Search

Prediction of high-risk events amongst patients with mental disorders is critical for personalized interventions. We developed DeepBiomarker2 by leveraging deep learning and natural language processing to analyze lab tests, medication use, diagnosis, social determinants of health (SDoH) parameters, and psychotherapy for outcome prediction. To increase the model's interpretability, we further refined our contribution analysis to identify key features by scaling with a factor from a reference feature. We applied DeepBiomarker2 to analyze the EMR data of 38,807 patients from the University of Pittsburgh Medical Center diagnosed with post-traumatic stress disorder (PTSD) to determine their risk of developing alcohol and substance use disorder (ASUD). DeepBiomarker2 predicted whether a PTSD patient would have a diagnosis of ASUD within the following 3 months with an average c-statistic (receiver operating characteristic AUC) of 0.93 and average F1 score, precision, and recall of 0.880, 0.895, and 0.866 in the test sets, respectively. Our study found that the medications clindamycin, enalapril, penicillin, valacyclovir, Xarelto/rivaroxaban, moxifloxacin, and atropine and the SDoH parameters access to psychotherapy, living in zip codes with a high normalized vegetative index, Gini index, and low-income segregation may have potential to reduce the risk of ASUDs in PTSD. In conclusion, the integration of SDoH information, coupled with the refined feature contribution analysis, empowers DeepBiomarker2 to accurately predict ASUD risk. Moreover, the model can further identify potential indicators of increased risk along with medications with beneficial effects. [ABSTRACT FROM AUTHOR]

In order to find novel natural antioxidant peptides, the water hyacinth leaf protein was hydrolyzed by Protamex at optimum condition to prepared water hyacinth leaf protein hydrolysate (WHLPH). And antioxidant properties of WHLPH were evaluated dependent on several in vitro antioxidant systems, including superoxide anion radical-scavenging activity, ABTS cation radical-scavenging activity, reducing power, and metal chelating capacity. WHLPH showed 86.37% of superoxide anion radical-scavenging activity at 1.0 mg/mL, and 56.51% of ABTS cation radical-scavenging activity at 100 μg/mL. At 1.0 mg/mL, the reducing power of WHLPH was 0.92, and the metal chelating capacity was 68.54%. Subsequently, the WHLPH was subjected to consecutive isolation and purification by macroporous resin, gel filtration chromatography, and reverse-phase high-performance liquid chromatography, and two peptide fractions with higher radical-scavenging activity were acquired. Finally, the two peptide fractions were identified to be Phe-Phe-Glu and Leu-Phe, respectively, by matrix-assisted laser desorption/ionization time-of-flight mass spectrometry. Considering the two peptides' amino acid composition, their antioxidant properties may be due to the hydrophobic and/or aromatic acid residues in their sequences. The results indicated that the isolated antioxidant peptides from WHLPH would find widespread application in food, cosmetics, and pharmaceutical industry because of their high potency, safety, low cost and abundant source. [ABSTRACT FROM AUTHOR]