-
JCO Clinical Cancer Informatics Jun 2024The estimation of prognosis and life expectancy is critical in the care of patients with advanced cancer. To aid clinical decision making, we build a prognostic strategy...
PURPOSE
The estimation of prognosis and life expectancy is critical in the care of patients with advanced cancer. To aid clinical decision making, we build a prognostic strategy combining a machine learning (ML) model with explainable artificial intelligence to predict 1-year survival after palliative radiotherapy (RT) for bone metastasis.
MATERIALS AND METHODS
Data collected in the multicentric PRAIS trial were extracted for 574 eligible adults diagnosed with metastatic cancer. The primary end point was the overall survival (OS) at 1 year (1-year OS) after the start of RT. Candidate covariate predictors consisted of 13 clinical and tumor-related pre-RT patient characteristics, seven dosimetric and treatment-related variables, and 45 pre-RT laboratory variables. ML models were developed and internally validated using the Python package. The effectiveness of each model was evaluated in terms of discrimination. A Shapley Additive Explanations (SHAP) explainability analysis to infer the global and local feature importance and to understand the reasons for correct and misclassified predictions was performed.
RESULTS
The best-performing model for the classification of 1-year OS was the extreme gradient boosting algorithm, with AUC and F1-score values equal to 0.805 and 0.802, respectively. The SHAP technique revealed that higher chance of 1-year survival is associated with low values of interleukin-8, higher values of hemoglobin and lymphocyte count, and the nonuse of steroids.
CONCLUSION
An explainable ML approach can provide a reliable prediction of 1-year survival after RT in patients with advanced cancer. The implementation of SHAP analysis provides an intelligible explanation of individualized risk prediction, enabling oncologists to identify the best strategy for patient stratification and treatment selection.
Topics: Humans; Machine Learning; Bone Neoplasms; Palliative Care; Male; Female; Prognosis; Aged; Middle Aged; Algorithms
PubMed: 38917384
DOI: 10.1200/CCI.24.00027 -
Health Science Reports Jun 2024Multiple diabetes care guidelines have called for the personalization of risk factor goals, medication management, and self-care plans among older patients. Study of the...
BACKGROUND AND AIMS
Multiple diabetes care guidelines have called for the personalization of risk factor goals, medication management, and self-care plans among older patients. Study of the implementation of these recommendations is needed. This study aimed to test whether a patient survey embedded in the Electronic Healthcare Record (EHR), coupled with telephonic nurse care management, could engage patients in personalized goal setting and chronic disease management.
METHODS
We conducted a single-center equal-randomization delayed comparator trial at the primary care clinics of the University of Chicago Medicine from 2018.6 to 2019.12. Patients over the age of 65 years with type 2 diabetes with an active patient portal account were recruited and randomized to receive an EHR embedded goal setting and preference survey immediately in the intervention arm or after 6 months in the delayed intervention control arm. In the intervention arm, nurses reviewed American Diabetes Association recommendations for A1C goals based on health status class, established personalized goals, and provided monthly telephonic care management phone calls for a maximum of 6 months. Our primary outcome was the documentation of a personalized A1C goal in the EHR.
RESULTS
A total of 100 patients completed the trial (mean age, 72.51 [SD, 5.22] years; mean baseline A1C, 7.14% [SD, 1.06%]; 68% women). The majority were in the Healthy (59%) followed by Complex (30%) and Very Complex (11%) health status classes. Documentation of an A1C goal in the EHR increased from 42% to 90% ( < 0.001) at 6 months in the intervention group and from 54% to 56% in the control group. Across health status classes, patients set similar A1C goals.
CONCLUSIONS
Older patients can be engaged in personalized goal setting and disease management through an embedded EHR intervention. The clinical impact of the intervention may differ if deployed among older patients with more complex health needs and higher glucose levels.
TRIAL REGISTRATION
ClinicalTrials.gov Identifier: NCT03692208.
PubMed: 38915356
DOI: 10.1002/hsr2.2208 -
Journal of Clinical Pathology Jun 2024Next generation sequencing (NGS) on tumour tissue is integral to the delivery of personalised medicine and targeted therapy. NGS on liquid biopsy, a much less invasive...
