The efficacy of the National Surgical Quality Improvement Program surgical risk calculator in head and neck surgery: A meta-analysis.

BACKGROUND: The National Surgical Quality Improvement Program surgical risk calculator (SRC) estimates the risk for postoperative complications. This meta-analysis assesses the efficacy of the SRC in the field of head and neck surgery. METHODS: A systematic review identified studies comparing the SRC's predictions to observed outcomes following head and neck surgeries. Predictive accuracy was assessed using receiver operating characteristic curves (AUCs) and Brier scoring. RESULTS: Nine studies totaling 1774 patients were included. The SRC underpredicted the risk of all outcomes (including any complication [observed (ob) = 35.9%, predicted (pr) = 21.8%] and serious complication [ob = 28.7%, pr = 17.0%]) except mortality (ob = 0.37%, pr = 1.55%). The observed length of stay was more than twice the predicted length (p < 0.02). Discrimination was acceptable for postoperative pneumonia (AUC = 0.778) and urinary tract infection (AUC = 0.782) only. Predictive accuracy was low for all outcomes (Brier scores ≥0.01) and comparable for patients with and without free-flap reconstructions. CONCLUSION: The SRC is an ineffective instrument for predicting outcomes in head and neck surgery.

Psychosocial Status and Self-Perception in Patients with Cleft Lip and/or Palate.

OBJECTIVE: To describe how the psychosocial status of patients with cleft lip and/or palate (CL/P) relates to patient-reported outcomes (PROs). DESIGN: Cross-sectional retrospective chart review. SETTING: Tertiary care pediatric hospital. PATIENTS/PARTICIPANTS: Patients aged 8 to 29 years attending cleft team evaluations during a 1-year period. MAIN OUTCOME MEASURES: CLEFT-Q. RESULTS: Patients (N = 158) with isolated or syndromic CL/P and mean age 13.4 ± 3.0 years were included. Fifteen (9%) patients had siblings who also had CL/P. Of 104 patients who met with the team psychologist, psychosocial concerns were identified in 49 (47%) patients, including 25 (24%) with Attention-Deficit/Hyperactivity Disorder or behavior concerns, 28 (27%) with anxiety, and 14 (13%) with depression or mood concerns. Younger age and having siblings with cleft were associated with better PROs, while psychosocial concerns were associated with worse PROs on Speech, Psychosocial, and Face Appearance scales. CONCLUSIONS: Patient perception of cleft outcomes is linked to psychosocial factors.

The fragility index: how robust are the outcomes of head and neck cancer randomised, controlled trials?

BACKGROUND: The fragility index represents the minimum number of patients required to convert an outcome from statistically significant to insignificant. This report assesses the fragility index of head and neck cancer randomised, controlled trials. METHODS: Studies were extracted from PubMed/Medline, Scopus, Embase and Cochrane databases. RESULTS: Overall, 123 randomised, controlled trials were included. The sample size and fragility index medians (interquartile ranges) were 103 (56-213) and 2 (0-5), respectively. The fragility index exceeded the number of patients lost to follow up in 42.3 per cent (n = 52) of studies. A higher fragility index correlated with higher sample size (r = 0.514, p < 0.001), number of events (r = 0.449, p < 0.001) and statistical significance via p-value (r = -0.367, p < 0.001). CONCLUSION: Head and neck cancer randomised, controlled trials demonstrated low fragility index values, in which statistically significant results could be nullified by altering the outcomes of just two patients, on average. Future head and neck oncology randomised, controlled trials should report the fragility index in order to provide insight into statistical robustness.

Long-Term Patient-Reported Outcomes in Internationally Adopted Children with Cleft Lip and Palate.

