Diagnosis Of Solid Tumors Research Articles

Differential Diagnosis of Hematologic and Solid Tumors Using Targeted Transcriptome and Artificial Intelligence

Diagnosis and classification of tumors is increasingly dependent on biomarkers. RNA expression profiling using next-generation sequencing provides reliable and reproducible information on the biology of cancer. This study investigated targeted transcriptome and artificial intelligence for differential diagnosis of hematologic and solid tumors. RNA samples from hematologic neoplasms (N=2606), solid tumors (N=2038), normal bone marrow (N=782), and lymph node control (N=24) were sequenced using next-generation sequencing using a targeted 1408-gene panel. There were 20 subtypes of hematologic neoplasms and 24 subtypes of solid tumors. Machine learning was used for diagnosis between two classes. Geometric mean naïve bayesian classifier was used for differential diagnosis across 45 diagnostic entities with assigned rankings. Machine learning showed high accuracy in distinguishing between two diagnoses, with area under the curve varying between 1 and 0.841. Geometric mean naïve bayesian algorithm was trained using 3045 samples and tested on 1415 samples, and showed correct first-choice diagnosis in 100%, 88%, 85%, 82%, 88%, 72%, and 72% of acute lymphoblastic leukemia, acute myeloid leukemia, diffuse large B-cell lymphoma, colorectal cancer, lung cancer, chronic lymphocytic leukemia, and follicular lymphoma cases, respectively. We conclude that targeted transcriptome combined with artificial intelligence are highly useful for diagnosis and classification of various cancers. Mutation profiles and clinical information can improve these algorithms and minimize errors in diagnoses.

Impact of the Cancer and Aging Research Group (CARG) chemotherapy toxicity (tox) risk score on the benefit of a geriatric assessment–driven intervention (GAIN) among older adults with cancer.

235 Background: The CARG tox score can predict risk of chemotherapy-related tox in older adults with cancer. GAIN can reduce tox vs standard of care (SOC) among these patients (pts); GAIN’s impact across CARG risk groups is unknown. Methods: A secondary analysis of the GAIN randomized clinical trial (NCT02517034) of pts aged ≥65 (solid tumor diagnosis, starting a new chemotherapy) was performed. Pts were randomized 2:1 to receive GAIN vs SOC and were categorized into low (0-5), medium (6-9), and high (10-20) risk groups according to CARG score. The primary outcome was incidence of grade 3-5 tox. Chi-square/Fisher’s exact tests were used to compare outcomes (GAIN vs SOC, stratified by risk groups). Log-rank tests were used to compare 1-year survival across risk groups. Results: This analysis included 600 pts: 26.5% low risk, 45.2% medium risk, 28.3% high risk. Table shows pt/treatment characteristics. For pts with low/medium risk scores, GAIN demonstrated a 14.0% (95% CI 4.1%-23.9%) reduction in tox vs SOC (p = 0.006). No significant reduction in tox was observed among pts with high risk scores (p = 0.86). One-year survival (GAIN vs SOC) for each risk group was 73.6% vs 67.4% (low risk), 68.5% vs 64.5% (medium risk), and 57.3% vs 61.7% (high risk), respectively (log-rank p = 0.10). Conclusions: Older adults with low/medium, but not high, CARG risk scores benefit from GAIN. Additional strategies may be needed to improve outcomes for pts with high CARG risk scores. Clinical trial information: NCT02517034. [Table: see text]

Role of antibody engineering in generation of derivatives starting from MOv19 MAb: 40years of biological/therapeutic tools against folate receptor alfa.

In the 1980s, we developed and characterized numerous murine monoclonal antibodies (MAbs) directed against human tumor-associated antigens. This mini review is focused on the generation of derivatives of an anti-folate receptor α (FRα) MAbs, named MOv19, exploiting the antibody-engineering progresses in the last 40 years. The FRα location on the luminal surface of proliferating epithelial cells, inaccessible to circulation, versus its over-expression in the entire surface of numerous carcinomas suggested a role for anti-FRα MAbs in the diagnosis and/or treatment of solid tumors. Presently, two MOv19 derivatives are in clinical trials: a chimeric resurfaced version in an antibody-drug conjugate format (SORAYA trial, 2022) and the murine scFv in a second generation chimeric antigen receptor, CAR-T (Phase Ia, 2021). MOv19 and its derivatives could be considered a relevant example that well-characterized anti-tumor murine Mabs and antibody engineering could be combined to generate useful therapeutic tools.

Feasibility and usability of an electronic patient (pt)-reported outcome (ePRO) smartphone application (app) and biosensor for pts with cancer undergoing systemic therapy.

