group comparisons. For example, notes of non-White and low-income insurance patients were over-represented with terms associated with housing and transportation, whereas notes of White and other insurance patients were over-represented with terms related to physical activity. Topic models identified a social history topic, and topic probability varied significantly between the demographic group comparisons. Classification models performed poorly at classifying notes of non-White and low-income insurance patients (F1 of 0.30 and 0.23, respectively).
    Conclusion: Exploration of linguistic differences in clinical notes between patients of different race/ethnicity, insurance status, and sex identified social contexts and needs in patients with cancer and revealed high-level differences in notes. Future work is needed to validate whether these findings may play a role in cancer disparities.
    MeSH term(s) Humans ; Male ; Female ; Natural Language Processing ; Retrospective Studies ; Social Environment ; Neoplasms/diagnosis ; Neoplasms/epidemiology ; Neoplasms/therapy
    Language English
    Publishing date 2023-05-20
    Publishing country United States
    Document type Journal Article ; Research Support, Non-U.S. Gov't
    ISSN 2473-4276
    ISSN (online) 2473-4276
    DOI 10.1200/CCI.22.00196
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

To top