Implementation of an ISO 15189 accredited next generation sequencing service for cell-free total nucleic acid (cfTNA) analysis to facilitate driver mutation reporting in blood: the experience of a clinical diagnostic laboratory.
AIMS
Next generation sequencing (NGS) on tumour tissue is integral to the delivery of personalised medicine and targeted therapy. NGS on liquid biopsy, a much less invasive technology, is an emerging clinical tool that has rapidly expanded clinical utility. Gene mutations in cell-free total nucleic acids (cfTNA) circulating in the blood are representative of whole tumour biology and can reveal different mutations from different tumour sites, thus addressing tumour heterogeneity challenges.
METHODS
The novel Ion Torrent Genexus NGS system with automated sample preparation, onboard library preparation, templating, sequencing, data analysis and Oncomine Reporter software was used. cfTNA extracted from plasma was verified with the targeted pan-cancer (~50 genes) Oncomine Precision Assay (OPA). Assessment criteria included analytical sensitivity, specificity, limits of detection (LOD), accuracy, repeatability, reproducibility and the establishment of performance metrics.
RESULTS
An ISO 15189 accredited, minimally invasive cfTNA NGS diagnostic service has been implemented. High sensitivity (>83%) and specificity between plasma and tissue were observed. A sequencing LOD of 1.2% was achieved when the depth of coverage was >22 000×. A reduction (>68%) in turnaround time (TAT) of liquid biopsy results was achieved: 5 days TAT for in-house analysis from sample receipt to a final report issued to oncologists as compared with >15 days from reference laboratories.
CONCLUSION
Tumour-derived somatic variants can now be reliably assessed from plasma to provide minimally invasive tumour profiling. Successful implementation of this accredited service resulted in:Appropriate molecular profiling of patients where tumour tissue is unavailable or inaccessible.Rapid TAT of plasma NGS results.
PubMed: 38914446
DOI: 10.1136/jcp-2024-209514 -
The Oncologist Jun 2024To describe reasons for deviations from planned chemotherapy treatments in women with nonmetastatic breast cancer that contribute to less-than-planned receipt of...
BACKGROUND
To describe reasons for deviations from planned chemotherapy treatments in women with nonmetastatic breast cancer that contribute to less-than-planned receipt of chemotherapy.
METHODS
Electronic medical records for patients receiving chemotherapy were reviewed for adverse events and treatment modifications. Log-binomial regression models were used to estimate relative risks (RRs) with 95% CIs to examine associations between chemotherapy modifications, patient characteristics, and treatment modalities.
RESULTS
Delays in chemotherapy initiation (7%) were for surgical complications (58%), personal reasons (16%), and other (26%; port malfunction, infections, and obtaining extra imaging). Delays during chemotherapy (38%) were for infections (20%), neutropenia (13%), and personal reasons (13%). Dose reductions (38%) were for neuropathy (36%), unknown causes (9%), anemia (9%), and neutropenia (8%). Early treatment discontinuations (23%) were for neuropathy (29%). Patients receiving paclitaxel/nab-paclitaxel (RR 2.05; 95% CI, 1.47-2.87) and an anthracycline (RR 1.89; 95% CI, 1.39-2.57) reported more dose delays during chemotherapy. Black race (RR 1.46; 95% CI, 1.07-2.00), stage 3 (RR 1.79; 95% CI, 1.09-2.93), and paclitaxel/nab-paclitaxel receipt (RR 1.39; 95% CI, 1.02-1.90) increased the likelihood of dose reduction. Both Black race (RR 2.06; 95% CI, 1.35-3.15) and receipt of paclitaxel/nab-paclitaxel (RR 1.93; 95% CI, 1.19-3.13) increased the likelihood of early discontinuation. Patients receiving anthracyclines had higher rates of hospitalizations during chemotherapy (RR: 1.79; 95% CI, 1.11-2.89).
CONCLUSION
Toxicities are the most common reason for treatment modifications and need close monitoring in high-risk groups for timely intervention. Dose reductions and early treatment discontinuations occurred more for Black patients and need further study.
