Genome-Wide Identification and Expression Analysis of Nitrate Transporter (NRT) Gene Family in Eucalyptus grandis.

Eucalyptus grandis is an important planted hardwood tree worldwide with fast growth and good wood performance. The nitrate transporter (NRT) gene family is a major core involved in nitrogen (N) absorption and utilization in plants, but the comprehensive characterization of NRT genes in E. grandis remains mostly elusive. In this study, a total of 75 EgNRT genes were identified from the genome of E. grandis that were distributed unevenly across ten chromosomes, except Chr9. A phylogenetic analysis showed that the EgNRT proteins could be divided into three classes, namely NRT1, NRT2 and NRT3, which contained 69, 4 and 2 members, respectively. The cis-regulatory elements in the promoter regions of EgNRT genes were mainly involved in phytohormone and stress response. The transcriptome analysis indicated that the differentially expressed genes of leaf and root in E. grandis under different N supply conditions were mainly involved in the metabolic process and plant hormone signal transduction. In addition, the transcriptome-based and RT-qPCR analysis revealed that the expression of 13 EgNRT genes, especially EgNRT1.3, EgNRT1.38, EgNRT1.39 and EgNRT1.52, was significantly upregulated in the root under low-N-supply treatment, suggesting that those genes might play a critical role in root response to nitrate deficiency. Taken together, these results would provide valuable information for characterizing the roles of EgNRTs and facilitate the clarification of the molecular mechanism underlying EgNRT-mediated N absorption and distribution in E. grandis.

Recycling channel strategy in the presence of free-riding in the carbon neutrality era.

Recycling has become a critical response to the goals of reaching a carbon peak and achieving carbon neutrality. This study explores the effects of consumer free-riding behavior, the quality of recycling services, and the costs of channel transfers on the profitability of manufacturers and retailers in a dual-channel closed-loop supply chain (CLSC), focusing on the importance of recycling practices for carbon neutrality. Using consumer utility theory and a Stackelberg game model, we analyze the dynamics among these factors. Our results show that: (i) Consumer free-riding behavior slightly increases market demand and recycling volumes, enhancing profitability for both manufacturers and retailers in the dual-channel CLSC. (ii) The quality of recycling services and the transfer costs associated with retailer free-riding behavior jointly influence the profits of manufacturers and retailers. (iii) The effect of free-riding behavior on recycling services affects both forward sales and reverse recycling channels equally. This study provides valuable insights for decision-making in sustainable development practices in the recycling sector, significantly contributing to the goal of achieving carbon neutrality.

Parent Quality of Life After Disclosure of Pediatric Oncology Germline Sequencing Results.

PURPOSE: To characterize parents' quality of life (QoL) after germline genomic sequencing for their children with cancer. METHODS: Participants were n = 104 parents of children with cancer enrolled in a prospective study of clinical tumor and germline genomic sequencing. Parents completed surveys at study consent (T0), before disclosure of their child's germline results (T1), and again ≥5 weeks after results disclosure (T2). Bivariate associations with QoL were examined, followed by a multivariable regression model predicting parents' psychological distress. RESULTS: At T2, parental distress significantly differed by their children's germline result type (positive, uncertain, negative; P = .038), parent relationship status (P = .04), predisclosure genetics knowledge (P = .006), and predisclosure worry about sequencing (P < .001). Specifically, parents of children with positive (ie, pathogenic or likely pathogenic) results experienced greater distress than those of children with negative results (P = .029), as did parents who were single, more knowledgeable about genetics, and with greater worry. In the adjusted regression model, a positive germline result remained significantly associated with parents' lower QoL at T2 follow-up (F [4,92] = 9.95; P < .001; R2 = .30; ß = .19; P = .031). CONCLUSION: Germline genomic sequencing for children with cancer is associated with distress among parents when revealing an underlying cancer predisposition among their affected children. Genetic education and counseling before and after germline sequencing may help attenuate this impact on QoL by addressing parents' concerns about test results and their health implications. Assessing parents' worry early in the testing process may also aid in identifying those most likely in need of psychosocial support.

