Citations

Background and motivation: Lung computed tomography (CT) techniques are high-resolution and are well adopted in the intensive care unit (ICU) for COVID-19 disease control classification. Most artificial intelligence (AI) systems do not undergo generalization and are typically overfitted. Such trained AI systems are not practical for clinical settings and therefore do not give accurate results when executed on unseen data sets. We hypothesize that ensemble deep learning (EDL) is superior to deep transfer learning (TL) in both non-augmented and augmented frameworks. Methodology: The system consists of a cascade of quality control, ResNet–UNet-based hybrid deep learning for lung segmentation, and seven models using TL-based classification followed by five types of EDL’s. To prove our hypothesis, five different kinds of data combinations (DC) were designed using a combination of two multicenter cohorts—Croatia (80 COVID) and Italy (72 COVID and 30 controls)—leading to 12,000 CT slices. As part of generalization, the system was tested on unseen data and statistically tested for reliability/stability. Results: Using the K5 (80:20) cross-validation protocol on the balanced and augmented dataset, the five DC datasets improved TL mean accuracy by 3.32%, 6.56%, 12.96%, 47.1%, and 2.78%, respectively. The five EDL systems showed improvements in accuracy of 2.12%, 5.78%, 6.72%, 32.05%, and 2.40%, thus validating our hypothesis. All statistical tests proved positive for reliability and stability. Conclusion: EDL showed superior performance to TL systems for both (a) unbalanced and unaugmented and (b) balanced and augmented datasets for both (i) seen and (ii) unseen paradigms, validating both our hypotheses.

The impact of bariatric surgery (BS) on kidney transplantation (KT) outcomes in patients with obesity remains controversial. We systematically searched MEDLINE, EMBASE, Scopus, Web of Science, and Cochrane Central Register of Controlled Trials for studies reporting outcomes of KT recipients that underwent prior BS. Common/random effects meta-analyses were performed to obtain summary ratios of the postoperative outcomes. Eighteen eligible studies involving 315 patients were identified. Sleeve gastrectomy was the most common BS type (65.7%) followed by Roux-en-Y gastric bypass (27.6%) and gastric banding (4.4%). Across studies that provided the data, the %excess weight loss from BS to KT was 62.79% (95% confidence interval [CI], 52.01-73.56; range, 46.2%-80.3%). The rates of delayed graft function and acute rejection were 16% (95% CI, 7%-28%) and 16% (95% CI, 11%-23%) in 14 and 11 studies that provided this data, respectively. The rates of wound, urinary, and vascular complications following KT were 5% (95% CI, 0%-13%),19% (95% CI, 2%-42%), and 2% (95% CI, 0%-5%), in 12, 9, and 11 studies that provided this data, respectively. Follow-up time after KT was reported in 11 studies (61.1%) and ranged from 16 mo to >5 y. Graft loss was reported in 14 studies with an average of 3% (95% CI, 1%-6%). Four studies that included a comparator group of patients with obesity who did not undergo BS before KT showed comparable outcomes between the groups. We conclude that currently there is a paucity of robust evidence to suggest that pretransplant BS has a major effect on post-KT outcomes. High-quality studies are needed to fully evaluate the impact of BS on KT outcomes.

e24161 Background: Pertuzumab-induced gastrointestinal toxicities (PIGT), particularly diarrhea, is the most common adverse event reported in over 70% of patients receiving pertuzumab in combination with chemotherapy. PIGT can result in dose reduction, treatment delay, and discontinuation of chemotherapy. Rifaximin is a minimally absorbed oral antibiotic approved for gastrointestinal tract infections and bacterial overgrowth. Our aim was to evaluate the efficacy of rifaximin in reducing PIGT. Methods: Patients with stage I-III HER2-positive (HER2+) breast cancer who received pertuzumab in combination with docetaxel, carboplatin, and trastuzumab (TCHP) were enrolled. PIGT included diarrhea, abdominal distention, abdominal pain, dyspepsia, stomach pain, and typhlitis. Patients with any PIGT ≥ grade 2 after the first cycle of TCHP received rifaximin 550 mg orally twice daily on days 1-5 in all subsequent cycles of chemotherapy. Patients with PIGT grade < 2 were observed without rifaximin. Simon's Two-Stage design was used. Results: Between 2018-2022, a total of 21 patients were enrolled. One patient was excluded due to significant anemia not meeting the eligibility criteria to proceed with rifaximin after the first cycle of TCHP. Of 20 patients, the median age was 52.5 (39-69) years. 18/20 (90.0%) patients had PIGT ≥ grade 2 after 1 cycle of TCHP with PIGT grade 2 in 15 (83.3%) and grade 3 in 3 (16.7%). PIGT ≥ grade 2 included diarrhea in 14 (70.0%) with grade 2 in 12 (60.0%) and grade 3 in 2 (10.0%), abdominal pain in 9 (45.0%) with grade 2 in 8 (40.0%) and grade 3 in 1 (5.0%), abdominal distension in 3 (15.0%), dyspepsia in 5 (25.0%), and stomach pain in 4 (20.0%) patients. Among 18 patients who received rifaximin, 15 (83.3%; 95% CI 0.586-0.964) had at least 1 cycle with a maximum PIGT grade < 2. This result surpassed the threshold of the Two-Stage analysis. Reduction of individual PIGT symptoms for patients who experienced > grade 2 at baseline after the first cycle of rifaximin was reported in 2/3 (66.7%) for abdominal distention, 8/9 (88.9%) for abdominal pain, 6/14 (42.9%) for diarrhea, 3/4 (75.0%) for stomach pain, and 4/5 (80.0%) for dyspepsia. No patients experienced > grade 2 typhilitis at baseline and during treatment. Treatment is well tolerated, with no significant grade 3+ adverse event related to rifaximin observed. Among patients who received rifaximin, there was no treatment delay or discontinuation of pertuzumab related to PIGT. Conclusions: PIGT is a debilitating side effect observed in most patients receiving pertuzumab. A short course of rifaximin after each cycle of treatment is a well-tolerated treatment option that significantly reduces PIGT in patients receiving pertuzumab in combination with chemotherapy. Clinical trial information: NCT04249622 .

