Integrating AI-driven Wearable Technology in Oncology Decision Making: A Narrative Review.

BACKGROUND: Clinical decision-making in oncology is a complex process influenced by numerous disease-related factors, patient demographics, and logistical considerations. With the advent of Artificial Intelligence (AI), precision medicine is undergoing a shift towards more precise and personalized care. Wearable device technology complements this paradigm shift by offering continuous monitoring of patient vitals, facilitating early intervention, and improving treatment adherence. The integration of these technologies promises to enhance the quality of oncological care, making it more responsive and tailored to individual patient needs, thereby enabling wider implementation of such applications in the clinical setting. SUMMARY: This review article addresses the integration of wearable devices and AI in oncology, exploring their role in patient monitoring, treatment optimization, and research advancement along with an overview of completed clinical trials and utility in different aspects. The vast applications have been exemplified using several studies and all the clinical trials completed till date have been summarized in table 2. Additionally, we discuss challenges in implementation, regulatory considerations, and future perspectives for leveraging these technologies to enhance cancer care and radically changing the global health sector. KEY MESSAGES: AI is transforming cancer care by enhancing diagnostic, prognostic, and treatment planning tools, thus making precision medicine more effective. Wearable technology facilitates continuous, non-invasive monitoring, improving patient engagement and adherence to treatment protocols. The combined use of AI and wearables aids in monitoring patient activity, assessing frailty, predicting chemotherapy tolerance, detecting biomarkers, and managing treatment adherence. Despite these advancements, challenges, such as data security, privacy, and the need for standardized devices persist. In the foreseeable future, wearable technology can hold significant potential to revolutionize personalized oncology care, empowering clinicians to deliver comprehensive and tailored treatments alongside standard therapy.

Retrospective application of WHO reporting system for lung cytopathology with assessment of risk of malignancy.

INTRODUCTION: The recently introduced World Health Organization (WHO) Reporting System for Lung Cytopathology presents 5 diagnostic categories with corresponding risk of malignancy (ROM) and management protocols. This study uses the system to categorize our institutional respiratory tract cytology specimens, evaluating ROM and diagnostic accuracy for each category. MATERIALS AND METHODS: In a retrospective analysis (May 2020 to August 2021), the following respiratory cytology specimens were classified based on the WHO categories: bronchoalveolar lavage (BAL), bronchial wash/bronchial brushings (BB/BW), endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA), fine-needle aspiration cytology (FNAC), sputum, biopsy imprint (BI), and endotracheal wash. Exclusions comprised pleural effusions and EBUS-TBNA from mediastinal and hilar lymph nodes. Correlation of cytologic and histopathologic diagnoses was performed to assess ROM collectively and individually. RESULTS: A total of 1518 respiratory samples (BAL [968], BW/BB [380], EBUS-TBNA [42], FNAC [32], sputum [80], BI [11] and endotracheal wash [5]) of 1410 patients were screened, of which 522 cases (34.3%) had histopathologic correlation. One hundred forty-one cases (9.3%) were Insufficient/Inadequate/Non-Diagnostic (ND), 1221 (80.4%) were Benign (B), 3 (0.2%) were Atypical (A), 32 (2.1%) were Suspicious for malignancy (SM) and 121 (8.0%) were Malignant (M). The estimated ROM for each category was 49.2% for ND, 13.3% for B, 66.6% for A, 81.5% for SM and 92.7% for M. FNAC and EBUS-TBNA exhibited the highest sensitivity (100%) compared with BW/BB (66.3%). Specificity ranged from 96.8% to 100% across the samples, while diagnostic accuracy varied from 58.8% to 100%. CONCLUSIONS: Application of the WHO reporting system enhances standardized terminology, aiding clinicians in informed decision-making and improving patient care through accurate risk assessment of malignancy.

'Plasma first' approach for detecting epidermal growth factor receptor mutation in advanced non-small cell lung carcinoma.

