Search

Pancreatic ductal adenocarcinoma (PDAC) has been left behind in the evolution of personalized medicine. Predictive markers of response to therapy are lacking in PDAC despite various histological and transcriptional classification schemes. We report an artificial intelligence (AI) approach to histologic feature examination that extracts a signature predictive of disease-specific survival (DSS) in patients with PDAC receiving adjuvant gemcitabine. We demonstrate that this AI-generated histologic signature is associated with outcomes following adjuvant gemcitabine, while three previously developed transcriptomic classification systems are not (n= 47). We externally validate this signature in an independent cohort of patients treated with adjuvant gemcitabine (n= 46). Finally, we demonstrate that the signature does not stratify survival outcomes in a third cohort of untreated patients (n= 161), suggesting that the signature is specifically predictive of treatment-related outcomes but is not generally prognostic. This imaging analysis pipeline has promise in the development of actionable markers in other clinical settings where few biomarkers currently exist.

e16295 Background: Adjuvant chemotherapy improves survival following resection of pancreatic ductal adenocarcinoma (PDAC). A modified fluorouracil/irinotecan/oxaliplatin regimen (mFOLFIRINOX) has demonstrated improved disease free survival and overall survival, though gemcitabine-based monotherapy and gemcitabine plus capecitabine are alternatives in less fit patients. Though there are several proposed biomarkers to guide treatment decisions (GATA6, hENT1, and GemPred), no biomarker is used to guide treatment selection in clinical practice. Consequently, we sought to develop an artificial intelligence-derived signature of features from digital images of routine histopathology specimens that could identify patients susceptible to routine chemotherapeutic agents. Methods: 139 whole-slide digitized histological slides corresponding to 102 resected PDAC tumors from TCGA-PAAD were used in this study. This dataset corresponded to patients that had received either gemcitabine-backbone or 5 FU-backbone chemotherapy as their first-line adjuvant treatment. We extracted nuclei images from tissue regions using segmentation models and computed geometric features of these nuclei which we then correlated with Disease Specific Survival (DSS) in order to construct a signature associated with treatment benefit. This signature was compared against two board certified pathologists using the grade of the digital slides images to classify patients into above or below average DSS buckets. Results: Among quantitative geometric features, a set of area and ellipse features describing nuclei geometry correlated most with response to gemcitabine (R̃0.4). The cox proportional hazards model using these geometric nuclei features was found to be predictive of response to gemcitabine and achieved a C-index (95% CI) of 0.69 (0.58, 0.79). The pathologist-based baseline model for above and below average DSS had a median DSS of 443 and 461 days respectively. Using the average expected lifetime as the threshold, the model divides patients receiving gemcitabine into two histological subtypes with median DSS of 586 and 394 days respectively (p < 0.05). The model appeared specific to gemcitabine. Among patients receiving 5-FU (n = 10) there was no statistical significance in median DSS between the subtypes and a c-index of 0.63 (0.27, 1.0). Conclusions: An artificial intelligence approach utilizing only routine histopathology can identify features that correlate with treatment outcomes in PDAC with classification performance (c-index:0.69) superior to the validated AJCC treatment prediction tool (0.59).

BACKGROUND The coronavirus disease 2019 (COVID-19) heralded an unprecedented increase in telemedicine utilization. OBJECTIVE Assess patient satisfaction with telemedicine during COVID-19 METHODS Telemedicine visit data were gathered from two separate institutions (Stanford Health Care (Stanford) and the Hospital for Special Surgery (HSS)). Patient satisfaction data from HSS were captured from a Press-Ganey questionnaire between April 19, 2020 and December 12, 2020, while the Stanford data was taken from a novel survey instrument that was distributed to all patients between June 22, 2020 and November 1, 2020. There were 60,550 telemedicine visits across 93 services at Stanford, each linked with a post-visit survey. At HSS, there were 66,349 total telemedicine visits with 7,348 randomly linked with a post-visit survey. The percentage of respondents who reported the highest possible likelihood to recommend score (“LTR top box percentage”) and mean overall visit scores were recorded. RESULTS Over 19 weeks, the LTR top box percentage at Stanford increased from 69.6% to 74.0% (p=.0002), and HSS showed no significant change across 35 weeks (p=.7100). LTR trend stability at Stanford was observed across 11 medical, four surgical, and five oncological services (p >.05). In the multivariable model, the use of a cell phone (aOR: 1.18; 95% CI: 1.12–1.23) and tablet (aOR: 1.15; 95% CI: 1.07–1.23) were associated with higher overall scores, while visits with interrupted connections (aOR: 0.49; 95% CI: 0.42–0.57) or help required to connect (aOR: 0.49; 95% CI: 0.42–0.56) predicted lower patient satisfaction. CONCLUSIONS We present the largest published description of patient satisfaction with telemedicine. We found high satisfaction with telemedicine encounters across multiple measures, and we identified a number of important telemedicine-specific factors that predict increased overall visit score. These include the use of cell phones or tablets, phone reminders, and connecting before the visit was scheduled to begin. Visits with poor connectivity, extended wait times, or difficulty being seen, examined, or understood by the provider were linked with reduced odds of high scores. Our results suggest that attention to connectivity and audio/visual definition will help optimize patient satisfaction with telemedicine encounters in the future. CLINICALTRIAL n/a