Estimation of nonlinear mixed-effects continuous-time models using the continuous-discrete extended Kalman filter.

Many intensive longitudinal measurements are collected at irregularly spaced time intervals, and involve complex, possibly nonlinear and heterogeneous patterns of change. Effective modelling of such change processes requires continuous-time differential equation models that may be nonlinear and include mixed effects in the parameters. One approach of fitting such models is to define random effect variables as additional latent variables in a stochastic differential equation (SDE) model of choice, and use estimation algorithms designed for fitting SDE models, such as the continuous-discrete extended Kalman filter (CDEKF) approach implemented in the dynr R package, to estimate the random effect variables as latent variables. However, this approach's efficacy and identification constraints in handling mixed-effects SDE models have not been investigated. In the current study, we analytically inspect the identification constraints of using the CDEKF approach to fit nonlinear mixed-effects SDE models; extend a published model of emotions to a nonlinear mixed-effects SDE model as an example, and fit it to a set of irregularly spaced ecological momentary assessment data; and evaluate the feasibility of the proposed approach to fit the model through a Monte Carlo simulation study. Results show that the proposed approach produces reasonable parameter and standard error estimates when some identification constraint is met. We address the effects of sample size, process noise variance, and data spacing conditions on estimation results.

Integration of Palliative Care in Hematopoietic Cell Transplant: Pediatric Patient and Parent Needs and Attitudes.

CONTEXT: Early integration of palliative care (PC) in hematopoietic cell transplantation (HCT) has demonstrated benefits, yet barriers remain, including perceived lack of patient/caregiver receptivity despite no data on attitudes toward PC and limited patient/caregiver reported outcomes in pediatric HCT. OBJECTIVES: This study aimed to evaluate perceived symptom burden and patient/parent attitudes toward early PC integration in pediatric HCT. METHODS: Following IRB approval, consent/assent, eligible participants were surveyed at St. Jude Children's Research Hospital including English-speaking patients aged 10-17, 1-month to 1-year from HCT, and their parents/primary-caregivers, as well as parent/primary-caregivers of living HCT recipients

A retrospective investigation of the relationship between neuroblastoma response to anti-GD2 monoclonal antibodies and exposure to opioids for pain management.

OBJECTIVE: Recent increased awareness and research studies reflect possible associations between opioid exposure and cancer outcomes. Children with neuroblastoma (NB) often require opioid treatment for pain. However, associations between tumor response to chemotherapy and opioid exposure have not been investigated in clinical settings. METHODS: This is a single-institution retrospective review of patients with NB treated between 2013 and 2016. We evaluated opioid consumption quantified in morphine equivalent doses (mg/kg) based on nurse- or patient-controlled analgesia during antibody infusions. We also analyzed their associations with change in primary tumor volume and total tumor burden. RESULTS: Of 42 patients given opioids for pain related to anti-disialoganglioside monoclonal antibodies (anti-GD2 mAb), data completion was achieved for 36, and details of statistical analyses were entered. Median total weight-based morphine equivalent (over 8 days) was 4.71 mg/kg (interquartile range 3.49-7.96). We found a statistically insignificant weak negative relationship between total weight-based morphine equivalents and tumor volume ratio (correlation coefficient -.0103, p-value .9525) and a statistically insignificant weak positive relationship between total weight-based morphine equivalent and Curie score ratio (correlation coefficient .1096, p-value .5247). CONCLUSION: Our study found no statistically significant correlation between opioid consumption and natural killer (NK) cell-mediated killing of NB cells as measured by effects on tumor volume/tumor load.

Expanding APHON's Pediatric Chemotherapy/Biotherapy Provider and Instructor Program to Spanish-Speaking Countries: Pilot Series Development and Evaluation.

