Making sense of artificial intelligence and large language models-including ChatGPT-in pediatric hematology/oncology.

ChatGPT and other artificial intelligence (AI) systems have captivated the attention of healthcare providers and researchers for their potential to improve care processes and outcomes. While these technologies hold promise to automate processes, increase efficiency, and reduce cognitive burden, their use also carries risks. In this commentary, we review basic concepts of AI, outline some of the capabilities and limitations of currently available tools, discuss current and future applications in pediatric hematology/oncology, and provide an evaluation and implementation framework that can be used by pediatric hematologist/oncologists considering the use of AI in clinical practice.

Advancing clinical and translational research in germ cell tumours (GCT): recommendations from the Malignant Germ Cell International Consortium.

Germ cell tumours (GCTs) are a heterogeneous group of rare neoplasms that present in different anatomical sites and across a wide spectrum of patient ages from birth through to adulthood. Once these strata are applied, cohort numbers become modest, hindering inferences regarding management and therapeutic advances. Moreover, patients with GCTs are treated by different medical professionals including paediatric oncologists, neuro-oncologists, medical oncologists, neurosurgeons, gynaecological oncologists, surgeons, and urologists. Silos of care have thus formed, further hampering knowledge dissemination between specialists. Dedicated biobank specimen collection is therefore critical to foster continuous growth in our understanding of similarities and differences by age, gender, and site, particularly for rare cancers such as GCTs. Here, the Malignant Germ Cell International Consortium provides a framework to create a sustainable, global research infrastructure that facilitates acquisition of tissue and liquid biopsies together with matched clinical data sets that reflect the diversity of GCTs. Such an effort would create an invaluable repository of clinical and biological data which can underpin international collaborations that span professional boundaries, translate into clinical practice, and ultimately impact patient outcomes.

Creating a data commons: The INternational Soft Tissue SaRcoma ConsorTium (INSTRuCT).

In this article, we will discuss the genesis, evolution, and progress of the INternational Soft Tissue SaRcoma ConsorTium (INSTRuCT), which aims to foster international research and collaboration focused on pediatric soft tissue sarcoma. We will begin by highlighting the current state of clinical research for pediatric soft tissue sarcomas, including rhabdomyosarcoma and non-rhabdomyosarcoma soft tissue sarcoma. We will then explore challenges and research priorities, describe the development of INSTRuCT, and discuss how the consortium aims to address key research priorities.

Pharmacogenomic genotypes define genetic ancestry in patients and enable population-specific genomic implementation.

The importance of genetic ancestry characterization is increasing in genomic implementation efforts, and clinical pharmacogenomic guidelines are being published that include population-specific recommendations. Our aim was to test the ability of focused clinical pharmacogenomic SNP panels to estimate individual genetic ancestry (IGA) and implement population-specific pharmacogenomic clinical decision-support (CDS) tools. Principle components and STRUCTURE were utilized to assess differences in genetic composition and estimate IGA among 1572 individuals from 1000 Genomes, two independent cohorts of Caucasians and African Americans (AAs), plus a real-world validation population of patients undergoing pharmacogenomic genotyping. We found that clinical pharmacogenomic SNP panels accurately estimate IGA compared to genome-wide genotyping and identify AAs with ≥70 African ancestry (sensitivity >82%, specificity >80%, PPV >95%, NPV >47%). We also validated a new AA-specific warfarin dosing algorithm for patients with ≥70% African ancestry and implemented it at our institution as a novel CDS tool. Consideration of IGA to develop an institutional CDS tool was accomplished to enable population-specific pharmacogenomic guidance at the point-of-care. These capabilities were immediately applied for guidance of warfarin dosing in AAs versus Caucasians, but also provide a real-world model that can be extended to other populations and drugs as actionable genomic evidence accumulates.

Computer-assisted Curie scoring for metaiodobenzylguanidine (MIBG) scans in patients with neuroblastoma.