OBJECTIVE: To compare patient-reported outcomes (PROs) in internationally adopted patients with cleft lip and palate to those in non-adopted peers. DESIGN: Cross-sectional study. SETTING: Multidisciplinary cleft team at tertiary care hospital. PATIENTS: Patients aged ≥ 8 with cleft lip and palate attending routine cleft team evaluations September 2021 - September 2022. MAIN OUTCOME MEASURE: CLEFT-Q PRO scores. RESULTS: Sixty-four internationally adopted patients and 113 non-adopted patients with a mean age of 13 years were included. Compared to non-adopted peers, adopted patients demonstrated worse satisfaction with face appearance (mean 59 vs. 66, p = .044), speech function (mean 69 vs. 78, p = .005), and speech distress (mean 80 vs. 84, p = .032). No significant differences were observed on the nose, nostrils, teeth, lips, lip scar, jaws, psychological function, or social function scales (p > .05). Objective clinical evaluation corroborated these findings, with adopted patients demonstrating worse Pittsburgh Weighted Speech scores (mean 3.0 vs 1.9, p = .027) and greater incidence of articulation errors (64% vs 46%, p = .021). No significant differences were observed in rates of mood, anxiety, or behavior concerns identified on psychosocial assessment (p = .764). Among adopted patients, undergoing palatoplasty prior to adoption was associated with worse satisfaction with speech, appearance, school, and social function (p < .05). CONCLUSIONS: Patient-reported outcomes among internationally adopted adolescents and young adults with cleft lip and palate show slightly lower satisfaction with facial appearance and speech but otherwise demonstrate similar results to non-adopted peers on most appearance and psychosocial measures. PRO data correlated well with objective speech assessment and did not portend worse psychosocial function.

Artificial intelligence in mammographic phenotyping of breast cancer risk: a narrative review.

BACKGROUND: Improved breast cancer risk assessment models are needed to enable personalized screening strategies that achieve better harm-to-benefit ratio based on earlier detection and better breast cancer outcomes than existing screening guidelines. Computational mammographic phenotypes have demonstrated a promising role in breast cancer risk prediction. With the recent exponential growth of computational efficiency, the artificial intelligence (AI) revolution, driven by the introduction of deep learning, has expanded the utility of imaging in predictive models. Consequently, AI-based imaging-derived data has led to some of the most promising tools for precision breast cancer screening. MAIN BODY: This review aims to synthesize the current state-of-the-art applications of AI in mammographic phenotyping of breast cancer risk. We discuss the fundamentals of AI and explore the computing advancements that have made AI-based image analysis essential in refining breast cancer risk assessment. Specifically, we discuss the use of data derived from digital mammography as well as digital breast tomosynthesis. Different aspects of breast cancer risk assessment are targeted including (a) robust and reproducible evaluations of breast density, a well-established breast cancer risk factor, (b) assessment of a woman's inherent breast cancer risk, and (c) identification of women who are likely to be diagnosed with breast cancers after a negative or routine screen due to masking or the rapid and aggressive growth of a tumor. Lastly, we discuss AI challenges unique to the computational analysis of mammographic imaging as well as future directions for this promising research field. CONCLUSIONS: We provide a useful reference for AI researchers investigating image-based breast cancer risk assessment while indicating key priorities and challenges that, if properly addressed, could accelerate the implementation of AI-assisted risk stratification to future refine and individualize breast cancer screening strategies.

Stratification by Tumor Grade Groups in a Holistic Evaluation of Machine Learning for Brain Tumor Segmentation.

Accurate and consistent segmentation plays an important role in the diagnosis, treatment planning, and monitoring of both High Grade Glioma (HGG), including Glioblastoma Multiforme (GBM), and Low Grade Glioma (LGG). Accuracy of segmentation can be affected by the imaging presentation of glioma, which greatly varies between the two tumor grade groups. In recent years, researchers have used Machine Learning (ML) to segment tumor rapidly and consistently, as compared to manual segmentation. However, existing ML validation relies heavily on computing summary statistics and rarely tests the generalizability of an algorithm on clinically heterogeneous data. In this work, our goal is to investigate how to holistically evaluate the performance of ML algorithms on a brain tumor segmentation task. We address the need for rigorous evaluation of ML algorithms and present four axes of model evaluation-diagnostic performance, model confidence, robustness, and data quality. We perform a comprehensive evaluation of a glioma segmentation ML algorithm by stratifying data by specific tumor grade groups (GBM and LGG) and evaluate these algorithms on each of the four axes. The main takeaways of our work are-(1) ML algorithms need to be evaluated on out-of-distribution data to assess generalizability, reflective of tumor heterogeneity. (2) Segmentation metrics alone are limited to evaluate the errors made by ML algorithms and their describe their consequences. (3) Adoption of tools in other domains such as robustness (adversarial attacks) and model uncertainty (prediction intervals) lead to a more comprehensive performance evaluation. Such a holistic evaluation framework could shed light on an algorithm's clinical utility and help it evolve into a more clinically valuable tool.