444 Background: Almost half of the nearly 370,000 pts with cancer who receive chemotherapy in the United States each year experience Emergency Department (ED) visits and unplanned inpatient (IP) stays during treatment, largely due to poorly controlled symptoms. Recent studies show that using PROs in oncology practice can improve symptom management and pt outcomes. This study examines the feasibility and usability of a PRO app paired with a biosensor to identify pts at high risk of ED and IP visits during systemic therapy. Methods: ML41539 is an ongoing prospective observational study evaluating the feasibility and usability of a clinic-provided app and smartwatch biosensor for monitoring pts undergoing systemic cancer therapy (ISRCTN25569053). Key inclusion criteria are 18–80 years old, Eastern Cooperative Oncology Group Performance Status 0–2, biopsy-proven solid tumor diagnosis (excluding non-melanoma skin cancer), and scheduled to receive a first dose of intravenous or oral cancer therapy as an initial or new line of therapy. Exclusion criteria include receiving radiation or hormone therapy only, residing in a skilled nursing facility, or participating in another clinical trial. The app collects 15 common treatment-related symptoms (PRO-CTCAE) daily. Usability and satisfaction were assessed with the modified mHealth App Usability Questionnaire (mMAUQ: score 1-7; higher score indicates better app usability and satisfaction) and the modified Quebec User Evaluation of Satisfaction with Assistive Technology (mQUEST 2.0: score 1-5; higher score indicates better sensor satisfaction). We report planned analysis results of the first 32 pts in the vanguard phase of the trial. Pts wore the biosensor and recorded symptoms on the app for 2 weeks. Results: Thirty-two pts from three Washington State community oncology clinics consented to the vanguard phase. One pt was not onboarded; two dropped out before completing the 2-week observation period. The mean age was 60 years; 68% were women. The most common cancer types were breast (41%), colorectal (13%), endometrial (9%), and melanoma (9%). Of the 29 pts, 59% completed all daily ePRO assessments and 55% wore the sensor every day during the 2-week period. The overall adherence rate was 91% (370/406 assessments) for ePRO and 86% (349/406 biosensor days) for the biosensor. The average mMAUQ score was 6.25 (n = 26); the average mQUEST score was 4.02 (n = 25). Conclusions: Pts receiving systemic cancer therapy had relatively high adherence to a daily digital monitoring system that included an ePRO app and biosensor. Participants expressed moderately high usability of the app and satisfaction with the biosensor. The results support the feasibility of monitoring pts with an app and biosensor. Future studies to assess adherence and data completeness for full courses of systemic therapy are needed. Clinical trial information: ISRCTN25569053.

Cardiovascular Vital Signs at Solid Tumor Diagnosis: Hypotension and Tachycardia Predict Shorter Overall Survival

Objective: We examined whether cardiovascular vital signs (VS) were prognostic for overall survival (OS) in newly diagnosed adult cancer outpatients. Methods: Electronic medical records data for patients with a solid tumor diagnosis and ≥2 consecutive weight measurements were analysed. BP (mmHg) and RHR (beats/minute) were identified at diagnosis (T1) and final visit (T2; >=7 days after T1). Systolic blood pressure (SBP) categories: <120; 120-129; 130-139; 140-149; ≥150. RHR categories: <60; 60-69; 70-79; 80-89; 90-100; 101-109; ≥110. Proportional Hazards Models examined potential prognostic factors for OS. Kaplan-Meier analysis estimated OS using lower (<80), normal (80-119), higher (≥120) SBP, and RHR of normal (60-100), bradycardia (<60), tachycardia (>100) categories. Results: N=5819; 59% men; mean age 61 (±12) years; 77% Caucasians; 9% African Americans. The most common tumor sites: prostate (19%), lung (15%), breast (14%). 18% had metastatic disease. Median OS after diagnosis was 27 months (range 25-28). Tachycardia had 2 to 3-fold increase in mortality. Survival time decreased by 8-10 months with lower SBP. RHR and SBP remained independently prognostic after adjusting clinically relevant characteristics at both timepoints. Conclusion: Elevated RHR and lower SBP independently predicted greater mortality in newly diagnosed cancer outpatients. These associations remained statistically significant longitudinally, and the differences observed were clinically important.

Expert consensus on the diagnosis and treatment of NTRK gene fusion solid tumors in China.