Background: To address the need for standardized, comprehensive chemotherapy/biotherapy education in Latin American and Caribbean (LAC) countries, the Association of Pediatric Hematology/Oncology Nurses (APHON) Pediatric Chemotherapy/Biotherapy Provider and Instructor program courses were culturally adapted, translated to Spanish, and piloted. The process of course adaptation and implementation are described. A Context, Input, Process, Product model outcomes evaluation determined: (a) differences in pass rates by test version and pilot location, (b) predictors of pass rates, (c) course appropriateness for nurses' education and practice levels, and (d) strategies for course improvements. Methods: The Spanish APHON Pediatric Chemotherapy/Biotherapy Provider program was piloted four times and the Instructor program twice with nurses from Mexico, Central America, the Caribbean, South America, and Spain. Statistical analysis identified factors associated with pass rates. Results: Of the 203 students in four Spanish APHON Provider program courses, data from 108 students (three pilots) were analyzed (one unplanned pilot excluded for missing data). Significant predictors of pass rates included: pediatric oncology frontline nurses (OR = 9.86; 95% CI [2.56, 65.23]; p = .004), nurses dedicated to an inpatient or outpatient unit (non-rotating) (OR = 6.79 [1.29, 51.98]; p = .033), and graduation from a 5-year nursing program (OR = 5.92; 95% CI [1.30, 33.15]; p = .028). Discussion: The Spanish APHON Pediatric Chemotherapy/Biotherapy program was determined appropriate for nurses' education and practice levels in LAC countries. Through the APHON Spanish language instructor network, pediatric oncology nurses in LAC countries have increased access to standardized, comprehensive chemotherapy/biotherapy education.

Chronic postsurgical pain in children and young adults with cancer and choice of regional anesthesia for amputation and limb-sparing surgery.

BACKGROUND: Patients undergoing limb amputation (LA) or limb-sparing (LS) for lower extremity oncologic diagnoses are at similar risk for chronic postsurgical pain of neuropathic nature (CPSP/NP). Regional anesthesia (RA) techniques are pre-emptive measures to prevent the occurrence of the CPS/NP. However, recommendations for epidural (EP) versus peripheral nerve blocks (PNBs) lack in pediatric literature. AIMS: This study investigates the incidence and duration of CPSP/NP and describes NP-directed regimens. METHODS AND RESULTS: Data on demographics, use of EP or PNB, duration of CPSP/NP, and NP-directed medication were retrospectively collected for LA and LS between 2009 and 2019. Mixed effects logistic regression was used to compare the odds of CPSP/NP between EP and PNB. Cox PH model with adjustment for clustering due to multiple surgeries on patients was used to quantify rate of pain relief between surgery groups (LA vs. LS) and RA groups (EP vs. PNB). The incidence of CPSP/NP was 36 (23.8%) after 165 surgeries (150 patients). The odds of CPSP/NP after PNB were 2.5 times those of CPSP/NP after EP (p = .11). The rate of pain relief at any instant after the EP was 1.2 times that after PNB (p = .3). The rate of pain relief for LS with EP was 1.9 times that of pain relief for LA with EP, a statistically significant difference (p = .03). Gabapentin was used (94.5%), with addition of amitriptyline (24.2%) and both amitriptyline and methadone (12.7%). CONCLUSION: The LS with the EP group had a significantly higher rate of relief of CPSP/NP than LA with EP. Odds of CPSP/NP after PNB were 2.5 times those of CPSP after EP.

Decreasing Burnout and Improving Work Environment: The Impact of Firgun on a Pediatric Hematopoietic Cell Transplant Team.