PubMed: 38913986
DOI: 10.1093/oncolo/oyae150 -
Acta Oncologica (Stockholm, Sweden) Jun 2024The delineation of intraprostatic lesions is vital for correct delivery of focal radiotherapy boost in patients with prostate cancer (PC). Errors in the delineation... (Comparative Study)
Comparative Study
BACKGROUND
The delineation of intraprostatic lesions is vital for correct delivery of focal radiotherapy boost in patients with prostate cancer (PC). Errors in the delineation could translate into reduced tumour control and potentially increase the side effects. The purpose of this study is to compare PET-based delineation methods with histopathology.
MATERIALS AND METHODS
The study population consisted of 15 patients with confirmed high-risk PC intended for prostatectomy. [68Ga]-PSMA-PET/MR was performed prior to surgery. Prostate lesions identified in histopathology were transferred to the in vivo [68Ga]-PSMA-PET/MR coordinate system. Four radiation oncologists manually delineated intraprostatic lesions based on PET data. Various semi-automatic segmentation methods were employed, including absolute and relative thresholds, adaptive threshold, and multi-level Otsu threshold.
RESULTS
The gross tumour volumes (GTVs) delineated by the oncologists showed a moderate level of interobserver agreement with Dice similarity coefficient (DSC) of 0.68. In comparison with histopathology, manual delineations exhibited the highest median DSC and the lowest false discovery rate (FDR) among all approaches. Among semi-automatic approaches, GTVs generated using standardized uptake value (SUV) thresholds above 4 (SUV > 4) demonstrated the highest median DSC (0.41), with 0.51 median lesion coverage ratio, FDR of 0.66 and the 95th percentile of the Hausdorff distance (HD95%) of 8.22 mm.
INTERPRETATION
Manual delineations showed a moderate level of interobserver agreement. Compared to histopathology, manual delineations and SUV > 4 exhibited the highest DSC and the lowest HD95% values. The methods that resulted in a high lesion coverage were associated with a large overestimation of the size of the lesions.
Topics: Humans; Male; Prostatic Neoplasms; Gallium Radioisotopes; Tumor Burden; Gallium Isotopes; Positron-Emission Tomography; Aged; Prostatectomy; Middle Aged; Radiopharmaceuticals; Oligopeptides; Magnetic Resonance Imaging; Edetic Acid
PubMed: 38912830
DOI: 10.2340/1651-226X.2024.39041 -
Physics and Imaging in Radiation... Apr 2024Magnetic Resonance Imaging (MRI) guided stereotactic body radiotherapy (SBRT) of liver metastases is an upcoming high-precision non-invasive treatment. Interobserver...
BACKGROUND AND PURPOSE
Magnetic Resonance Imaging (MRI) guided stereotactic body radiotherapy (SBRT) of liver metastases is an upcoming high-precision non-invasive treatment. Interobserver variation (IOV) in tumor delineation, however, remains a relevant uncertainty for planning target volume (PTV) margins. The aims of this study were to quantify IOV in MRI-based delineation of the gross tumor volume (GTV) of liver metastases and to detect patient-specific factors influencing IOV.
MATERIALS AND METHODS
A total of 22 patients with liver metastases from three primary tumor origins were selected (colorectal(8), breast(6), lung(8)). Delineation guidelines and planning MRI-scans were provided to eight radiation oncologists who delineated all GTVs. All delineations were centrally peer reviewed to identify outliers not meeting the guidelines. Analyses were performed both in- and excluding outliers. IOV was quantified as the standard deviation (SD) of the perpendicular distance of each observer's delineation towards the median delineation. The correlation of IOV with shape regularity, tumor origin and volume was determined.
RESULTS
Including all delineations, average IOV was 1.6 mm (range 0.6-3.3 mm). From 160 delineations, in total fourteen single delineations were marked as outliers after peer review. After excluding outliers, the average IOV was 1.3 mm (range 0.6-2.3 mm). There was no significant correlation between IOV and tumor origin or volume. However, there was a significant correlation between IOV and regularity (Spearman's ρ = -0.66; p = 0.002).
CONCLUSION
MRI-based IOV in tumor delineation of liver metastases was 1.3-1.6 mm, from which PTV margins for IOV can be calculated. Tumor regularity and IOV were significantly correlated, potentially allowing for patient-specific margin calculation.