Gene fusions can drive tumor development for multiple types of cancer. Currently, many drugs targeting gene fusions are being approved for clinical application. At present, tyrosine receptor kinase (TRK) inhibitors targeting neurotrophic tyrosine receptor kinase (NTRK) gene fusions are among the first "tumor agnostic" drugs approved for pan-cancer use. Representative TRK inhibitors, including larotrectinib and entrectinib, have shown high efficacy for many types of cancer. At the same time, several second-generation drugs designed to overcome first-generation drug resistance are undergoing clinical development. Due to the rarity of NTRK gene fusions in common cancer types and technical issues regarding the complexity of fusion patterns, effectively screening patients for TRK inhibitor treatment in routine clinical practice is challenging. Different detection methods including immunohistochemistry, fluorescence in situ hybridization, reverse transcription-polymerase chain reaction, and (DNA and/or RNA-based) next-generation sequencing have pros and cons. As such, recommending suitable tests for individual patients and ensuring the quality of tests is essential. Moreover, at present, there is a lack of systematic review for the clinical efficacy and development status of first- and second-generation TRK inhibitors. To resolve the above issues, our expert group has reached a consensus regarding the diagnosis and treatment of NTRK gene fusion solid tumors, aiming to standardize clinical practice with the goal of benefiting patients with NTRK gene fusions treated with TRK inhibitors.

Rapid Characterization of Solid Tumors Using Resonant Sensors.

Cancer continues to be a significant cause of non-traumatic pediatric mortality. Diagnosis of pediatric solid tumors is paramount to prescribing the correct treatment regimen. Recent efforts have focused on non-invasive methods to obtain tumor tissues, but one of the challenges encountered is the ability to obtain an adequate amount of viable tissue. In this study, a wireless, inductor-capacitor (LC) sensor was employed to detect relative permittivity of pediatric tumor tissues. There is a comparison of resonant frequencies of tumor tissues between live versus dead tissues, the primary tumor tissue versus tissue from the organs of origin or metastasis, and treated versus untreated tumors. The results show significant shifts in resonant frequencies between the comparison groups. Dead tissues demonstrated a significant shift in resonant frequencies compared to alive tissues. There were significant differences between the resonant frequencies of normal tissues versus tumor tissues. Resonant frequencies were also significantly different between primary tumors compared to their respective metastases. These data indicate that there are potential clinical applications of LC technology in the detection and diagnosis of pediatric solid tumors.

Immunotherapy targeting mesothelin in acute myeloid leukemia.

Mesothelin (MSLN) is an emerging target that exists in soluble and membrane-associated forms. It is usually used for the diagnosis and treatment of MSLN-positive solid tumors. Interestingly, recent studies have shown that MSLN is highly expressed in 36% of acute myeloid leukemia (AML) patients and barely expressed in normal hematopoietic cells, which makes MSLN a promising target for the treatment of AML. It has been shown that MSLN is detectable as a diagnostic marker in its soluble form. Although the mechanism of action is unclear, MSLN remains a promising target for immunotherapy. Most MSLN research has been conducted in solid tumors, and less research has been conducted in hematopoietic tumors. Increasing research on MSLN is underway in AML, a hematopoietic neoplasm. For example, MSLN is related to extramedullary disease, minimal residual disease, and relapse in AML patients. Decreasing the expression of MSLN reduces the severity of the disease course. This information suggests that MSLN may be an ideal target for the treatment of many AML-related diseases to improve the prognosis and survival rate. At present, there are a few immunotherapies targeting MSLN in AML in preclinical and clinical trials, such as antibody-drug conjugates, bispecific T-cell engagers, and chimeric antigen receptor-T cells, which opens new room for the treatment of MSLN-related AML.

A synergistic therapy strategy for hypoxic solid tumor therapy

Photodynamic therapy (PDT) has been considered an effective treatment for various types of cancers. However, hypoxic microenvironment within the solid tumor is averse to oxygen-involved PDT, resulting in low therapeutic efficacy. This Preview highlights a recent study regarding a synergistic therapy that combines PDT and chemotherapy, in which hypoxic solid tumor diagnosis imaging and therapy can be achieved. Photodynamic therapy (PDT) has been considered an effective treatment for various types of cancers. However, hypoxic microenvironment within the solid tumor is averse to oxygen-involved PDT, resulting in low therapeutic efficacy. This Preview highlights a recent study regarding a synergistic therapy that combines PDT and chemotherapy, in which hypoxic solid tumor diagnosis imaging and therapy can be achieved. Engineering a theranostic platform for synergistic hypoxia-responsive photodynamic therapy and chemotherapyXiong et al.MatterMarch 11, 2022In BriefA molecular theranostic (DHQ-Cl-Azo) integrating hypoxia-responsive photodynamic therapy and chemotherapy, as well as NIR fluorescence surveillance, was reported. The agent serves as a novel heavy-atom-free photosensitizer via intersystem crossing. Thus, PDT could be operated in the normoxic tumor cells on the surface of solid tumors, and hypoxia-activatable chemotherapy was triggered in the hypoxic center of solid tumors. Through dual-mode therapies in different regions of a solid tumor with DHQ-Cl-Azo, good treatment efficacies for solid tumors have been achieved. Full-Text PDF

The role of confocal endomicroscopy for diagnosis of solid pseudopapillary tumor of the pancreas.