PURPOSE: Oncology teams are challenged by BO, which may be alleviated by meaningful recognition. In this study, firgun-altruistic acknowledgment-was implemented on a pediatric hematopoietic cell transplant unit to evaluate its impact on staff and work environment. METHODS: In this longitudinal, mixed-methods pilot study, interdisciplinary inpatient hematopoietic cell transplant providers received web-based firgun education. Electronic administration of validated surveys occurred at baseline and 8 weeks, including Perceived Stress Scale, Professional Quality of Life Scale, Maslach Burnout Inventory, Workplace Civility Index, Areas of Work Life Survey, and WHO-5. Weekly e-mails reminded participants to practice and log firgun. Wilcoxon signed test for paired data compared pre/post results. Interviews conducted at project completion were coded using MaxQDA software. RESULTS: Forty-two participants enrolled; 25 completed pre/post surveys; eight were interviewed. At study end, participants reported feeling less nervous and stressed (P = .008), and less difficulty coping (P = .01; Perceived Stress Scale), while noting increased acknowledgment of others' work (P = .04) and seeking constructive feedback (P = .04; Workplace Civility Index). Marked BO was not evident overall on the Maslach Burnout Inventory; however, emotional exhaustion subscale mean (SD) scores improved from pre (19.4 [8.6]) to post (16 [6.3; P = .02]) and individual items illustrated decreased fatigue (P = .008), frustration (P = .04), and feeling "at the end of my rope" (P = .001). Postintervention participants noted increased receipt of recognition (P = .02; Areas of Work Life Survey), decreased feeling "bogged down" (P = .02), decreased affective stress (P = .04), and negative pre-occupations (P = .04; Professional Quality of Life Scale). Qualitative analysis revealed themes of improved confidence at work and enhanced feelings of trust and teamwork. CONCLUSION: Firgun is a tool that can potentially reduce BO and stress in interdisciplinary providers, facilitate teamwork, and promote positive work environments in clinical oncology and beyond.

A high-dimensional mediation model for a neuroimaging mediator: Integrating clinical, neuroimaging, and neurocognitive data to mitigate late effects in pediatric cancer.

Pediatric cancer treatment, especially for brain tumors, can have profound and complicated late effects. With the survival rates increasing because of improved detection and treatment, a more comprehensive understanding of the impact of current treatments on neurocognitive function and brain structure is critically needed. A frontline medulloblastoma clinical trial (SJMB03) has collected data, including treatment, clinical, neuroimaging, and cognitive variables. Advanced methods for modeling and integrating these data are critically needed to understand the mediation pathway from the treatment through brain structure to neurocognitive outcomes. We propose an integrative Bayesian mediation analysis approach to model jointly a treatment exposure, a high-dimensional structural neuroimaging mediator, and a neurocognitive outcome and to uncover the mediation pathway. The high-dimensional imaging-related coefficients are modeled via a binary Ising-Gaussian Markov random field prior (BI-GMRF), addressing the sparsity, spatial dependency, and smoothness and increasing the power to detect brain regions with mediation effects. Numerical simulations demonstrate the estimation accuracy, power, and robustness. For the SJMB03 study, the BI-GMRF method has identified white matter microstructure that is damaged by cancer-directed treatment and impacts late neurocognitive outcomes. The results provide guidance on improving treatment planning to minimize long-term cognitive sequela for pediatric brain tumor patients.

A CT scan-based formula for predicting central venous catheter length in pediatric patients.

PURPOSE: Placement of a central venous catheter (CVC) is the most commonly performed pediatric procedure. This study aims to develop simple formulas to calculate intravascular length of CVCs prior to insertion to minimize reliance on fluoroscopic and radiographic imaging, which may not be uniformly available. METHODS: We performed a single-institution, retrospective review of 115 pediatric patients who received both CVC placement and computed tomography (CT) imaging of the chest within 3 months of the procedure. Using measurements from the CT imaging, formulas calculating the length of the intravascular component of the CVC based on height and insertion laterality were developed and compared to previously published formulas. These formulas were then trialed prospectively to validate reliability and application. RESULTS: Formulas were developed for right-sided and left subclavian insertion. The right-side formula accurately predicted CVC length in 52.6% of patients, compared to 47.4% by the Andropoulos formula. The left subclavian formula accurately estimated 62.5%, compared to 34.5% by the Stroud formula. CONCLUSIONS: The optimal intravascular length of central venous catheters may be determined by simple formulas based on patient height and insertion site. LEVEL OF EVIDENCE: III.

Impact of urban innovation on urban green development in China's Yangtze River Economic Belt: perspectives of scale and network.