INTRODUCTION: The treatment approach for recently diagnosed advanced non-small cell lung cancer (NSCLC) with EGFR mutations primarily relies on confirming the tissue diagnosis as non-squamous NSCLC. This routine clinical practice of tissue diagnosis imposes several barriers and delays in turnaround time (TAT) for biomarker testing, significantly delaying the time to treatment. The objective of this study is to investigate the 'plasma first' approach for detection of EGFR mutation in advanced stage treatment naïve NSCLC patients. METHODS: We prospectively collected blood samples of treatment naïve patients with clinical and radiological suspicion of advanced stage NSCLC prior to obtaining tissue biopsy. Plasma cfDNA was tested for EGFR mutation using two different methods. We compared the sensitivity and TAT of liquid biopsy with tissue biopsy. RESULTS: In total, we analyzed plasma cell-free DNA (cfDNA) of 236 patients suspected of having advanced NSCLC for EGFR mutations. We observed a notably shorter turnaround time (TAT) of 3 days, which was significantly quicker compared to the 12-day TAT for tissue biopsy (p < 0.05). The ddPCR method had a sensitivity of 82.8%, which was higher than 66.34% sensitivity of ARMS-PCR. The current study also highlights that there is no significant difference in the clinical outcome of the patients whether treated based on liquid biopsy only or tissue biopsy (median progression-free survival of 11.56 vs. 11.9 months; p = 0.94). CONCLUSIONS: Utilizing a 'plasma first' strategy, given its shorter turnaround time, strong positive concordance and comparable outcomes to tissue biopsy, emerges as a highly specific and reliable method for detecting EGFR mutations in advanced-stage NSCLC.

Pleural effusion supernatant: a reliable resource for cell-free DNA in molecular testing of lung cancer.

INTRODUCTION: DNA extracted from malignant pleural effusion (PE) sediments is the traditional source of tumor DNA for predictive biomarker molecular testing (MT). Few recent studies have proposed the utility of cell-free DNA (cfDNA) extracted from effusion cytology centrifuged supernatants (CCS) in MT. The aim of this study was to assess the feasibility and utility of molecular testing on cfDNA extracted from PE CCS in lung cancer patients. MATERIALS AND METHODS: The study was of prospective design. All PE CCS were collected and stored. Subsequently, in patients confirmed as primary lung adenocarcinoma (LUAD) and where patient matched effusion sediment/tissue biopsy/plasma was being tested for EGFR mutations, cfDNA extraction and EGFR MT by real-time polymerase chain reaction (qPCR) were performed. Custom panel targeted next-generation sequencing (NGS) (Ion Torrent; Thermo Fisher, Carlsbad, CA) was also performed wherever feasible. RESULTS: Out of 299 PE CCS collected, 20 CCS samples were included in the study. Concordant EGFR mutations were detected in pleural effusion CCS of 10 of 11 (91%) EGFR mutant cases as per qPCR performed on the matched sediment DNA (n = 8), lung biopsy (n = 2), and plasma (n = 1) samples. In 1 positive sample, CCS detected additional EGFR T790M mutation. Among 10 CCS samples also tested by NGS, additional EGFR mutations missed by qPCR were picked up in 2 (2 of 10). Success of mutation detection in CCS cfDNA did not correlate with cfDNA quantity or tumor fraction in sediment. CONCLUSIONS: cfDNA from effusion CCS is a reliable and independent source of tumor DNA highly amenable for MT and complement results from other tumor DNA sources for comprehensive mutation profiling in LUAD patients.

Identification of CT Features to Differentiate Pulmonary Sarcoma from Carcinoma.

Background Primary lung sarcoma (PLS) differs in management protocols and prognosis from the more common primary lung carcinoma (PLC). It becomes imperative to raise a high index of suspicion on radiological and pathological features. Purpose The aim of this study is to highlight the variable imaging appearances of PLS compared with PLC, which impacts radiologic - pathologic correlation. Materials and Methods A retrospective observational study of 68 patients with biopsy-proven lung tumors who underwent baseline imaging at our tertiary care cancer hospital was conducted between January 2018 and March 2022. The patient details and imaging parameters of the mass on contrast-enhanced computed tomography (CECT) were recorded and analyzed for patients with PLS and compared with PLC. Follow-up imaging was available in 9/12 PLS and 52/56 PLC patients. Results Among 12 patients with PLS, 5 patients had synovial sarcoma on histopathology. PLS was seen in patients with a mean age of 40.8 years; the mass showed a mean size of 13.2 cm, lower lobe (75%), parahilar (75%), hilar involvement (41.7%), oval shape (41.7%), circumscribed (25%) or lobulated (75%) margins, lower mean postcontrast attenuation of 57.3 HU, fissural extension (50%), calcification (50%), and no organ metastasis other than to the lung. PLC (56 patients) was seen in the elderly with a mean age of 54.8 years; the mass showed a mean size of 5.7 cm, irregular shape (83.9%), spiculated margins (73.2%), higher mean postcontrast attenuation (77.3 HU), chest wall infiltration (30.4%), and distant metastasis (58.9%) at baseline imaging. A statistically significant difference ( p < 0.05) was seen between sarcoma and carcinoma in the mean age, size, site, shape, margins, postcontrast attenuation, presence of calcifications, fissural extension, and distant metastasis. Conclusion The distinct imaging features of sarcoma help in differentiating it from carcinoma. This can also be used to corroborate with histopathology to achieve concordance and guide clinicians on further approach.