The role of confocal endomicroscopy for diagnosis of solid pseudopapillary tumor of the pancreas.

Timing Is Everything! Fertility Preservation Process From Patient Cancer Diagnosis Through Ovarian Tissue Cryopreservation to the Start of Treatment

AbstractChildren diagnosed with cancer today can expect a greater than 80% chance of 5-year survival. Childhood cancer survivors are significantly more likely to be infertile or have difficulty getting pregnant than their siblings. Studies have shown that infertility is one of the primary concerns of cancer survivors. Fertility preservation (FP) completed before treatment starts gives the patient the best fertility potential for a biological child in the future. Infertility is a significant risk factor for those treated with gonadotoxic therapy for cancer in childhood or adolescence. Infertility risk counseling and FP procedures may have the greatest success of fertility and hormone restoration if performed before the initiation of gonadotoxic therapy.A single-institution retrospective chart review was completed of patients enrolled in an institutional-review-board-approved ovarian tissue cryopreservation protocol from 2011 to 2019. Data collected include demographics and the timing of various stages of the FP process. One hundred five patients were included in this chart review (58 prepubertal and 47 postpubertal).Most consult requests were from the solid tumor diagnosis group. The time from diagnosis to consultation was 18 days, the time from consult to ovarian tissue cryopreservation surgery was 7 days, and the time from surgery to treatment was 5 days. Further investigation of time to consult revealed timing was justified in most patient situations.Workflow, education, and outreach were established. Future analyses will include defining the incidents and efficiencies in providing fertility and hormone consultations in female and male patients who do not undergo FP procedures.

Significance of serum carcinoembryonic antigen in metastatic breast cancer patients: A prospective study.

BACKGROUNDCarcinoembryonic antigen (CEA) is an important serum tumour marker with a substantial role in diagnosis and monitoring of various solid tumours. About 36%-70% of breast cancers have elevated serum CEA. And the available studies show discrepancy in addressing the prognostic significance of CEA in advanced breast cancer.AIMTo estimate the serum CEA level in our metastatic breast cancer patients and correlate it with response to treatment and clinical outcome.METHODSThis was a prospective clinical study conducted on 50 metastatic breast cancer patients treated at breast clinic, with newly diagnosed metastatic breast cancer planned for palliative chemotherapy, targeted therapy, and hormonal treatment. We estimated the proportion of patients with elevated serum CEA level at baseline and after palliative treatment and also studied the association of serum CEA levels with known prognostic factors. The response to treatment was correlated with the serum CEA levels in the context of responders and non-responders.RESULTSThe median pre-treatment and post-treatment CEA levels were 7.9 (1.8-40.7) ng/mL and 4.39 (1.4-12.15) ng/mL, respectively, in the whole study population (P = 0.032). No statistically significant difference was seen in baseline serum CEA between responders and non-responders. Even in the luminal group, pre-treatment serum CEA was not a predictor of response, but post-treatment CEA was a significant predictor of tumour progression. In patients with liver and lung metastases, post-treatment CEA level difference was not statistically significant in both responders and non-responders though the values were higher in non-responders. Among those with bone metastases, 69.5% had elevated post-treatment serum CEA, and only 37.5% had elevated serum CEA in those with no bone metastases.CONCLUSIONElevated post-treatment serum CEA levels are associated with disease progression and poor response to therapy. Persistently elevated post-treatment serum CEA levels are significantly associated with bone metastases. Elevated serum CEA and hormonal status are significant predictors of treatment response.