e24104 Background: There is a high rate of anemia present in cancer patients and anemia is also a common referral to a hematologist. Symptomatic anemia can significantly impair an individual’s functional status so identifying its cause is essential for improving quality of life. Correction of nutritional deficiencies, like iron, B12, and folate deficiency can improve hemoglobin counts, prevent recurrent PRBC transfusions, and can often resolve the anemia. In a busy academic hematology oncology practice, we hypothesize that it is easy to overlook performing a basic nutritional evaluation especially in the setting of other causes for anemia such as chemotherapy, hemolysis, blood loss, chronic kidney disease, and other disorders. We aim to evaluate the frequency of anemia workup in the hematology and oncology division at our academic institution. Methods: We conducted a retrospective study of all hematology oncology patients seen in our clinic who received a blood transfusion in 2021. All patients were 18 years old or order and received at least one-unit PRBC transfusion as an outpatient. One “transfusion event” was defined as any number of PRBC transfusions on a single day and any subsequent transfusions within a 90-day periods. A single patient, therefore, can have multiple distinct transfusion events. We analyzed whether patients received a “basic” anemia evaluation, defined as checking ferritin, iron saturation, B12, and folate levels within 3 months before or after the first transfusion, and whether a discrepancy in practice patterns exists between different hematology oncology subspecialties. Results: At the interim analysis, we identified 368 transfusion events for 275 patients. Those events were ordered by providers (physician, nurse practitioner, or physician assistant) in the following subspecialties: oncology (n = 20), malignant hematology (n = 18), classical hematology (n = 3), and fellow-in-training (n = 5). A basic anemia workup was missing in 58% (84 of 146), 27% (49 of 183), 23% (8 of 35), 40% (2 of 5) in the above groups respectively. For patients with macrocytic anemia defined as mean corpuscular volume (MCV) > 100 fL, 48% (38 of 79) did not have B12 or folate levels checked within 3 months before or after a transfusion event. For patients with MCV < 80 fL, 47% (14 of 30) did not have ferritin or iron saturation checked within 3 months before or after a transfusion event. Conclusions: We observed a high percentage of cancer and non-malignant hematology patients who did not receive a basic anemia evaluation within three months before or three months after a blood transfusion. A higher percentage of patients with solid tumors patients who required PRBC transfusions did not receive a basic anemia evaluation in a timely manner. Our study identified an area of quality improvement and need for intervention that can easily be overlooked in a busy academic hematology oncology practice.