BACKGROUND: Radiolabeled metaiodobenzylguanidine (MIBG) is sensitive and specific for detecting neuroblastoma. The extent of MIBG-avid disease is assessed using Curie scores. Although Curie scoring is prognostic in patients with high-risk neuroblastoma, there is no standardized method to assess the response of specific sites of disease over time. The goal of this study was to develop approaches for Curie scoring to facilitate the calculation of scores and comparison of specific sites on serial scans. PROCEDURE: We designed three semiautomated methods for determining Curie scores, each with increasing degrees of computer assistance. Method A was based on visual assessment and tallying of MIBG-avid lesions. For method B, scores were tabulated from a schematic that associated anatomic regions to MIBG-positive lesions. For method C, an anatomic mesh was used to mark MIBG-positive lesions with automatic assignment and tallying of scores. Five imaging physicians experienced in MIBG interpretation scored 38 scans using each method, and the feasibility and utility of the methods were assessed using surveys. RESULTS: There was good reliability between methods and observers. The user-interface methods required 57 to 110 seconds longer than the visual method. Imaging physicians indicated that it was useful that methods B and C enabled tracking of lesions. Imaging physicians preferred method B to method C because of its efficiency. CONCLUSIONS: We demonstrate the feasibility of semiautomated approaches for Curie score calculation. Although more time was needed for strategies B and C, the ability to track and document individual MIBG-positive lesions over time is a strength of these methods.

Simplifying the use of pharmacogenomics in clinical practice: Building the genomic prescribing system.

BACKGROUND: A barrier to the use of genomic information during prescribing is the limited number of software solutions that combine a user-friendly interface with complex medical data. We built and designed an online, secure, electronic custom interface termed the Genomic Prescribing System (GPS). METHODS: Actionable pharmacogenomic (PGx) information was reviewed, collected, and stored in the back-end of GPS to enable creation of customized drug- and variant-specific clinical decision support (CDS) summaries. The database architecture utilized the star schema to store information. Patient raw genomic data underwent transformation via custom-designed algorithms to enable gene and phenotype-level associations. Multiple external data sets (PubMed, The Systematized Nomenclature of Medicine (SNOMED), National Drug File - Reference Terminology (ND-FRT), and a publically-available PGx knowledgebase) were integrated to facilitate the delivery of patient, drug, disease, and genomic information. Institutional security infrastructure was leveraged to securely store patient genomic and clinical data on a HIPAA-compliant server farm. RESULTS: As of May 17, 2016, the GPS back-end housed 257 CDS encompassing 112 genetic variants, 42 genes, and 46 PGx-actionable drugs. The GPS user interface presented patient-specific CDS alongside a recognizable traffic light symbol (green/yellow/red), denoting PGx risk for each genomic result. The number of traffic lights per visit increased with the corresponding increase in the number of available PGx-annotated drugs over time. An integrated drug and disease search functionality, links to primary literature sources, and potential alternative PGx drugs were indicated. The system, which was initially used as stand-alone CDS software within our clinical environment, was then integrated with the institutional electronic medical record for enhanced usability. There have been nearly 2000 logins in 43months since inception, with usage exceeding 56 logins per month and system up-times of 99.99%. For all patient-provider visits encompassing >3years of implementation, unique alert click-through rates corresponded to genomic risk: red lights clicked 100%, yellow lights 79%, green lights 43%. CONCLUSIONS: Successful deployment of GPS by combining complex data and recognizable iconography led to a tool that enabled point-of-care genomic delivery with high usability. Continued scalability and incorporation of additional clinical elements to be considered alongside PGx information could expand future impact.

A method for whole protein isolation from human cranial bone.

The presence of the dense hydroxyapatite matrix within human bone limits the applicability of conventional protocols for protein extraction. This has hindered the complete and accurate characterization of the human bone proteome thus far, leaving many bone-related disorders poorly understood. We sought to refine an existing method of protein extraction from mouse bone to extract whole proteins of varying molecular weights from human cranial bone. Whole protein was extracted from human cranial suture by mechanically processing samples using a method that limits protein degradation by minimizing heat introduction to proteins. The presence of whole protein was confirmed by western blotting. Mass spectrometry was used to sequence peptides and identify isolated proteins. The data have been deposited to the ProteomeXchange with identifier PXD003215. Extracted proteins were characterized as both intra- and extracellular and had molecular weights ranging from 9.4 to 629 kDa. High correlation scores among suture protein spectral counts support the reproducibility of the method. Ontology analytics revealed proteins of myriad functions including mediators of metabolic processes and cell organelles. These results demonstrate a reproducible method for isolation of whole protein from human cranial bone, representing a large range of molecular weights, origins and functions.

