Participant flow diagrams for health equity in AI.

Selection bias can arise through many aspects of a study, including recruitment, inclusion/exclusion criteria, input-level exclusion and outcome-level exclusion, and often reflects the underrepresentation of populations historically disadvantaged in medical research. The effects of selection bias can be further amplified when non-representative samples are used in artificial intelligence (AI) and machine learning (ML) applications to construct clinical algorithms. Building on the "Data Cards" initiative for transparency in AI research, we advocate for the addition of a participant flow diagram for AI studies detailing relevant sociodemographic and/or clinical characteristics of excluded participants across study phases, with the goal of identifying potential algorithmic biases before their clinical implementation. We include both a model for this flow diagram as well as a brief case study explaining how it could be implemented in practice. Through standardized reporting of participant flow diagrams, we aim to better identify potential inequities embedded in AI applications, facilitating more reliable and equitable clinical algorithms.

Multi-institutional analysis of treatment modalities in basal ganglia and thalamic germinoma.

BACKGROUND: Central nervous system (CNS) germinomas are treatment-sensitive tumors with excellent survival outcomes. Current treatment strategies combine chemotherapy with radiotherapy (RT) in order to reduce the field and dose of RT. Germinomas originating in the basal ganglia/thalamus (BGTGs) have proven challenging to treat given their rarity and poorly defined imaging characteristics. Craniospinal (CSI), whole brain (WBI), whole ventricle (WVI), and focal RT have all been utilized; however, the best treatment strategy remains unclear. METHODS: Retrospective multi-institutional analysis has been conducted across 18 institutions in four countries. RESULTS: For 43 cases of nonmetastatic BGTGs, the 5- and 10-year event-free survivals (EFS) were 85.8% and 81.0%, respectively, while the 5- and 10-year overall survivals (OS) were 100% and 95.5%, respectively (one patient fatality from unrelated cause). Median RT doses were as follows: CSI: 2250 cGy/cGy(RBE) (1980-2400); WBI: 2340 cGy/cGy(RBE) (1800-3000); WVI: 2340 cGy/cGy(RBE) (1800-2550); focal: 3600 cGy (3060-5400). Thirty-eight patients (90.5%) received chemotherapy. There was no statistically significant difference in the EFS based on initial field extent (p = .84). Nevertheless, no relapses were reported in patients who received CSI or WBI. Chemotherapy alone had significantly inferior EFS compared to combined therapy (p = .0092), but patients were salvageable with RT. CONCLUSION: Patients with BGTGs have excellent outcomes and RT proved to be an integral component of the treatment plan. This group of patients should be included in future prospective clinical trials and the best RT field should be investigated further.

Assessing Mobility in Patients With Glioblastoma Using Digital Phenotyping-Piloting the Digital Assessment in Neuro-Oncology.

BACKGROUND AND OBJECTIVES: Digital phenotyping (DP) enables objective measurements of patient behavior and may be a useful tool in assessments of quality-of-life and functional status in neuro-oncology patients. We aimed to identify trends in mobility among patients with glioblastoma (GBM) using DP. METHODS: A total of 15 patients with GBM enrolled in a DP study were included. The Beiwe application was used to passively collect patient smartphone global positioning system data during the study period. We estimated step count, time spent at home, total distance traveled, and number of places visited in the preoperative, immediate postoperative, and late postoperative periods. Mobility trends for patients with GBM after surgery were calculated by using local regression and were compared with preoperative values and with values derived from a nonoperative spine disease group. RESULTS: One month postoperatively, median values for time spent at home and number of locations visited by patients with GBM decreased by 1.48 h and 2.79 locations, respectively. Two months postoperatively, these values further decreased by 0.38 h and 1.17 locations, respectively. Compared with the nonoperative spine group, values for time spent at home and the number of locations visited by patients with GBM 1 month postoperatively were less than control values by 0.71 h and 2.79 locations, respectively. Two months postoperatively, time spent at home for patients with GBM was higher by 1.21 h and locations visited were less than nonoperative spine group values by 1.17. Immediate postoperative values for distance traveled, maximum distance from home, and radius of gyration for patients with GBM increased by 0.346 km, 2.24 km, and 1.814 km, respectively, compared with preoperative values. CONCLUSIONS: :Trends in patients with GBM mobility throughout treatment were quantified through the use of DP in this study. DP has the potential to quantify patient behavior and recovery objectively and with minimal patient burden.