Abstract CT216: A phase 0 master protocol utilizing a novel intratumoral microdosing approach for simultaneously evaluating multiple drugs and drug combinations in patients with solid tumors

Abstract Purpose/Objectives: Tumor responses to cancer treatments are highly context-specific and often involve complex interactions between the anti-cancer therapy, genetically diverse tumor cells, and a heterogeneous tumor microenvironment (TME). All preclinical models fall short in capturing this complexity. CIVO (Comparative In Vivo Oncology) is an intratumoral microdose injection research tool intended to bridge the translational gap between preclinical and clinical studies by enabling in situ assessment of up to 8 oncology drugs or drug combinations simultaneously within a patient’s tumor. The CIVO Phase 0 model was established under FDA’s exploratory IND guidelines for microdosing. A Master Protocol was then developed, enabling ongoing evaluation of multiple investigational drugs and combinations without a need for stand-alone new protocols. Each investigational drug or combination is specified as a substudy of the Master Protocol, thus reducing administrative burden to clinical site staff and creating an infrastructure to ensure quality data and oversight of patient safety. This is a multi-center, open-label Phase 0 Master Protocol designed to study the localized pharmacodynamics (PD) of anti-cancer therapies within the TME when administered intratumorally in microdose quantities via the CIVO device. The safety of intratumoral microdose administration via the CIVO device will also be evaluated. Materials/Methods: Approximately 12 subjects are expected to be enrolled per substudy. All substudies will evaluate subjects ≥18 years with a diagnosis of solid tumors with scheduled surgical intervention. Eligible subjects have at least one lesion (primary or recurrent tumor or effaced metastatic lymph node) ≥2 cm in the shortest diameter that is surface accessible for CIVO injection. Each substudy will define the tumor type and specific eligibility criteria for enrollment. The study visits consist of screening, CIVO injection, surgical intervention, and two follow-up visits. All patients will be injected by the CIVO device containing microdose quantities of drugs specified in respective substudies. The CIVO device can be configured with 3, 5, or 8 needles and the device configuration will be assigned on a per-patient basis, dependent upon lesion size. Following surgical resection, the injected portion of the tumor will undergo central PD biomarker analysis. At the time of submission, the study is open for enrollment with 1 substudy enrolling Head and Neck Squamous Cell Carcinoma (HNSCC) patients and 1 substudy enrolling HNSCC or soft tissue sarcoma patients. The Master Protocol was established to efficiently add substudies and accommodate evaluation of a wider repertoire of new agents in order to continually inform and de-risk drug development via the CIVO platform. Clinical trial information: NCT04541108. Citation Format: Karthik Rajasekaran, Jason G. Newman, Robert G. Maki, Thomas J. Ow, Vikas Mehta, Kenneth R. Gundle, Daniel R. Clayburgh, Ryan J. Li, Mercedes Porosnicu, Cherie-Ann O. Nathan, Alice Tang, Beryl A. Hatton, Kimberly H. Sottero, Gloria Kung, Marc O. Grenley, Kirsten Anderson, Richard A. Klinghoffer. A phase 0 master protocol utilizing a novel intratumoral microdosing approach for simultaneously evaluating multiple drugs and drug combinations in patients with solid tumors [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr CT216.

Abstract CT255: Study of PRS-344/S095012 a PD-L1/4-1BB bispecific antibody-Anticalin®-fusion in patients with solid tumors

Abstract PRS-344/S095012 is a bispecific antibody-Anticalin® fusion protein targeting PD-L1 and 4-1BB. It is designed to block the PD-1/PD-L1 axis and localize 4-1BB co-stimulation to PD-L1-positive tumor microenvironment (TME) or tumor draining lymph nodes with the aim of maximizing antitumor immunity and increasing the therapeutic window of 4-1BB monoclonal antibodies (mAbs). Multiple in vitro assays have shown that PRS-344/S095012 inhibits PD-1/PD-L1 signaling while simultaneously activating 4-1BB signaling on T cells. This resulted in a synergistic effect on both pathways leading to anti-tumor immune responses. PRS-344/S095012 presents mAb-like pharmacokinetics in vivo and non-clinical mouse models demonstrated dose-dependent efficacy in anti-PD-L1 refractory tumors. In the higher dose range, complete tumor regression was achieved in PD-L1 high and PD-L1 low expressing xenograft mouse models. This first-in-human (FIH), phase 1/2, open-label, multi center, dose escalation and cohort expansion study is designed to determine the safety and tolerability of intravenously administered PRS-344/S095012 in patients with advanced and/or metastatic solid tumors (NCT05159388). Patients with histologically confirmed diagnosis of unresectable, locally advanced, or metastatic solid tumors for which standard treatment options are not available, no longer effective, or not tolerated are eligible. Patients must have Eastern Cooperative Oncology Group (ECOG) status 0 or 1, RECIST 1.1 measurable disease and should have documented progression on prior therapy. Prior therapy with 4-1BB agonists is prohibited. Phase 1 is a dose escalation guided by a Bayesian Logistic Regression Model and a 28-day dose limiting toxicities (DLT) period. Primary objectives are safety and tolerability of PRS-344/S095012; secondary objectives include exploration of antitumor activity and evaluation of pharmacokinetics. Pharmacodynamics and comprehensive biomarker program will be explored. Additional patients may be enrolled to backfill cohort(s)to further explore pharmacokinetic/pharmacodynamic signals. Phase 2 is an expansion with primary objective of anti-tumor activity. First patient was dosed in November 2021 and the study is planned to enroll at sites in Belgium, Spain and Australia. Citation Format: Christiane Jungels, Nuria Kotecki, Emiliano Calvo, Elena Garralda, Timothy Price, Xiaojiang Zahn, Atif Abbas, Lisa Mahnke, Winrich Rauschning, Aizea Morales-Kastresana, Lucia Pattarini, Birgit Bossenmaier, Alix Scholer-Dahirel, Tim Demuth, Julie Legrande. Study of PRS-344/S095012 a PD-L1/4-1BB bispecific antibody-Anticalin®-fusion in patients with solid tumors [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr CT255.