A Phase I New Approaches to Neuroblastoma Therapy Study of Buthionine Sulfoximine and Melphalan With Autologous Stem Cells for Recurrent/Refractory High-Risk Neuroblastoma.

BACKGROUND: Myeloablative therapy for high-risk neuroblastoma commonly includes melphalan. Increased cellular glutathione (GSH) can mediate melphalan resistance. Buthionine sulfoximine (BSO), a GSH synthesis inhibitor, enhances melphalan activity against neuroblastoma cell lines, providing the rationale for a Phase 1 trial of BSO-melphalan. PROCEDURES: Patients with recurrent/resistant high-risk neuroblastoma received BSO (3 gram/m(2) bolus, then 24 grams/m(2) /day infusion days -4 to -2), with escalating doses of intravenous melphalan (20-125 mg/m(2) ) days -3 and -2, and autologous stem cells day 0 using 3 + 3 dose escalation. RESULTS: Among 28 patients evaluable for dose escalation, one dose-limiting toxicity occurred at 20 mg/m(2) melphalan (grade 3 aspartate aminotransferase/alanine aminotransferase) and one at 80 mg/m(2) (streptococcal bacteremia, grade 4 hypotension/pulmonary/hypocalcemia) without sequelae. Among 25 patients evaluable for response, there was one partial response (PR) and two mixed responses (MRs) among eight patients with prior melphalan exposure; one PR and three MRs among 16 patients without prior melphalan; one stable disease with unknown melphalan history. Melphalan pharmacokinetics with BSO were similar to reports for melphalan alone. Melphalan Cmax for most patients was below the 10 µM concentration that showed neuroblastoma preclinical activity with BSO. CONCLUSIONS: BSO (75 gram/m(2) ) with melphalan (125 mg/m(2) ) is tolerable with stem cell support and active in recurrent/refractory neuroblastoma. Further dose escalation is feasible and may increase responses.

An Approach to Acquiring, Normalizing, and Managing EHR Data From a Clinical Data Repository for Studying Pressure Ulcer Outcomes.

Changes in the methods that individual facilities follow to collect and store data related to hospital-acquired pressure ulcer (HAPU) occurrences are essential for improving patient outcomes and advancing our understanding the science behind this clinically relevant issue. Using an established electronic health record system at a large, urban, tertiary-care academic medical center, we investigated the process required for taking raw data of HAPU outcomes and submitting these data to a normalization process. We extracted data from 1.5 million patient shifts and filtered observations to those with a Braden score and linked tables in the electronic health record, including (1) Braden scale scores, (2) laboratory outcomes data, (3) surgical time, (4) provider orders, (5) medications, and (6) discharge diagnoses. Braden scores are important measures specific to HAPUs since these scores clarify the daily risk of a hospitalized patient for developing a pressure ulcer. The other more common measures that may be associated with HAPU outcomes are important to organize in a single data frame with Braden scores according to each patient. Primary keys were assigned to each table, and the data were processed through 3 normalization steps and 1 denormalization step. These processes created 8 tables that can be stored efficiently in a clinical database of HAPU outcomes. As hospitals focus on organizing data for review of HAPUs and other types of hospital-acquired conditions, the normalization process we describe in this article offers directions for collaboration between providers and informatics teams using a common language and structure.

N-linked glycan profiling in neuroblastoma cell lines.