Autoencoder-based multimodal prediction of non-small cell lung cancer survival.

The ability to accurately predict non-small cell lung cancer (NSCLC) patient survival is crucial for informing physician decision-making, and the increasing availability of multi-omics data offers the promise of enhancing prognosis predictions. We present a multimodal integration approach that leverages microRNA, mRNA, DNA methylation, long non-coding RNA (lncRNA) and clinical data to predict NSCLC survival and identify patient subtypes, utilizing denoising autoencoders for data compression and integration. Survival performance for patients with lung adenocarcinoma (LUAD) and squamous cell carcinoma (LUSC) was compared across modality combinations and data integration methods. Using The Cancer Genome Atlas data, our results demonstrate that survival prediction models combining multiple modalities outperform single modality models. The highest performance was achieved with a combination of only two modalities, lncRNA and clinical, at concordance indices (C-indices) of 0.69 ± 0.03 for LUAD and 0.62 ± 0.03 for LUSC. Models utilizing all five modalities achieved mean C-indices of 0.67 ± 0.04 and 0.63 ± 0.02 for LUAD and LUSC, respectively, while the best individual modality performance reached C-indices of 0.64 ± 0.03 for LUAD and 0.59 ± 0.03 for LUSC. Analysis of biological differences revealed two distinct survival subtypes with over 900 differentially expressed transcripts.

An artificial neural network for automated behavioral state classification in rats.

Accurate behavioral state classification is critical for many research applications. Researchers typically rely upon manual identification of behavioral state through visual inspection of electrophysiological signals, but this approach is time intensive and subject to low inter-rater reliability. To overcome these limitations, a diverse set of algorithmic approaches have been put forth to automate the classification process. Recently, novel machine learning approaches have been detailed that produce rapid and highly accurate classifications. These approaches however, are often computationally expensive, require significant expertise to implement, and/or require proprietary software that limits broader adoption. Here we detail a novel artificial neural network that uses electrophysiological features to automatically classify behavioral state in rats with high accuracy, sensitivity, and specificity. Common parameters of interest to sleep scientists, including state-dependent power spectra and homeostatic non-REM slow wave activity, did not significantly differ when using this automated classifier as compared to manual scoring. Flexible options enable researchers to further increase classification accuracy through manual rescoring of a small subset of time intervals with low model prediction certainty or further decrease researcher time by generalizing trained networks across multiple recording days. The algorithm is fully open-source and coded within a popular, and freely available, software platform to increase access to this research tool and provide additional flexibility for future researchers. In sum, we have developed a readily implementable, efficient, and effective approach for automated behavioral state classification in rats.

Pilot study of smartphone-based health outcome tracking (OurBrainBank) for glioblastoma patients.

BACKGROUND: Patients with glioblastoma (GBM) typically have high symptom burden impacting on quality of life. Mobile apps may help patients track their condition and provide real-time data to clinicians and researchers. We developed a health outcome reporting app (OurBrainBank [OBB]) for GBM patients. Our primary aim was to explore the feasibility and take-up of OBB. Secondary aims were to examine the potential value of OBB app usage for patient well-being and clinical research. METHODS: Participants (or caregiver proxies) completed baseline surveys and tracked 10 health outcomes over time. We evaluated usage and engagement, and relationships between clinical/sociodemographic variables and OBB use. Participant satisfaction and feedback were described. To demonstrate usefulness for clinical research, health outcomes were compared with corresponding items on a validated measure (EQ-5D-5L). RESULTS: From March 2018 to February 2021, OBB was downloaded by 630 individuals, with 15 207 sets of 10 health outcomes submitted. Higher engagement was associated with being a patient rather than a caregiver (χ 2(2,568) = 28.6, P < .001), having higher self-rated health scores at baseline (F(2,460) = 4.8, P = .009) and more previous experience with mobile apps (χ 2(2,585) = 9.6, P = .008). Among the 66 participants who completed a feedback survey, most found health outcome tracking useful (average 7/10), and would recommend the app to others (average 8.4/10). The OBB health outcomes mapped onto corresponding EQ-5D-5L items, suggesting their validity. CONCLUSIONS: OBB can efficiently collect GBM patients' health outcomes. The long-term goal is to create a unique database of thousands of deidentified GBM patients, with open access to qualified researchers.