IMG-11. A COMPUTERISED CLINICAL DECISION SUPPORT SYSTEM FOR DIAGNOSING CHILDREN’S BRAIN TUMOURS USING FUNCTIONAL IMAGING AND MACHINE LEARNING

Abstract INTRODUCTION: Magnetic resonance imaging is a key investigation in the diagnosis of childhood solid tumours. Advanced techniques such as diffusion weighted imaging (DWI), magnetic resonance spectroscopy (MRS) and perfusion imaging probe the underlying cellular, chemical and vascular nature of the disease. Coupled with machine learning these scanning methods show improvement in diagnostic accuracy compared with conventional imaging. Advanced image analysis is not routinely available in hospitals. We present a clinical decision support system (CDSS) developed for advanced MR analysis and interpretation. METHOD: The CDSS was developed in house. The Children’s Cancer and Leukaemia Group Functional Imaging Group (CCLGFIG) Database, a national resource, was used to provide a repository of cases together with their advanced imaging and machine learning diagnostic classifiers. A new case is displayed alongside cases in the repository with known diagnoses, including summary statistics for relevant diagnostic categories. The CDSS was made available to radiologists, in their clinical environment for technical and clinical evaluation. Structured interviews were undertaken. The CDSS was developed as a computer app for multi-centre distribution. RESULTS: 436 MRS, 240 DWI and 85 perfusion cases were available for building repositories. Machine learning classifiers showed diagnostic accuracies for the major childhood brain tumour types of 85-95%. Comparison of MRS with a data repository was found to improve non-invasive diagnosis. Results from the CDSS can be uploaded to the CCLGFIG to support multicentre research. Positive feedback on the CDSS from clinicians included: ready access to advanced analysis; simple and efficient integration into clinical workflow; and assisted interpretation of advanced analysis. DISCUSSION: Advanced MR analysis techniques provide improved non-invasive diagnostic accuracy but are difficult to implement on clinical systems due to technical, infrastructure and training limitations. CONCLUSION: We have successfully released a CDSS for paediatric cancer within the hospital environment and assessed its suitability for clinical use.

NFB-21. Neurofibromatosis Type I in the Setting of Neuro-Oncology

Neurofibromatosis Type I (NF1) is an autosomal dominant genetic syndrome that is inherited or sporadic. Neuro-Oncology nurses are experienced in the multidisciplinary care of NF1 patients due to an increased incidence of brain tumors and the treatment of plexiform neurofibromas with Mek inhibitors. However, these children are also at higher risk of rare solid tumors, specifically malignant peripheral nerve sheath tumors (MPNST). Most brain tumors in NF1 have a good prognosis. Conversely, MPNST has an extremely poor prognosis. While patients with MPNST are often cared for by solid tumor care teams, the identification and diagnosis of the tumors occur under the care of the neuro-oncology care team. Complex care coordination for patients with NF1 and cancer is required. Specifically, patients with NF1 are more sensitive to chemotherapy, have a higher incidence of radiation-induced secondary tumors, and need monitoring for NF1 related health impacts. Nurses and nurse practitioners with expertise in neuro-oncology, NF1, and solid tumors must collaborate to provide comprehensive care. Teaching tools and clinical strategies have been developed to maintain patients’ continuity with the primary oncology team while gaining the support of subspecialists. The genetic basis, inheritance pattern, and characteristics of Neurofibromatosis Type I will be discussed as well as rare oncologic diagnoses that are more prevalent in children/young adults with NF1. The multidisciplinary approach to the care of the patient with NF1 and a rare cancer diagnoses at a tertiary care center as well as the optimization of care of patients with NF1 and other underlying syndromes and rare cancers will be reviewed. Increased knowledge of NF1 and the associated health impacts and risk of cancers will improve the care of all patients with NF1.