Although MYCN amplification has been associated with aggressive neuroblastoma, the molecular mechanisms that differentiate low-risk, MYCN-nonamplified neuroblastoma from high-risk, MYCN-amplified disease are largely unknown. Genomic and proteomic studies have been limited in discerning differences in signaling pathways that account for this heterogeneity. N-Linked glycosylation is a common protein modification resulting from the attachment of sugars to protein residues and is important in cell signaling and immune response. Aberrant N-linked glycosylation has been routinely linked to various cancers. In particular, glycomic markers have often proven to be useful in distinguishing cancers from precancerous conditions. Here, we perform a systematic comparison of N-linked glycomic variation between MYCN-nonamplified SY5Y and MYCN-amplified NLF cell lines with the aim of identifying changes in sugar abundance linked to high-risk neuroblastoma. Through a combination of liquid chromatography-mass spectrometry and bioinformatics analysis, we identified 16 glycans that show a statistically significant change in abundance between NLF and SY5Y samples. Closer examination revealed the preference for larger (in terms of total monosaccharide count) and more sialylated glycan structures in the MYCN-amplified samples in comparison to smaller, nonsialylated glycans that are more dominant in the MYCN-nonamplified samples. These results offer clues for deriving marker candidates for accurate neuroblastoma risk diagnosis.

Proteomic profiling of naïve multiple myeloma patient plasma cells identifies pathways associated with favourable response to bortezomib-based treatment regimens.

Toward our goal of personalized medicine, we comprehensively profiled pre-treatment malignant plasma cells from multiple myeloma patients and prospectively identified pathways predictive of favourable response to bortezomib-based treatment regimens. We utilized two complementary quantitative proteomics platforms to identify differentially-regulated proteins indicative of at least a very good partial response (VGPR) or complete response/near complete response (CR/nCR) to two treatment regimens containing either bortezomib, liposomal doxorubicin and dexamethasone (VDD), or lenalidomide, bortezomib and dexamethasone (RVD). Our results suggest enrichment of 'universal response' pathways that are common to both treatment regimens and are probable predictors of favourable response to bortezomib, including a subset of endoplasmic reticulum stress pathways. The data also implicate pathways unique to each regimen that may predict sensitivity to DNA-damaging agents, such as mitochondrial dysfunction, and immunomodulatory drugs, which was associated with acute phase response signalling. Overall, we identified patterns of tumour characteristics that may predict response to bortezomib-based regimens and their components. These results provide a rationale for further evaluation of the protein profiles identified herein for targeted selection of anti-myeloma therapy to increase the likelihood of improved treatment outcome of patients with newly-diagnosed myeloma.

Second malignancies in patients with neuroblastoma: the effects of risk-based therapy.

BACKGROUND: To investigate the incidence of second malignant neoplasms (SMN) for patients with neuroblastoma, we analyzed patients from the SEER database according to three treatment eras (Era 1: 1973-1989, Era 2: 1990-1996, and Era 3: 1997-2006) corresponding to the introduction of multi-agent chemotherapy, risk-based treatment, and stem cell transplant. PROCEDURES: The SEER database was mined for all patients with neuroblastoma or ganglioneuroblastoma. Cumulative incidence of SMN was calculated with death as a competing risk. A poisson regression model was used to estimate incidence rate ratios and 95% confidence intervals to compare the rates of SMN between patients in different Eras. RESULTS: The analytic cohort included 2,801 patients. Thirty-four patients developed a SMN, accounting for 1.2% of all patients. Of the patients who developed a SMN, 47.1% received radiation for their primary neuroblastoma. Fourteen of the SMN were carcinomas, and 10 were hematologic malignancies, with six cases of acute myelogenous leukemia. There was no difference in the incidence of SMN in Era 1 compared to Era 3 (P = 0.48). The cumulative incidence of SMN at 30 years for high-risk patients was 10.44% (95% CI 3.98-20.52%) compared to 3.57% (95% CI 1.87-6.12%) for non-high-risk patients (P < 0.001). CONCLUSIONS: This study showed no increase in the incidence of SMNs for children treated in the most recent treatment era as compared to earlier Eras. However, as the risk for developing SMN does not plateau, the number of SMNs will likely continue to rise in the cohort of patients treated after 1996. Comprehensive follow-up care for these survivors will be important.

Targeted Enrollment in Pediatric Oncology Trials: A Vision for Just-in-Time Matching.

