JCO Clinical Cancer Informatics最新文献

Purpose: Eastern Cooperative Oncology Group performance status (ECOG PS) is a key confounder in comparative effectiveness research, predicting treatment and survival, but is often incomplete in electronic health records (EHRs). Imputation on the basis of classification metrics alone may introduce differences in survival between patients with known and imputed ECOG PS, complicating comparative effectiveness research. We developed an approach to impute ECOG PS so that those with known and imputed ECOG PS are indistinguishable in their survival, reducing potential biases introduced by the imputation.

Methods: We analyzed deidentified data from an EHR-derived database for patients with advanced non-small cell lung cancer (aNSCLC) at their first line of treatment. Our novel imputation method involved (1) sample-splitting patients with known ECOG PS into modeling and thresholding data sets, (2) developing a predictive model of ECOG PS, (3) determining an optimal threshold aligning clinical outcomes, where a choice of outcome metric may depend on the use case, and (4) applying the model and threshold to impute missing ECOG PS. We evaluated the approach using binary classification metrics and alignment of survival metrics between observed and imputed ECOG PS.

Results: Of 62,101 patients, 13,297 (21%) had missing ECOG PS at the start of their first treatment. Our method achieved similar or better performance in accuracy (73.3%), sensitivity (42.4%), and specificity (81%) compared with other techniques, with smaller survival metric differences between observed and imputed ECOG PS, with differences of 0.07 in hazard ratio, -0.36 months in median survival for good ECOG PS (<2), and -0.39 months for poor ECOG PS (≥2).

Conclusion: Our imputed ECOG PS aligning clinical outcomes enhanced the use of real-world EHR data of patients with aNSCLC for comparative effectiveness research.

Purpose: Endocrine treatments for patients with hormone-sensitive breast cancer are associated with significant side effects that can negatively affect health-related quality of life and result in treatment discontinuation. The objective of this qualitative study was to obtain feedback from stakeholder clinicians and patients about an online interactive tool that was designed to provide information and visualizations of breast cancer symptoms.

Methods: The online Breast Cancer Symptom Explorer tool was developed to allow patients to visualize trajectories for common symptoms associated with tamoxifen and anastrozole using symptom data from the NSABP B35 breast cancer clinical trial. To refine the tool, virtual focus groups were conducted among oncology clinicians and women with a history of breast cancer who had received treatment with an aromatase inhibitor or tamoxifen, seeking feedback on the tool and its potential usefulness. Discussions took place using a secure web-conferencing platform following a semi-structured interview guide. Focus groups were audio-recorded, transcribed, and analyzed using reflexive thematic analysis.

Results: Nine focus groups were conducted (n = 21 participants: eight clinicians and 13 patients). Key benefits and barriers to tool use emerged from the discussions. Both patients and oncologists valued the ability to engage with the tool and visualize symptoms over time. They indicated that ideal settings for its use would be at home before treatment initiation. Combinations of graphical representations with text were perceived to be most effective in communicating symptoms. Key barriers identified included concerns about accessibility to the tool and digital literacy, with recommendations to simplify the text and provide health literacy support to enhance its clinical utility in the future.

Conclusion: Clinician and patient involvement was critical for refinement of the breast cancer symptom explorer and provided insights into its future use and evaluation of the tool in clinical decision making.

Purpose: The use of real-world data (RWD) in oncology is becoming increasingly important for clinical decision making and tailoring treatment. Despite the significant success of targeted therapy and immunotherapy in advanced melanoma, substantial variability in clinical responses to these treatments emphasizes the need for personalized approaches to therapy.

Materials and methods: In this pilot study, 239 patients with melanoma were included to predict the response to both targeted therapies and immunotherapies. We used machine learning (ML) to incorporate RWD and applied explainable artificial intelligence (XAI) to explain the individual predictions.

Results: We developed, validated, and compared four ML models to evaluate 2-year survival using RWD. Our research showed encouraging outcomes, achieving an AUC of more than 80% and an estimated accuracy of over 74% across the four ML models. The random forest model exhibited the highest performance in predicting 2-year survival with an AUC of 0.85. Local interpretable model-agnostic explanations was used to explain individual predictions and provide trust and insights into the clinical implications of the ML model.

Conclusion: With this proof-of-concept, we integrated RWD into predictive modeling using ML techniques to predict clinical outcomes and explore their potential implications for clinical decision making. The potential of XAI was demonstrated to enhance trust and improve the usability of the model in clinical settings. Further research, including foundation modeling and generative AI, will likely increase the predictive power of prognostic and predictive ML models in advanced melanoma.