Understanding whether and how urban innovation offers a sound solution to the dilemma of urban green development is a crucial response to mitigate the detrimental effect on natural resources and environment for transitioning to sustainable urban development. To address the critical issue, we propose urban green development evaluation index system, and then examine how the urban innovation affects urban green development from the perspectives of government-scale, enterprise-scale, and spatial correlation network, all of which are originally applied in the 108 cities of Yangtze River Economic Belt of China (YREB) during period 2006-2018. The evaluation results show that urban innovation promotes urban green development, and both government-scale and enterprise-scale contribute to the effects. The constructed spatial correlation network of urban innovation illustrates the network structural form and reveals the network property, and further results tell that increasing network density and centrality would promote green development obviously. More specifically, the network density of urban innovation has been tied to the enhancement of urban green development, which is more significant in middle reaches than in lower and upper reaches of YREB. Similarly, optimizing the network's degree centrality and closeness centrality can help facilitate urban green development in whole YREB. Thus, the research findings would provide new insights into the essence and driving forces from various scale and hidden network when exploring and seeking urban green development path.

Quality improvement knowledge in pediatric hematology/oncology physicians: A need for improved education.

Pediatric hematology/oncology fellows face unique quality improvement challenges given the danger of chemotherapy and caring for immunocompromised patients. Curricula to teach pediatric hematology/oncology fellows about quality improvement are lacking. We conducted a needs assessment of pediatric hematology/oncology physicians as a first step for creating a quality improvement curriculum for pediatric hematology/oncology fellows. Curricular topics were identified: root cause analysis, run charts, process mapping, chemotherapy/medication safety, implementation/adherence to guidelines. Identified barriers to curriculum implementation included a possible lack of quality improvement expertise, lack of awareness of quality improvement resources, and limited time.

Managing Pandora's Box: Familial Expectations around the Return of (Future) Germline Results.

BACKGROUND: Pediatric oncology patients are increasingly being offered germline testing to diagnose underlying cancer predispositions. Meanwhile, as understanding of variant pathogenicity evolves, planned reanalysis of genomic results has been suggested. Little is known regarding the types of genomic information that parents and their adolescent children with cancer prefer to receive at the time of testing or their expectations around the future return of genomic results. METHODS: Parents and adolescent children with cancer eligible for genomic testing for cancer predisposition were surveyed regarding their attitudes and expectations for receiving current and future germline results (ClinicalTrials.gov Identifier: NCT02530658). RESULTS: All parents (100%) desired to learn about results for treatable or preventable conditions, with 92.4% wanting results even when there is no treatment or prevention. Parents expressed less interest in receiving uncertain results for themselves (88.3%) than for their children (95.3%). Most parents (95.9%) and adolescents (87.9%) believed that providers have a responsibility to share new or updated germline results indefinitely or at any point during follow-up care. Fewer parents (67.5%) indicated that they would want results if their child was deceased: 10.3% would not want to be contacted, 19.3% were uncertain. CONCLUSIONS: Expectations for return of new or updated genomic results are high among pediatric oncology families, although up to one third of parents have reservations about receiving such information in the event of their child's death. These results underscore the importance of high-quality pre-and post-test counseling, conducted by individuals trained in consenting around genomic testing to elicit family preferences and align expectations around the return of germline results.

Alzheimer's Disease Classification Through Imaging Genetic Data With IGnet.

The application of deep learning techniques to the detection and automated classification of Alzheimer's disease (AD) has recently gained considerable attention. The rapid progress in neuroimaging and sequencing techniques has enabled the generation of large-scale imaging genetic data for AD research. In this study, we developed a deep learning approach, IGnet, for automated AD classification using both magnetic resonance imaging (MRI) data and genetic sequencing data. The proposed approach integrates computer vision (CV) and natural language processing (NLP) techniques, with a deep three-dimensional convolutional network (3D CNN) being used to handle the three-dimensional MRI input and a Transformer encoder being used to manage the genetic sequence input. The proposed approach has been applied to the Alzheimer's Disease Neuroimaging Initiative (ADNI) data set. Using baseline MRI scans and selected single-nucleotide polymorphisms on chromosome 19, it achieved a classification accuracy of 83.78% and an area under the receiver operating characteristic curve (AUC-ROC) of 0.924 with the test set. The results demonstrate the great potential of using multi-disciplinary AI approaches to integrate imaging genetic data for the automated classification of AD.