PubMed: 38912009
DOI: 10.1016/j.phro.2024.100592 -
Cancer Imaging : the Official... Jun 2024Preserved ratio impaired spirometry (PRISm) and chronic obstructive pulmonary disease (COPD) belong to lung function injury. PRISm is a precursor to COPD. We compared...
PURPOSE
Preserved ratio impaired spirometry (PRISm) and chronic obstructive pulmonary disease (COPD) belong to lung function injury. PRISm is a precursor to COPD. We compared and evaluated the different basic information, imaging findings and survival curves of 108 lung cancer patients with different pulmonary function based on high resolution computed tomography (HRCT).
METHODS
This retrospective study was performed on 108 lung cancer patients who did pulmonary function test (PFT) and thoracic HRCT. The basic information was evaluated: gender, age, body mass index (BMI), smoke, smoking index (SI). The following pulmonary function findings were evaluated: forced expiratory volume in 1s (FEV), forced vital capacity (FVC), FEV/FVC ratio. The following computed tomography (CT) findings were evaluated: appearance (bronchiectasis, pneumonectasis, atelectasis, ground-glass opacities [GGO], interstitial inflammation, thickened bronchial wall), diameter (aortic diameter, pulmonary artery diameter, MPAD/AD ratio, inferior vena cava diameter [IVCD]), tumor (volume, classification, distribution, staging [I, II, III, IV]). Mortality rates were calculated and survival curves were estimated using the Kaplan-Meier method.
RESULTS
Compared with normal pulmonary function group, PRISm group and COPD group were predominantly male, older, smoked more, poorer lung function and had shorter survival time after diagnosis. There were more abnormal images in PRISm group and COPD group than in normal lung function group (N-C group). In PRISm group and COPD group, lung cancer was found late, and the tumor volume was larger, mainly central squamous carcinoma. But the opposite was true for the N-C group. The PRISm group and COPD group had significant poor survival probability compared with the normal lung function group.
CONCLUSIONS
Considerable differences regarding basic information, pulmonary function, imaging findings and survival curves are found between normal lung function group and lung function injury group. Lung function injury (PRISm and COPD) should be taken into account in future lung cancer screening studies.
Topics: Humans; Male; Female; Lung Neoplasms; Middle Aged; Aged; Retrospective Studies; Tomography, X-Ray Computed; Respiratory Function Tests; Pulmonary Disease, Chronic Obstructive; Adult; Aged, 80 and over; Lung
PubMed: 38910260
DOI: 10.1186/s40644-024-00720-9 -
The Oncologist Jun 2024HER2, encoded by the ERBB2 gene, is an important druggable driver of human cancer gaining increasing importance as a therapeutic target in urothelial carcinoma (UC). The...
HER2, encoded by the ERBB2 gene, is an important druggable driver of human cancer gaining increasing importance as a therapeutic target in urothelial carcinoma (UC). The genomic underpinnings of HER2 overexpression in ERBB2 nonamplified UC are poorly defined. To address this knowledge gap, we investigated 172 UC tumors from patients treated at the University of California San Francisco, using immunohistochemistry and next-generation sequencing. We found that GATA3 and PPARG copy number gains individually predicted HER2 protein expression independently of ERBB2 amplification. To validate these findings, we interrogated the Memorial Sloan Kettering/The Cancer Genome Atlas (MSK/TCGA) dataset and found that GATA3 and PPARG copy number gains individually predicted ERBB2 mRNA expression independently of ERBB2 amplification. Our findings reveal a potential link between the luminal marker HER2 and the key transcription factors GATA3 and PPARG in UC and highlight the utility of examining GATA3 and PPARG copy number states to identify UC tumors that overexpress HER2 in the absence of ERBB2 amplification. In summary, we found that an increase in copy number of GATA3 and PPARG was independently associated with higher ERBB2 expression in patient samples of UC. This finding provides a potential explanation for HER2 overexpression in UC tumors without ERBB2 amplification and a way to identify these tumors for HER2-targeted therapies.
PubMed: 38908022
DOI: 10.1093/oncolo/oyae127 -
The Oncologist Jun 2024The value of serum biomarkers, particularly alpha-fetoprotein (AFP) and protein induced by vitamin K absence or antagonist-II (PIVKA-II), gains increasing attention in...
Prognostic significance of postoperative serological incomplete conversion of AFP and PIVKA-II after hepatic resection for hepatocellular carcinoma: a multicenter analysis of 1755 patients.