Purpose: Guidelines recommend omission of sentinel lymph node biopsy (SLNB) for axillary staging in select patients age 70 years and older with early-stage estrogen receptor-positive (ER+), human epidermal growth factor receptor 2 neu-negative (HER2-) invasive breast cancers (BCs). However, many women meeting criteria for SLNB omission continue to receive this procedure. This study aims to stratify patients into risk cohorts for nodal positivity that can be incorporated into deimplementation strategies to reduce low-value SLNB procedures.

Methods: A retrospective cohort analysis using the National Cancer Database was performed on patients age 70 years and older with ER+/HER2-, cT1-2, cN0, cM0 BC who underwent breast surgery from 2018 to 2021. Patients who received neoadjuvant therapies were excluded. Recursive partitioning analysis (RPA) was used to develop two models to estimate nodal positivity: (1) a clinical model for preoperative use to decide whether to perform SLNB and (2) a pathologic model for postoperative use to guide adjuvant decisions in cases of SLNB omission.

Results: The study included 68,867 patients who received SLNB; 13.4% had a tumor-involved lymph node. RPA on the basis of clinical covariates demonstrated <8% risk of nodal positivity for patients with cT1mi-cT1b and grade 1-2 tumors. RPA on the basis of pathologic covariates found <10% risk of nodal positivity for patients with pT1 tumors without lymphovascular invasion (LVI). Patients with cT2 or pT2 without LVI and nonductal/nonlobular histology had <5% risk of nodal positivity.

Conclusion: This study demonstrates a low risk of nodal positivity for patients with cT1 or pT1 tumors. Our RPA-defined subgroups offer a novel approach to predict nodal positivity in patients age 70 years and older with early-stage, ER+/HER2- invasive BC that can be incorporated in deimplementation strategies to reduce low-value axillary surgery.

Purpose: With the aid of ever-increasing computing resources, many deep learning algorithms have been proposed to aid in diagnostic workup for clinicians. However, existing studies usually selected informative patches from whole-slide images for the training of the deep learning model, requiring labor-intensive labeling efforts. This work aimed to improve diagnostic accuracy through the statistic features extracted from hematoxylin and eosin-stained slides.

Methods: We designed a computational pipeline for the diagnosis of inverted urothelial papilloma (IUP) of the bladder from its cancer mimics using statistical features automatically extracted from whole-slide images. Whole-slide images from 225 cases of common and uncommon urothelial lesions (64 IUPs; 69 inverted urothelial carcinomas [UCInvs], and 92 low-grade urothelial carcinoma [UCLG]) were analyzed.

Results: We identified 68 image features in total that were significantly different between IUP and UCInv and 42 image features significantly different between IUP and UCLG. Our method integrated multiple types of image features and achieved high AUCs (the AUCs) of 0.913 and 0.920 for classifying IUP from UCInv and conventional UC, respectively. Moreover, we constructed an ensemble classifier to test the prediction accuracy of IUP from an external validation cohort, which provided a new workflow to diagnose rare cancer subtypes and test the models with limited validation samples.

Conclusion: Our data suggest that the proposed computational pipeline can robustly and accurately capture histopathologic differences between IUP and other UC subtypes. The proposed workflow and related findings have the potential to expand the clinician's armamentarium for accurate diagnosis of urothelial malignancies and other rare tumors.

Purpose: Pathologists diagnose prostate cancer (PCa) on hematoxylin and eosin (HE)-stained sections of prostate needle biopsies (PBx). Some laboratories use costly immunohistochemistry (IHC) for all cases to optimize workflow, often exceeding reimbursement for the full specimen. Despite the rise in digital pathology and artificial intelligence (AI) algorithms, clinical implementation studies are scarce. This prospective clinical trial evaluated whether an AI-assisted workflow for detecting PCa in PBx reduces IHC use while maintaining diagnostic safety standards.

Methods: Patients suspected of PCa were allocated biweekly to either a control or intervention arm. In the control arm, pathologists assessed whole-slide images (WSI) of PBx using HE and IHC stainings. In the intervention arm, pathologists used the Paige Prostate Detect AI algorithm on HE slides, requesting IHC only as needed. IHC was requested for all morphologically negative slides in the AI arm. The main outcome was the relative risk (RR) of IHC use per detected PCa case at both patient and WSI levels.

Results: Overall, 143 of 237 (60.3%) slides of 64 of 82 patients contained PCa (78.0%). AI assistance significantly reduced the risk of IHC use per detected PCa case at both the patient level (RR, 0.55; 95% CI, 0.39 to 0.72) and slide level (RR, 0.41; 95% CI, 0.29 to 0.52). Cost reductions on IHC were €1,700 for the trial, at €50 per IHC stain. AI-assisted pathologists reported higher confidence in their diagnoses (80% v 56% confident or high confidence). The median assessment time per HE slide showed no significant difference between the AI-assisted and control arms (139 seconds v 112 seconds; P = .2).