Differential diagnosis of hematologic and solid tumors using targeted transcriptome and artificial intelligence.

3018 Background: Diagnosis and classification of tumors is becoming increasingly dependent on biological and molecular biomarkers. RNA expression profiling using next generation sequencing (NGS) provides information on various biological and molecular changes in the cancer and in the microenvironment. We explored the potential of using targeted transcriptome and artificial intelligence (AI) in the differential diagnosis and classification of various hematologic and solid tumors. Methods: RNA from hematologic neoplasms (N = 2606) and solid tumors (N = 2038) as well as normal bone marrow and lymph node control (N = 806) were sequenced by NGS using a targeted 1408-gene panel. The hematologic neoplasms included 20 different subtypes. Solid tumors included 24 different subtypes. Machine learning is used for comparing two classes at a time. Geometric Mean Naïve Bayesian (GMNB) classifier is used to provide differential diagnosis across 45 diagnostic entities with assigned ranking. Results: Machine learning showed high accuracy in distinguishing between two diagnoses with AUC varied between 1 (Sarcoma vs GIST) and 0.841 (MDS vs normal control) (examples in Table). For differential diagnosis between all 45 different diagnoses, we used 3045 samples for training the GMNB algorithm and 1415 samples for testing. Correct first choice diagnosis was obtained in 100% of ALL, 88% of AML, 85% of DLBCL, 82% of colorectal cancer, 88% of lung cancer, 72% of CLL, and 72% of follicular lymphoma. The algorithm had difficulty in typically overlapping diagnoses and diagnosed as first choice 19% of MDS, 46% of normal, and 12% of MPN. Diagnosis improved significantly when second choice was considered. Conclusions: Targeted RNA profiling with proper AI can provide highly useful tools for the pathologic diagnosis and classification of various cancers. Additional information such as mutation profile and clinical information can improve these algorithms, reduce subjectivity, and minimize errors in pathologic diagnoses. [Table: see text]

Development of a predictive model for emergency room utilization and unanticipated hospital admission in patients receiving cancer treatment for solid tumor malignancies.

e18674 Background: Unanticipated healthcare resource utilization, in the form of either emergency department utilization (EDUs) or hospital admission (HA), is an indicator of lower quality of cancer care. The objective of this study was to develop a comprehensive predictive model for emergency department utilization and hospital admission (HA) for patients with solid tumors who received chemotherapy within 30 days. Methods: We abstracted electronic health data on oncology encounters from all patients receiving systemic therapy chemotherapy for solid tumors from March 01, 2015 to August 21, 2020. Patients included in the cohort met the following criteria:1) Ages > = 18 years old 2) Diagnosed with any solid tumor (3) Had any oncology treatment plan related to their solid tumor diagnosis; 4) Received at least one chemotherapy during March 01, 2015 through August 21, 2020. We defined a primary composite outcome of emergency visit or unanticipated hospitalization within 30 days after the encounter. Patient information was abstracted. We developed a predictive model for the primary outcome using LASSO logistic regression modeling. To evaluate the model, we calculated the Area Under the Receiver Operator Characteristic (AUROC) and the calibration slope. Results: 12,917 unique patients with 134,641 encounters were included. Of these, 9100 (6.7%) of encounters were ED visits or hospitalizations. 714 patients (5.5%) had at least one ED visit or hospitalization within 30 days of treatment; patients at highest risk for this outcome included those with pancreatic cancer, lung cancer and ovarian/endometrial cancer (9.1%, 7.4% and 6.8% respectively). 38 variables were identified as contributing to the LASSO model. The top predictors, in order of importance, were fever, hypernatremia, hypotension and low albumin. The model’s AUC was 0.83, indicating good model sensitivity to outcome. Conclusions: Approximately 7% of healthcare encounters in patients undergoing treatment for solid malignancies were ED visits or hospitalizations. Identifying patients at highest risk for this outcome may prevent unnecessary resource utilization and optimize patient care during cancer treatment. The model developed in this study demonstrated good sensitivity and could be implemented in clinical practice to allow for preventive outpatient interventions. Work is ongoing to integrate this model into clinical care at our institution.[Table: see text]

Hospitalization and post-discharge survival outcomes of adolescents and young adults with cancer.