e24089 Background: Little is known about risk and protective factors for dementia in cancer survivors. With increasing longevity due to improved cancer therapy, it’s prudent to study factors contributing to cognitive impairment in this patient population. Methods: We performed multivariable cox regression analyses to assess established risk factors for all-cause dementia (age, education, APOE4-status, social and physical activity engagement) in breast and prostate cancer survivors. Patients 50+ years old with pathology-confirmed cancer diagnosis at Mayo Clinic were identified from a longitudinal, population-based cohort – Mayo Clinic Study of Aging. Analyses were controlled for age, APOE4-status, education, and cancer treatment. Results: We included a total of 209 patients with breast cancer (mean age 75.4 years, 24% APOE4-positive, median follow-up 6.8 years) and 352 with prostate cancer (mean age 77 years, 26% APOE4-positive, median follow-up 6.4 years). 31 patients with breast cancer (15%) and 66 patients with prostate cancer (20%) were diagnosed with dementia at last follow-up. Older age was associated with increased risk for dementia (5-year increase – breast: hazard ratio (HR) 1.9 [95%CI 1.3-2.7, p = 0.001]; prostate: HR 2.4 [95%CI 1.8-3.2, p < 0.0001]). APOE4-positivity was associated with increased dementia risk in breast (HR 3.6 [95%CI 1.6-7.8, p < 0.002]), but not prostate cancer (HR 1.2 [95%CI 0.7-2.0, p = 0.5]). More education was associated with lower dementia risk in prostate cancer (education year: HR 0.91 [95%CI 0.84-0.98, p < 0.02]; education years > 12: HR 0.26 [95%CI 0.1-0.6, p < 0.001]). Physical activity engagement in mid-life was associated with lower dementia risk (prostate: HR 0.56 [95%CI 0.4-0.8, p < 0.005]; breast: HR 0.48 [95%CI 0.3-0.9, p < 0.02]). Conclusions: In this longitudinal, population-based study we found that some risk and protective factors for dementia in cancer survivors vary by cancer type. While advanced age is an expected dementia risk factor, there were mixed results for APOE4-positivity (increased risk only in breast cancer) and education (only protective in prostate cancer). Our results support further study into factors influencing dementia risk by cancer type in hopes of identifying preventative strategies.

e24078 Background: The addition of anti-CD38 mAbs, daratumumab and isatuximab, to standard anti-myeloma regimens have drawn scrutiny towards long-term safety concerns, including the risk of SPMs. ICARIA-MM study reported SPMs in 3.9% patients (pts.) in the Isatuximab, pomalidomide and dexamethasone (Isa-Pd) arm compared to 0.7% in the Pd arm. We hypothesized that exposure to anti-CD38 mAbs could potentially increase risk of SPMs due to prolonged immunosuppression. An assessment of this association is warranted, given the improved life expectancy and growing prevalence of pts. with MM. Methods: We performed a meta-analysis on data obtained from RCTs published between January 2005 and April 2022 that compared anti-CD38 mAb-based regimens to other standard anti-myeloma regimens (control) in pts. with newly diagnosed or relapsed/refractory (r/r) MM. Total number of SPMs (including categories) were extracted for pts. in both groups. Malignant melanomas were included under solid SPM category. Binary outcome data were analyzed using fixed-effect Peto method. Treatment effect estimates were expressed as odds ratio (OR) and 95% confidence interval (CI). I2 > 50% indicated substantial heterogeneity. Results: 10 RCTs involving 4980 pts. were included, with 2824 (57%) and 2156 (43%) pts. randomized to the anti-CD38 mAb and control arms, respectively (Table). Overall, 191 and 112 SPMs were reported in the anti-CD38 mAb and control arms, respectively. At a median follow-up of 35.3 months, anti-CD38 mAb exposure was associated with an increased risk of developing SPMs compared to control (6.8% vs. 5.2%; OR: 1.53 [95% CI: 1.20-1.95]; I2= 0%). Non-melanoma cutaneous cancers were the most common, and higher in the anti-CD38 mAb vs. control arms (92 versus 47; OR: 1.77 [95% CI: 1.25-2.51]; I2= 0%). The increase in solid cancers (including melanoma) (OR: 1.28 [95% CI: 0.85-1.95]) and hematologic SPMs (OR: 1.86; [95% CI: 0.81-4.27] was not significant. On sensitivity analysis, the total number of SPMs were higher in the anti-CD38 mAb arm vs. control arm, regardless of the presence of immunomodulatory drugs in combination regimen. Conclusions: This meta-analysis shows an increased risk of SPMs in pts. with MM exposed to daratumumab or isatuximab, particularly that of non-invasive cutaneous tumors. This association should be further investigated in real-world settings using large databases. [Table: see text]

