Objective: Our study was aimed to construct a predictive model to advance ovarian cancer diagnosis by machine learning. Methods: A retrospective analysis of patients with pelvic/adnexal/ovarian mass was performed. Potential features related to ovarian cancer were obtained as many as possible.The optimal machine learning algorithm was selected among six candidates through 5-fold cross validation. Top 20 features having the most powerful predictive significance were ranked by Shapley Additive Interpretation (Shap) method. Clinical validation was further performed to confirm whether our model could advance diagnosis of ovarian cancer. Results: A total of 9,799 patients were collected. The inclusion criteria included age >18 years old, the first diagnosis being pelvic/adnexal/ovarian mass of undetermined significance, and pathological report indispensable. Four hundred and thirty-eight dimensional features were obtained after filtration. LightGBM showed the best performance with accuracy 88%.Among the top 20 features, 55% belonged to laboratory test report, 35% came from imaging examination report, and 10% were attributed to basic demographics and main symptom.Age, CA125, and risk of ovarian malignancy algorithm were the top three. Our predictive model performed stably in testing and clinical validation datasets, and was found to advance the diagnosis of ovarian cancer about 17 days before clinical pathological examination. Conclusion LightGBM was the optimal algorithm for our predictive model with accuracy of 88%. Laboratory test and imaging examination played essential roles in diagnosing ovarian cancer. Our model could advance the diagnosis of ovarian cancer before clinical pathological examination.

BACKGROUND: This study aimed to explore the effect of a nanomaterial-based miR-320a inhibitor sustained release system in trauma-induced osteonecrosis of the femoral head (TIONFH). METHODS: The miR-320a inhibitor-loaded polyethylene glycol (PEG)- Poly(lactic-co-glycolic acid) (PLGA)- Poly-L-lysine (PLL) nanoparticles were constructed using the double emulsion method. The TIONFH rabbit model was established to observe the effects of miR-320a inhibitor nanoparticles in vivo. Hematoxylin–eosin staining and microcomputed tomography scanning were used for bone morphology analysis. Bone marrow mesenchymal stem cells (BMSCs), derived from TIONFH rabbits, were used for in vitro experiments. Cell viability was determined using the MTT assay. RESULTS: High expression of miR-320a inhibited the osteogenic differentiation capacity of BMSCs in vitro by inhibiting the expression of the osteoblastic differentiation markers ALP and RUNX2. MiR-320a inhibitor-loaded PEG-PLGA-PLL nanoparticles were constructed with a mean loading efficiency of 1.414 ± 0.160%, and a mean encapsulation efficiency of 93.45 ± 1.24%, which released 50% of the loaded miR-320a inhibitor at day 12 and 80% on day 18. Then, inhibitor release entered the plateau. After treatment with the miR-320a inhibitor nanoparticle, the empty lacunae were decreased in the femoral head tissue of TIONFH rabbits, and the osteoblast surface/bone surface (Ob.S/BS), osteoblast number/bone perimeter (Ob.N/B.Pm), bone volume fraction, and bone mineral density increased. Additionally, the expression of osteogenic markers RUNX2 and ALP was significantly elevated in the TIONFH rabbit model. CONCLUSION The miR-320a inhibitor-loaded PEG-PLGA-PLL nanoparticle sustained drug release system significantly contributed to bone regeneration in the TIONFH rabbit model, which might be a promising strategy for the treatment of TIONFH.

OBJECTIVE: To evaluate the effectiveness of neurovascular staghorn flap for repairing defects in fingertips. METHODS: Between August 2019 and October 2021, a total of 15 fingertips defects were repaired with neurovascular staghorn flap. There were 8 males and 7 females with an average age of 44 years (range, 28-65 years). The causes of injury included 8 cases of machine crush injury, 4 cases of heavy object crush injury, and 3 cases of cutting injury. There were 1 case of thumb, 5 cases of index finger, 6 cases of middle finger, 2 cases of ring finger, and 1 case of little finger. There were 12 cases in emergency, and 3 cases with finger tip necrosis after trauma suture. Bone and tendon exposed in all cases. The range of fingertip defect was 1.2 cm×0.8 cm to 1.8 cm×1.5 cm, and the range of skin flap was 2.0 cm×1.5 cm to 2.5 cm×2.0 cm. The donor site was sutured directly. RESULTS: All flaps survived without infection or necrosis, and the incisions healed by first intention. All patients were followed up 6-12 months, with an average of 10 months. At last follow-up, the appearance of the flap was satisfactory, the wear resistance was good, the color was similar to the skin of the finger pulp, and there was no swelling; the two-point discrimination of the flap was 3-5 mm. One patient had linear scar contracture on the palmar side with slight limitation of flexion and extension, which had little effect on the function; the other patients had no obvious scar contracture, good flexion and extension of the fingers, and no dysfunction. The finger function was evaluated according to the total range of motion (TAM) system of the Hand Surgery Society of Chinese Medical Association, and excellent results were obtained in 13 cases and good results in 2 cases. CONCLUSION The neurovascular staghorn flap is a simple and reliable method to repair fingertip defect. The flap has a good fit with the wound without wasting skin. The appearance and function of the finger are satisfactory after operation.
Adult ; Female ; Humans ; Male ; Cicatrix/surgery* ; Contracture/surgery* ; Crush Injuries/surgery* ; Finger Injuries/surgery* ; Plastic Surgery Procedures ; Skin Transplantation/methods* ; Soft Tissue Injuries/surgery* ; Treatment Outcome ; Middle Aged ; Aged

Objective To observe the difference of vascular endothelial growth factor (VEGF) and myeloperoxidase (MPO) between diabetic and non-diabetic patients with maintenance hemodialysis (MHD),and to explore whether it was associated with duration of hemodialysis.Methods A total of 120 patients with MHD were divided into diabetic group (40 cases) and non-diabetic group (80 cases) according to the primary disease.The blood samples from the patients before dialysis were selected to test the serum VEGF and plasma MPO and other indicators.The blood samples from April 2012 to March 2013 were labeled diabetic group 1(40 cases) and non-diabetic group 1 (80 cases).The blood samples from April 2013 to March 2014 were labeled diabetic group 2 (40 cases) and non-diabetic group 2 (80 cases).Results The serum VEGF and plasma MPO levels were (74.63 ± 47.43) ng/L,(300.63 ± 235.37) μ g/L in diabetic group 1,and (63.69 ± 43.23) ng/L,(275.35 ± 216.32) μ g/L in non-diabetic group 1,and there were significant differences between two groups (P ＜ 0.05).The serum VEGF and plasma MPO levels were (83.32 ± 40.38) ng/L,(414.12 ±265.52) μg/L in diabetic group 2,and (70.89 ±39.74) rig/L,(289.45 ±202.85) μg/L in non-diabetic group 2,and there were significant differences between two groups (P ＜ 0.05).The correlation analysis showed that VEGF was positively correlated with MPO in diabetic group 1 and diabetic group 2 (r =0.632 and 0.763,P ＜ 0.05),and VEGF was positively correlated with MPO in non-diabetic group 1 and non-diabetic group 2 (r =0.610 and 0.713,P ＜ 0.05).Conclusions Compared with those in non-diabetic MHD patients,VEGF and MPO levels are significandy higher in diabetic MHD patients.In non-diabetic MHD patients and diabetic MHD patients,VEGF and MPO levels will rise gradually with duration of hemodialysis.The expressions of VEGF and MPO are associated with each other.