Search for: All records

Early diagnosis of Alzheimer’s disease plays a pivotal role in patient care and clinical trials. In this study, we have developed a new approach based on 3D deep convolutional neural networks to accurately differentiate mild Alzheimer’s disease dementia from mild cognitive impairment and cognitively normal individuals using structural MRIs. For comparison, we have built a reference model based on the volumes and thickness of previously reported brain regions that are known to be implicated in disease progression. We validate both models on an internal held-out cohort from The Alzheimer's Disease Neuroimaging Initiative (ADNI) and on an external independent cohort from The National Alzheimer's Coordinating Center (NACC). The deep-learning model is accurate, achieved an area-under-the-curve (AUC) of 85.12 when distinguishing between cognitive normal subjects and subjects with either MCI or mild Alzheimer’s dementia. In the more challenging task of detecting MCI, it achieves an AUC of 62.45. It is also significantly faster than the volume/thickness model in which the volumes and thickness need to be extracted beforehand. The model can also be used to forecast progression: subjects with mild cognitive impairment misclassified as having mild Alzheimer’s disease dementia by the model were faster to progress to dementia over time. An analysis of the features learned by the proposed model shows that it relies on a wide range of regions associated with Alzheimer's disease. These findings suggest that deep neural networks can automatically learn to identify imaging biomarkers that are predictive of Alzheimer's disease, and leverage them to achieve accurate early detection of the disease.

During the coronavirus disease 2019 (COVID-19) pandemic, rapid and accurate triage of patients at the emergency department is critical to inform decision-making. We propose a data-driven approach for automatic prediction of deterioration risk using a deep neural network that learns from chest X-ray images and a gradient boosting model that learns from routine clinical variables. Our AI prognosis system, trained using data from 3661 patients, achieves an area under the receiver operating characteristic curve (AUC) of 0.786 (95% CI: 0.745–0.830) when predicting deterioration within 96 hours. The deep neural network extracts informative areas of chest X-ray images to assist clinicians in interpreting the predictions and performs comparably to two radiologists in a reader study. In order to verify performance in a real clinical setting, we silently deployed a preliminary version of the deep neural network at New York University Langone Health during the first wave of the pandemic, which produced accurate predictions in real-time. In summary, our findings demonstrate the potential of the proposed system for assisting front-line physicians in the triage of COVID-19 patients.

Delivering stem/progenitor cells via a degradable synthetic membrane to devitalized allogenic tissue graft surfaces presents a promising allograft‐mediated tissue regeneration strategy. However, balancing degradability and bioactivity of the synthetic membrane with physical characteristics demanded for successful clinical translation is challenging. Here, well‐integrated composites of hydroxyapatite (HA) and amphiphilic poly(lactide‐co‐glycolide)‐b‐poly(ethylene glycol)‐b‐poly(lactide‐co‐glycolide) (PELGA) with tunable degradation rates are designed that stiffen upon hydration and exhibit excellent shape recovery ability at body temperature for efficiently delivering skeletal progenitor cells around bone grafts. Unlike conventional degradable polymers that weaken upon wetting, these amphiphilic composites stiffen upon hydration as a result of enhanced polyethylene glycol (PEG) crystallization. HA‐PELGA composite membranes support the attachment, proliferation, and osteogenesis of rat periosteum‐derived cells in vitro, as well as the facile transfer of confluent cell sheets of green fluorescent protein‐labeled bone marrow stromal cells. With efficient shape memory behaviors around physiological temperature, the composite membranes can be programmed with a permanent tubular configuration, deformed into a flat temporary shape desired for cell seeding/cell sheet transfer, and triggered to wrap around a femoral bone allograft upon 37 °C saline rinse and subsequently stiffen. These properties combined make electrospun HA‐PELGA promising smart synthetic periosteal membranes for augmenting allograft healing.