e24049 Background: Vulvo-Vaginal Atrophy (VVA) or Genitourinary Syndrome of Menopause (GSM) is a common condition among breast cancer (BC) patients, especially those undergoing antiestrogen therapy. Despite being an option in refractory cases, the safety of hormonal treatment remains uncertain in this population. The aim of this study was to review the safety and serum estrogen levels of hormonal therapy in patients with BC history presenting with VVA symptoms. Methods: Pubmed, Embase, and Cochrane were searched for studies comparing different hormonal treatment options for VVA in breast cancer survivors. Statistical analysis was performed using a random effects model and heterogeneity using Cochran's Q-statistic and the I2 index. Results: We included 17 studies, of which 5 were randomized controlled trials (RCTs). Treatment modalities included in this study were topical vaginal estradiol and estriol preparations, vaginally applied testosterone, DHEA, and ospemifene. We found that, among patients treated with the estriol and estradiol preparations, there was an average increase of 7.67pg/ml (SMD 7.67 pg/mL; 95% CI -1.00, 16.35; p < 0.001). Analysis of the testosterone group found temporary peaks of serum estradiol levels, but one study showed persistent elevation above normal postmenopausal levels. One study with prasterone revealed no elevation of serum estradiol concentration. One study with ospemifene demonstrated no increase in the risk of BC recurrence. Conclusions: In conclusion, among treatments available for BC survivors, low-dose vaginal estrogen showed the smallest changes in serum estradiol levels and had the most evidence, but safety remains unclear, especially for patients on aromatase inhibitors. Alternative treatments such as ospemifene need more data supporting safety and efficacy. These results suggest that concerns related to cancer recurrence should keep aiming for the lowest possible concentration.

e24042 Background: Cancer is 2nd leading cause of death (1 in every 5) in the United States followed by heart disease. Use of ketogenic diet (KD)- high-fat & low-carbohydrate diet, allows fatty acids to become the obligatory source of cellular energy which can help in decreasing the tumor cell growth. Aim of this study was to evaluate role of KD in different types of cancer. Methods: We performed a systematic review using PRISMA protocol to identify articles describing the role of the ketogenic diet in cancer patients in PubMed. Keywords like cancer, neoplasm, tumor, KD, and intermittent fasting (IF) were used & filters like full text, English, human, observational studies, & clinical trials (CTs) were applied between 2018-2022. Results: Of the 362 studies after using filters only 22 studies were CTs. Of these 22, 12 studies were excluded & 10 studies were included in this study. [Table 1] We found CTs describing role of KD, IF or standard diet (SD) in brain cancer, non-metastasized rectal cancer, high-grade glioma, head and neck squamous cell carcinoma, locally advanced and metastatic breast cancer, ovarian and endometrial cancer. KD was describes as an accompanying measure for patients undergoing standard-of-care therapy that helps to improve the quality of life, survival & acceptable safety and tolerability. KD may augment the antitumor effects of classic chemotherapy and radiotherapy. Conclusions: Role of KD is described in depth, but majority RCT results were heterogeneous in nature to provide quantitative measures of survival timeline, outcomes, & recovery. Thus, more human prospective studies are warranted to evaluate the therapeutic effectiveness & safety of KD.[Table: see text]

12114 Background: A retrospective study suggested a potential benefit from rose geranium in sesame oil nasal spray for alleviating nasal vestibulitis symptoms in patients (pts) undergoing chemotherapy. Methods: Pts undergoing active chemotherapy who reported moderate or worse nasal symptoms were randomized 1:1 to receive a rose geranium in sesame oil nasal spray (RG) or an isotonic saline nasal spray (IS), administered twice daily for two weeks. Consenting pts completed nasal symptom questionnaires at baseline and then weekly while on treatment. The number and percentage of pts experiencing improvements in their nasal symptoms 2 weeks after initiating the nasal spray, defined as symptoms moderately (2) or very much (3) better on a 7-point global impression of change score (ranging from scores of -3: very much worse, to 3: very much better), was estimated within and then between each randomized arm, using Fisher’s exact test (5% significance level). The estimated odds ratio was determined (95% confidence interval). After 2 weeks, pts initially randomized to IS were allowed to cross-over to RG and completed weekly surveys. Results: 106 pts consented to this study; 43 pts in the RG arm and 41 in the IS arm were evaluable for the primary endpoint. Pts had a mean age of 57.8 (SD 13.9). Demographic characteristics and baseline nasal symptoms were similar between arms. The most prominent baseline nasal symptoms were dryness (36%) and bleeding (35%). Of the 43 evaluable pts who received RG, 67.4% reported improved nasal symptoms, compared with 36.6% of the 41 pts who received IS (p=0.009; Table). On the global impression of change score, pts who received RG had a mean score of 1.93 (SD 1.16), compared to a mean score of 0.98 (SD 1.41) among pts who received IS. Adjusting for potential confounding factors, pts who received RG had a 4.56 odds of responding to the nasal spray, compared with those who received IS (p=0.005). There were no significant differences between pt responses based upon type of nasal symptoms, age, allergies, or gender. Adverse events were sparse and did not differ between arms. 34 pts crossed over to RG after week 2. Among the 29 pts who completed final surveys, 37% reported a response on IS, 79% reported a response on RG. Conclusions: Rose geranium in sesame oil nasal spray significantly improves nasal vestibulitis symptoms among patients undergoing chemotherapy. Clinical trial information: NCT04620369 . [Table: see text]