Conclusion: This study demonstrates that AI assistance for PCa detection in PBx significantly reduces IHC costs while maintaining diagnostic safety standards, supporting the business case for AI implementation in PCa detection.

Purpose: Understanding the genetic heterogeneity of Lynch syndrome (LS) cancers has led to significant scientific advancements. However, these findings are widely dispersed across various resources, making it difficult for clinicians and researchers to stay informed. Furthermore, the uneven quality of studies and the lack of effective translation of knowledge into clinical practice create challenges in delivering optimal patient care. To address these issues, we developed and launched the Precision Lynch Syndrome Knowledge Base (PLSKB), a specialized, interactive web-based platform that consolidates comprehensive information on LS.

Methods: To create the PLSKB, we conducted an extensive literature review and gathered data from reliable sources. Through an extensive literature review and survey of other reliable sources, we have extracted prominent and relevant content with a high level of accuracy, transparency, and detailed provenance. To enhance usability, we implemented an evidence-leveling framework, categorizing studies on the basis of the type of research, reliability, and applicability to clinical care. The platform is designed to be dynamic, with updates performed monthly to incorporate the latest research.

Results: The PLSKB integrates a broad spectrum of data related to LS, including biomarkers, cancer types, screening and prevention strategies, diagnostic methods, and therapeutics options. This centralized resource is intended to support clinicians and researchers in making evidence-based decisions throughout surveillance and care processes. Its interactive design and frequent updates ensure that users have access to the most current and relevant findings.

Conclusion: The PLSKB bridges the gap between research and clinical practice by offering a reliable, up-to-date repository of evidence-based information. This tool empowers clinicians and researchers to deliver precision care and advance research for LS and related conditions, ultimately improving patient outcomes.

Purpose: To determine the accuracy of large language models (LLMs) in generating appropriate treatment options for patients with early breast cancer on the basis of their medical records.

Materials and methods: Retrospective study using anonymized medical records of patients with BC presented during multidisciplinary team meetings (MDTs) between January and April 2024. Three generalist artificial intelligence models (Claude3-Opus, GPT4-Turbo, and LLaMa3-70B) were used to generate treatment suggestions, which were compared with experts' decisions. The primary outcome was the rate of appropriate suggestions from the LLMs, compared with the reference experts' decisions. The secondary outcome was the LLMs' performances (F1 score and specificity) in generating appropriate suggestions for each treatment category.

Results: The rates of appropriate suggestions were 86.6% (97/112), 85.7% (96/112), and 75.0% (84/112) for Claude3-Opus, GPT4-Turbo, and LLaMa3-70B, respectively. No significant difference was found between Claude3-Opus and GPT4-Turbo (P = .85), but both tended to perform better than LLaMa3-70B (P = .027 and P = .043, respectively). LLMs showed high accuracy for adjuvant endocrine therapy and targeted therapy indications. However, they tended to overestimate the need for adjuvant radiotherapy and had variable performances in suggesting adjuvant chemotherapy and genomic tests.

Conclusion: LLMs, particularly Claude3-Opus and GPT4-Turbo, demonstrated promising accuracy in suggesting appropriate adjuvant treatments for patients with early BC on the basis of their medical records. Although LLMs showed limitations in validating surgery and indicating genomic tests, their performance in other treatment modalities highlights their potential to automate and augment decision making during MDTs. Further studies with fine-tuned LLMs and a prospective design are needed to demonstrate their utility in clinical practice.

Purpose: The COVID-19 pandemic disrupted normal mechanisms of health care delivery and facilitated the rapid and widespread implementation of telehealth technology. As a result, the effectiveness of virtual health care visits in diverse populations represents an important consideration. We used lung cancer screening as a prototype to determine whether subsequent adherence differs between virtual and in-person encounters in an urban, safety-net health care system.

Methods: We conducted a retrospective analysis of initial low-dose computed tomography (LDCT) ordered for lung cancer screening from March 2020 through February 2023 within Parkland Health, the integrated safety-net provider for Dallas County, TX. We collected data on patient characteristics, visit type, and LDCT completion from the electronic medical record. Associations among these variables were assessed using the chi-square test. We also performed interaction analyses according to visit type.

Results: Initial LDCT orders were placed for a total of 1,887 patients, of whom 43% were female, 45% were Black, and 17% were Hispanic. Among these orders, 343 (18%) were placed during virtual health care visits. From March to August 2020, 79 of 163 (48%) LDCT orders were placed during virtual visits; after that time, 264 of 1,724 (15%) LDCT orders were placed during virtual visits. No patient characteristics were significantly associated with visit type (in-person v virtual) or LDCT completion. Rates of LDCT completion were 95% after in-person visits and 97% after virtual visits (P = .13).

Conclusion: In a safety-net lung cancer screening population, patients were as likely to complete postvisit initial LDCT when ordered in a virtual encounter as in an in-person encounter.