@PedsDataCommons shares vision for automated clinical trials matching in pediatric oncology.

An open-source platform for pediatric cancer data exploration: a report from Data for the Common Good.

Objective: The Pediatric Cancer Data Commons (PCDC)-a project of Data for the Common Good-houses clinical pediatric oncology data and utilizes the open-source Gen3 platform. To meet the needs of end users, the PCDC development team expanded the out-of-box functionality and developed additional custom features that should be useful to any group developing similar data commons. Materials and Methods: Modifications of the PCDC data portal software were implemented to facilitate desired functionality. Results: Newly developed functionality includes updates to authorization methods, expansion of filtering capabilities, and addition of data analysis functions. Discussion: We describe the process by which custom functionalities were developed. Features are open source and available to be implemented and adapted to suit needs of data portals that utilize the Gen3 platform. Conclusion: Data portals are indispensable tools for facilitating data sharing. Open-source infrastructure facilitates a modular and collaborative approach for meeting needs of end users and stakeholders.

Extracting Electronic Health Record Neuroblastoma Treatment Data With High Fidelity Using the REDCap Clinical Data Interoperability Services Module.

PURPOSE: Although the International Neuroblastoma Risk Group Data Commons (INRGdc) has enabled seminal large cohort studies, the research is limited by the lack of real-world, electronic health record (EHR) treatment data. To address this limitation, we evaluated the feasibility of extracting treatment data directly from EHRs using the REDCap Clinical Data Interoperability Services (CDIS) module for future submission to the INRGdc. METHODS: Patients enrolled on the Children's Oncology Group neuroblastoma biology study ANBL00B1 (ClinicalTrials.gov identifier: NCT00904241) who received care at the University of Chicago (UChicago) or the Vanderbilt University Medical Center (VUMC) after the go-live dates for the Fast Healthcare Interoperability Resources (FHIR)-compliant EHRs were identified. Antineoplastic drug orders were extracted using the CDIS module. To validate the CDIS output, antineoplastic agents extracted through FHIR were compared with those queried through EHR relational databases (UChicago's Clinical Research Data Warehouse and VUMC's Epic Clarity database) and manual chart review. RESULTS: The analytic cohort consisted of 41 patients at UChicago and 32 VUMC patients. Antineoplastic drug orders were identified in the extracted EHR records of 39 (95.1%) UChicago patients and 26 (81.3%) VUMC patients. Manual chart review confirmed that patients with missing (n = 8) or discontinued (n = 1) orders in the CDIS output did not receive antineoplastic agents during the timeframe of the study. More than 99% of the antineoplastic drug orders in the EHR relational databases were identified in the corresponding CDIS output. CONCLUSION: Our results demonstrate the feasibility of extracting EHR treatment data with high fidelity using HL7-FHIR via REDCap CDIS for future submission to the INRGdc.

Accelerating pediatric Hodgkin lymphoma research: the Hodgkin Lymphoma Data Collaboration (NODAL).

Data commons have proven to be an indispensable avenue for advancing pediatric cancer research by serving as unified information technology platforms that, when coupled with data standards, facilitate data sharing. The Pediatric Cancer Data Commons, the flagship project of Data for the Common Good (D4CG), collaborates with disease-based consortia to facilitate development of clinical data standards, harmonization and pooling of clinical data from disparate sources, establishment of governance structure, and sharing of clinical data. In the interest of international collaboration, researchers developed the Hodgkin Lymphoma Data Collaboration and forged a relationship with the Pediatric Cancer Data Commons to establish a data commons for pediatric Hodgkin lymphoma. Herein, we describe the progress made in the formation of Hodgkin Lymphoma Data Collaboration and foundational goals to advance pediatric Hodgkin lymphoma research.

Using A Standardized Nomenclature to Semantically Map Oncology-Related Concepts from Common Data Models to a Pediatric Cancer Data Model.