e18687 Background: Cancer incidence has increased among adolescents and young adults (AYA) over the last two decades. Younger patients often present with late diagnosis, aggressive disease, and are more likely to receive chemotherapy during cancer treatment. We investigated admission outcomes and post-discharge survival of AYA who were hospitalized after urgent admission. Methods: Retrospective cohort of patients with solid tumor diagnosis and age between 18 and 39 years, hospitalized after urgent admission to a tertiary, publicly-funded, cancer hospital in São Paulo, Brazil, from February 1st to December 31th 2021. We excluded patients with positive COVID-19 RT-PCR. We collected data on gender, cancer diagnosis, length of hospital stay, in-hospital mortality, chemotherapy infusion either before and during hospitalization; and last-follow up date and status. AYA admissions were compared to older adults (≥ 40 years [non-AYA]) admissions with chi-squared test. Overall survival (OS) after discharge between groups was analyzed with the log-rank test. Results: Of 4011 admissions, 312 were AYA. The median age was 34 (IQR 29-38) and most patients were female (63%). Compared to older adults (N = 3699), a higher proportion of AYA patients had breast cancer (25% vs 15%), central nervous system cancer (8.4% vs 2.6%), cervical cancer (12% vs 2.7%) and germinative cancer (4.5% vs 0.3%). The median length of hospital stay was 6 days (IQR 4-10). AYA were more likely to be under chemotherapy treatment during (11% versus 4%, p = 0.001) and within 30 days before hospitalization (32% vs 20%, p = 0.001). The overall in-hospital mortality rate was lower among AYA compared to older adults during the same period (12% vs 20%, p = 0.01). However, of those who died, a higher proportion were prescribed chemotherapy infusion before (38% vs 19%, p = 0.004) and during (15% vs 3.3%, p = 0.003) hospitalization; and a higher number of patients deceased on intensive-care unit beds, although the difference was not statistically significant (46% versus 36%, p = 0.2). Despite similar rates of 30-days readmissions (29% versus 26%, p = 0.3), AYA had better prognosis after discharge (mOS 295 days versus 181 days, p = 0.002). Conclusions: AYA patients had better hospitalization outcomes and were more likely to receive aggressive care near the end of life. Despite similar rates of early (≤ 30 days) readmissions, AYA had higher median overall survival after discharge compared to older adults. These finding should be taken into consideration when discussing hospitalization goals during admission of AYA with cancer.

Evaluation of a pharmacist-led video consultation to identify drug interactions among patients initiating oral anticancer drugs.

1592 Background: The past decade has seen a dramatic increase in the number of oral anti-cancer drug (OACD) approvals in the United States. Though polypharmacy and drug-drug interactions (DDIs) likely contribute to OACD toxicity, the prevalence of these features in patients on OACDs remains largely unknown. We aimed to evaluate a one-time 30-minute pharmacist-led video consultation among metastatic cancer patients initiating OACDs to identify medication list inaccuracies as well as the prevalence, characteristics, and severity of OACD-related potential DDIs. Methods: We conducted a single-arm, prospective telehealth intervention study among 29 patients initiating OACDs to evaluate a one-time 30-minute pharmacist-led video consultation. The video visits focused on identifying and discussing polypharmacy and potential DDIs, and pharmacists then communicated recommendations to each patient's oncologist. We estimated the prevalence, characteristics (QTc prolongation, absorption interactions, etc.), and severity of OACD-related potential DDIs. Lexicomp and Micromedex were used to assess potential DDIs and measure severity on a standardized scale (A – D, X). In addition, we assessed the prevalence of medication list inaccuracies, polypharmacy, and patient satisfaction. Results: Twenty-five patients completed the intervention (86% completion rate) of whom 40% were 75 years of age or older and 60% were men. The majority were white (68%) and non-Hispanic (76%). Sixteen patients (68%) had a solid tumor diagnosis. Nearly half (48%) were insured by Medicare. The median number of medications per patient was 9 with a range of 4 – 21, and 96% of patients had at least 5 prescriptions listed. The median number of medication list errors was 2 with a range of 0 – 16, with at least 1 error for 76% and more than 1 error for 52% of patients. Pharmacists identified potential OACD-related interactions in 9 cases (40%). These included change in drug absorption or metabolism (7), QTc prolongation (1), hypotension (1), and bleeding (1). Interactions were classified as either category C (8) or D (2), requiring close monitoring or a change in treatment, respectively. All patients expressed a high level of satisfaction with the video visit. Conclusions: Polypharmacy, medication list errors, and potential DDIs are prevalent among patients initiating OACDs despite use of an electronic medical record requiring medication reconciliation. Our study suggests that a one-time remote 30-minute pharmacist-led video consultation can effectively identify and address OACD-related potential DDIs, which may decrease medication complexity and improve adherence in this population.