BACKGROUND
The value of serum biomarkers, particularly alpha-fetoprotein (AFP) and protein induced by vitamin K absence or antagonist-II (PIVKA-II), gains increasing attention in prognostic evaluation and recurrence monitoring for patients with hepatocellular carcinoma (HCC). This study investigated the implications of serological incomplete conversion (SIC) of these 2 biomarkers as prognostic indicators for long-term outcomes after HCC resection.
METHODS
A multicenter observational study was conducted on a cohort of HCC patients presenting with AFP (>20 ng/mL) or PIVKA-II (>40 mAU/mL) positivity who underwent curative-intent resection. Based on their postoperative AFP and PIVKA-II levels at first postoperative follow-up (4~8 weeks after surgery), these patients were stratified into the serological incomplete conversion (SIC) and serological complete conversion (SCC) groups. The study endpoints were recurrence and overall survival (OS).
RESULTS
Among 1755 patients, 379 and 1376 were categorized as having SIC and SCC, respectively. The SIC group exhibited 1- and 5-year OS rates of 67.5% and 26.3%, with the corresponding recurrence rates of 53.2% and 79.0%, respectively; while the SCC group displayed 1- and 5-year OS rates of 95.8% and 62.5%, with the corresponding recurrence rates of 16.8% and 48.8%, respectively (both P < .001). Multivariate Cox regression analysis demonstrated that postoperative SIC was an independent risk factor for both increased recurrence (HR: 2.40, 95% CI, 2.04-2.81, P < .001) and decreased OS (HR: 2.69, 95% CI, 2.24-3.24, P < .001).
CONCLUSION
The results emphasize that postoperative incomplete conversion of either AFP or PIVKA-II is a significant prognostic marker, indicating a higher risk for adverse oncologic outcomes following HCC resection. This revelation has crucial implications for refining postoperative adjuvant therapy and surveillance strategies for HCC patients.
PubMed: 38907676
DOI: 10.1093/oncolo/oyae139 -
The Oncologist Jun 2024Tumor microenvironment (TME) characteristics including tumor stroma ratio (TSR), tumor budding (TB), and tumor-infiltrating lymphocytes (TILs) were examined in resected...
BACKGROUND
Tumor microenvironment (TME) characteristics including tumor stroma ratio (TSR), tumor budding (TB), and tumor-infiltrating lymphocytes (TILs) were examined in resected gastric cancer. These TME features have been shown to indicate metastatic potential in colon cancer, and intestinal-type gastric cancer (IGC) has pathological similarities with that malignancy.
METHODS
TSR, TB, and TILs were quantified in routine histological sections from 493 patients with IGC who underwent radical resection at 2 university hospitals in China from 2010 to 2016. TME variables were dichotomized as follows: TSR (50%), TILs (median), TB per international guidelines (4 buds/0.785mm2), and platelet-lymphocyte ratio (PLR) per survival ROC. Association of TME features with patient clinicopathological characteristics, time-to-recurrence (TTR), and cancer-specific-survival (CSS) were examined using univariate and multivariate analysis, including a relative contribution analysis by Cox regression.
RESULTS
Patients whose tumors showed high TSR or high TB or low TILs were each significantly associated with increased T and N stage, higher histological grade, and poorer TTR and CSS at 5 years. Only TSR and N stage were independently associated with TTR and CSS after adjustment for covariates. PLR was only independently associated with TTR after adjustment for covariates. Among the variables examined, only TSR was significantly associated with both TTR (HR 1.72, 95% CI, 1.14-2.60, P = .01) and CSS (HR 1.62, 95% CI, 1.05-2.51, P = .03) multivariately. Relative contribution to TTR revealed that the top 3 contributors were N stage (45.1%), TSR (22.5%), and PLR (12.9%), while the top 3 contributors to CSS were N stage (59.9%), TSR (14.7%), and PLR (10.9%).
CONCLUSIONS
Among the examined TME features, TSR was the most robust for prognostication and was significantly associated with both TTR and CSS. Furthermore, the relative contribution of TSR to patient TTR and CSS was second only to nodal status.
PubMed: 38907674
DOI: 10.1093/oncolo/oyae124