The Pediatric Cancer Data Commons (PCDC) comprises an international community whose ironclad commitment to data sharing is combatting pediatric cancer in an unprecedented way. The byproduct of their data sharing efforts is a gold-standard consensus data model covering many types of pediatric cancer. This article describes an effort to utilize SSSOM, an emerging specification for semantically-rich data mappings, to provide a "hub and spoke" model of mappings from several common data models (CDMs) to the PCDC data model. This provides important contributions to the research community, including: 1) a clear view of the current coverage of these CDMs in the domain of pediatric oncology, and 2) a demonstration of creating standardized mappings. These mappings can allow downstream crosswalk for data transformation and enhance data sharing. This can guide those who currently create and maintain brittle ad hoc data mappings in order to utilize the growing volume of viable research data.

Automated Matching of Patients to Clinical Trials: A Patient-Centric Natural Language Processing Approach for Pediatric Leukemia.

PURPOSE: Matching patients to clinical trials is cumbersome and costly. Attempts have been made to automate the matching process; however, most have used a trial-centric approach, which focuses on a single trial. In this study, we developed a patient-centric matching tool that matches patient-specific demographic and clinical information with free-text clinical trial inclusion and exclusion criteria extracted using natural language processing to return a list of relevant clinical trials ordered by the patient's likelihood of eligibility. MATERIALS AND METHODS: Records from pediatric leukemia clinical trials were downloaded from ClinicalTrials.gov. Regular expressions were used to discretize and extract individual trial criteria. A multilabel support vector machine (SVM) was trained to classify sentence embeddings of criteria into relevant clinical categories. Labeled criteria were parsed using regular expressions to extract numbers, comparators, and relationships. In the validation phase, a patient-trial match score was generated for each trial and returned in the form of a ranked list for each patient. RESULTS: In total, 5,251 discretized criteria were extracted from 216 protocols. The most frequent criterion was previous chemotherapy/biologics (17%). The multilabel SVM demonstrated a pooled accuracy of 75%. The text processing pipeline was able to automatically extract 68% of eligibility criteria rules, as compared with 80% in a manual version of the tool. Automated matching was accomplished in approximately 4 seconds, as compared with several hours using manual derivation. CONCLUSION: To our knowledge, this project represents the first open-source attempt to generate a patient-centric clinical trial matching tool. The tool demonstrated acceptable performance when compared with a manual version, and it has potential to save time and money when matching patients to trials.

Persistence of Racial and Ethnic Disparities in Risk and Survival for Patients with Neuroblastoma over Two Decades.

BACKGROUND: Racial/ethnic survival disparities in neuroblastoma were first reported more than a decade ago. We sought to investigate if these disparities have persisted with current era therapy. METHODS: Two patient cohorts were identified in the International Neuroblastoma Risk Group Data Commons (INRGdc) (Cohort 1: diagnosed 2001-2009, n=4359; Cohort 2: diagnosed 2010-2019, n=4891). Chi-squared tests were used to assess the relationship between race/ethnicity and clinical and biologic features. Survival was estimated by the Kaplan-Meier method. Cox proportional hazards regression analyses were performed to investigate the association between racial/ethnic groups and prognostic markers. RESULTS: Significantly higher 5-year event-free survival (EFS) and overall survival (OS) were observed for Cohort 2 compared to Cohort 1 (P<0.001 and P<0.001, respectively). Compared to White patients, Black patients in both cohorts had a higher proportion of high-risk disease (Cohort 1: P<0.001; Cohort 2: P<0.001) and worse EFS (Cohort 1: P<0.001; Cohort 2 P<0.001) and OS (Cohort 1: P<0.001; Cohort 2: P<0.001). In Cohort 1, Native Americans also had a higher proportion of high-risk disease (P=0.03) and inferior EFS/OS. No significant survival disparities were observed for low- or intermediate-risk patients in either cohort or high-risk patients in Cohort 1. Hispanic patients with high-risk disease in Cohort 2 had significantly inferior OS (P=0.047). Significantly worse OS, but not EFS, (P=0.006 and P=0.02, respectively) was also observed among Black and Hispanic patients assigned to receive post-Consolidation dinutuximab on clinical trials (n=885). CONCLUSION: Racial/ethnic survival disparities have persisted over time and were observed among high-risk patients assigned to receive post-Consolidation dinutuximab.