Indocyanine green-guided nephron-sparing surgery for pediatric renal tumors.

BACKGROUND: Indocyanine green (ICG), a water-soluble tricarbocyanine fluorophore, is being increasingly used for tumor localization based on its passive intra-tumoral accumulation due to enhanced permeability and retention in tumor tissue. Therefore, we hypothesized that ICG can provide contrast to facilitate accurate, real-time recognition of renal tumors at the time of nephron-sparing surgery in children. METHODS: This retrospective study examined the feasibility of ICG in guiding nephron-sparing surgery for pediatric renal tumors. RESULTS: We reviewed the medical records of 8 pediatric patients with renal tumors in 12 kidneys. Intraoperative localization of tumor with near infrared guidance was successful in all 12 kidneys. However, we consistently found an inverse pattern of near infrared signal in which the normal kidney demonstrated increased fluorescent signal relative to the kidney tumor. CONCLUSIONS: Fluorescence-guided renal tumor delineation is unique because it has an inverse pattern of near infrared signal in which the normal kidney demonstrates increased signal relative to the adjacent tumor. Nevertheless fluorescence-guided distinguishing of renal tumor from surrounding normal kidney is feasible.

Why do subcutaneous ports get stuck? A case-control study.

PURPOSE: We sought to identify clinical features associated with difficult subcutaneous port removals in children. METHODS: Ports placed between April 2014 and September 2017 at our institution were prospectively tracked for difficult removals. A case-control analysis was performed. Patients with ports that were difficult to remove (stuck; cases) were compared to biological sex and age-matched controls in a ratio of 1:3. Logistic regression determined the association between case/control status and clinical features adjusting for biological sex and age as covariates. A multivariable analysis was performed to identify independent associations. RESULTS: 57 stuck ports (28 extreme [10 endovascular intervention] and 29 moderate) and 171 controls were analyzed. Stuck ports were associated with a diagnosis of acute lymphoblastic leukemia (86% cases versus 22.2% controls; p < 0.001) and a longer placement duration (median 2.6 years [interquartile range (IQR) 2.5-2.6] versus 0.8 years [IQR 0.5-1.4]; p < 0.001). On univariate analysis, procedural and device features associated with stuck ports included subclavian access (71.9% cases versus 48.5% controls; p = 0.0126), a polyurethane versus silicone catheter (96.5% cases versus 79.9% controls; p = 0.001), and a rough catheter appearance at removal (92.6% cases versus 9.4% controls; p < 0.0001). A diagnosis of ALL and duration of line placement were associated with having a stuck port on multivariate analysis. CONCLUSION: Polyurethane central venous catheters placed for the two-year treatment of acute lymphoblastic leukemia may become difficult to remove. This constellation of factors warrants more extensive preoperative discussion of risk, endovascular backup availability, and scheduling for longer operating room time.

Bivalirudin Presents a Favorable Safety Profile Regarding Adverse Drug Reactions, Thrombocytopenia, and Bleeding in Chinese Patients With High Bleeding Risk Undergoing Percutaneous Coronary Intervention: A Prospective, Multi-Center, Intensive Monitoring Study.