SMART-ESAS: Smartphone Monitoring and Assessment in Real Time of Edmonton Symptom Assessment System Scores for Patients With Cancer.

PURPOSE: Serial patient-reported outcome (PRO) measurements in clinical practice are associated with a better quality of life and survival. Recording electronic PROs using smartphones is an efficient way to implement this. We aimed to assess the feasibility of the electronically filled Edmonton Symptom Assessment System (e-ESAS) scale in the lower-middle-income country (LMIC) setting. METHODS: Baseline clinical features and conventional paper-based ESAS (p-ESAS) were collected in newly diagnosed patients with solid organ tumors. Text message link was sent to these patients for filling e-ESAS. ESAS was categorized into physical, psychological, and total symptom domains. Scores were divided into none to mild (0-3) and moderate to severe (4-10). Intraclass correlation coefficients (ICCs) were used to determine the correlation between p-ESAS and e-ESAS. Multivariable logistic regression was used to identify independent factors affecting symptom burden. RESULTS: Of 1,160 participants who filled out p-ESAS, 595 completed both e-ESAS and p-ESAS questionnaires and were included in the final analysis. Moderate to severe physical, psychological, and total symptom scores were seen in 39.8%, 40%, and 39% of participants. Tiredness and anxiety were the most common physical and psychological symptoms, respectively. ICCs between the p-ESAS and e-ESAS varied between 0.75 and 0.9. Total symptom scores were independently predicted by metastatic disease (odds ratio [OR], 1.83; 95% CI, 1.26 to 2.67; P = .001) and a higher level of education (OR, 0.42; 95% CI, 0.25 to 0.72; P = .001). CONCLUSION: Paper-based and electronically filled ESASs have good intraobserver reliability across individual symptoms and domain scores in a representative cohort at a tertiary care institute in the LMIC. This may help us incorporate e-ESAS in routine clinical care in the real-world setting with financial, infrastructural, and manpower limitations.

Topical Diclofenac for Prevention of Capecitabine-Associated Hand-Foot Syndrome: A Double-Blind Randomized Controlled Trial.

PURPOSE: Hand-foot syndrome (HFS) is a dose-limiting side effect of capecitabine. Celecoxib prevents HFS by inhibiting cyclooxygenase-2 (COX-2) that is upregulated because of the underlying associated inflammation. However, systemic side effects of celecoxib have limited routine prescription. Topical diclofenac inhibits COX-2 locally with minimal risk of systemic adverse events. Therefore, we conducted this study to assess the efficacy of topical diclofenac in the prevention of capecitabine-induced HFS. METHODS: In this single-site phase III randomized double-blind trial, we enrolled patients with breast or GI cancer who were planned to receive capecitabine-based treatment. Participants were randomly assigned in a 1:1 ratio to receive topical diclofenac or placebo gel for 12 weeks or until the development of HFS, whichever occurred earlier. The primary end point was the incidence of grade 2 or 3 HFS (Common Terminology Criteria for Adverse Events version 5), which was compared between the two groups using simple logistic regression. RESULTS: In total, 264 patients were randomly assigned to receive topical diclofenac gel (n = 131) or placebo (n = 133). Grade 2 or 3 HFS was observed in 3.8% of participants in the diclofenac group compared with 15.0% in the placebo group (absolute difference, 11.2%; 95% CI, 4.3 to 18.1; P = .003). Grade 1-3 HFS was lower in the diclofenac group than in the placebo group (6.1% v 18.1%; absolute risk difference, 11.9%; 95% CI, 4.1 to 19.6). Capecitabine dose reductions because of HFS were less frequent in the diclofenac group (3.8%) than in the placebo group (13.5%; absolute risk difference, 9.7%; 95% CI, 3.0 to 16.4). CONCLUSION: Topical diclofenac prevented HFS in patients receiving capecitabine. This trial supports the use of topical diclofenac to prevent capecitabine-associated HFS.