Background: This study aimed to comprehensively explore the occurrence and risk factors for adverse events (AEs) and adverse drug reactions (ADRs) (especially for thrombocytopenia and bleeding) in Chinese patients with high bleeding risk (older adults, or complicated with diabetes mellitus or renal function impairment) undergoing percutaneous coronary intervention (PCI) with bivalirudin as an anticoagulant. Methods: A total of 1,226 patients with high bleeding risk who received PCI with bivalirudin as an anticoagulant from 27 Chinese medical centers were enrolled in this prospective, multi-center, intensive monitoring study. AEs, ADRs, thrombocytopenia, and bleeding were collected from admission to 72 h post-bivalirudin administration; subsequently, patients were followed up on the 30th day with the safety data collected as well. Results: Adverse events were observed in 198 (16.2) patients, among which severe AEs occurred in 16 (1.3%) patients. Meanwhile, bivalirudin-related ADRs were reported in 66 (5.4%) patients, among which 5 (0.4%) patients experienced bivalirudin-related severe ADRs. Besides, thrombocytopenia and bleeding occurred in 45 (3.7%) and 19 (1.5%) patients, respectively. The subsequent multivariate logistic analysis revealed that age >75 years [p = 0.017, odds ratio (OR) = 1.856] and spontaneous coronary artery dissection (SCAD) (p = 0.030, OR = 2.022) were independently related to higher ADR risk; SCAD (p = 0.017, OR = 2.426) was independently correlated with higher thrombocytopenia risk, while radial artery access (p = 0.015, OR = 0.352) was independently correlated with lower thrombocytopenia risk; and the administration of bivalirudin preoperatively or intraoperatively (p = 0.013, OR = 5.097) was independently associated with higher bleeding risk. Conclusion: Bivalirudin presents a favorable safety profile regarding ADRs, thrombocytopenia, and bleeding in Chinese patients with high bleeding risk undergoing PCI.

Natural Language Processing and Machine Learning Methods to Characterize Unstructured Patient-Reported Outcomes: Validation Study.

BACKGROUND: Assessing patient-reported outcomes (PROs) through interviews or conversations during clinical encounters provides insightful information about survivorship. OBJECTIVE: This study aims to test the validity of natural language processing (NLP) and machine learning (ML) algorithms in identifying different attributes of pain interference and fatigue symptoms experienced by child and adolescent survivors of cancer versus the judgment by PRO content experts as the gold standard to validate NLP/ML algorithms. METHODS: This cross-sectional study focused on child and adolescent survivors of cancer, aged 8 to 17 years, and caregivers, from whom 391 meaning units in the pain interference domain and 423 in the fatigue domain were generated for analyses. Data were collected from the After Completion of Therapy Clinic at St. Jude Children's Research Hospital. Experienced pain interference and fatigue symptoms were reported through in-depth interviews. After verbatim transcription, analyzable sentences (ie, meaning units) were semantically labeled by 2 content experts for each attribute (physical, cognitive, social, or unclassified). Two NLP/ML methods were used to extract and validate the semantic features: bidirectional encoder representations from transformers (BERT) and Word2vec plus one of the ML methods, the support vector machine or extreme gradient boosting. Receiver operating characteristic and precision-recall curves were used to evaluate the accuracy and validity of the NLP/ML methods. RESULTS: Compared with Word2vec/support vector machine and Word2vec/extreme gradient boosting, BERT demonstrated higher accuracy in both symptom domains, with 0.931 (95% CI 0.905-0.957) and 0.916 (95% CI 0.887-0.941) for problems with cognitive and social attributes on pain interference, respectively, and 0.929 (95% CI 0.903-0.953) and 0.917 (95% CI 0.891-0.943) for problems with cognitive and social attributes on fatigue, respectively. In addition, BERT yielded superior areas under the receiver operating characteristic curve for cognitive attributes on pain interference and fatigue domains (0.923, 95% CI 0.879-0.997; 0.948, 95% CI 0.922-0.979) and superior areas under the precision-recall curve for cognitive attributes on pain interference and fatigue domains (0.818, 95% CI 0.735-0.917; 0.855, 95% CI 0.791-0.930). CONCLUSIONS: The BERT method performed better than the other methods. As an alternative to using standard PRO surveys, collecting unstructured PROs via interviews or conversations during clinical encounters and applying NLP/ML methods can facilitate PRO assessment in child and adolescent cancer survivors.