Can Artificial Intelligence Be Applied to Diagnose Intracerebral Hemorrhage under the Background of the Fourth Industrial Revolution? A Novel Systemic Review and Meta-Analysis
Zhao K, Zhao Q, Zhou P, Liu B, Zhang Q, Yang M
International journal of clinical practice. 2022;2022:9430097
AIM: We intended to provide the clinical evidence that artificial intelligence (AI) could be used to assist doctors in the diagnosis of intracerebral hemorrhage (ICH). METHODS Studies published in 2021 were identified after the literature search of PubMed, Embase, and Cochrane. Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) was used to perform the quality assessment of studies. Data extraction of diagnosis effect included accuracy (ACC), sensitivity (SEN), specificity (SPE), positive predictive value (PPV), negative predictive value (NPV), area under curve (AUC), and Dice scores (Dices). The pooled effect with its 95% confidence interval (95%CI) was calculated by the random effects model. I-Square (I (2)) was used to test heterogeneity. To check the stability of the overall results, sensitivity analysis was conducted by recalculating the pooled effect of the remaining studies after omitting the study with the highest quality or the random effects model was switched to the fixed effects model. Funnel plot was used to evaluate publication bias. To reduce heterogeneity, recalculating the pooled effect of the remaining studies after omitting the study with the lowest quality or perform subgroup analysis. RESULTS Twenty-five diagnostic tests of ICH via AI and doctors with overall high quality were included. Pooled ACC, SEN, SPE, PPV, NPV, AUC, and Dices were 0.88 (0.83∼0.93), 0.85 (0.81∼0.89), 0.90 (0.88∼0.92), 0.80 (0.75∼0.85), 0.93 (0.91∼0.95), 0.84 (0.80∼0.89), and 0.90 (0.85∼0.95), respectively. There was no publication bias. All of results were stable as revealed by sensitivity analysis and were accordant as outcomes via subgroups analysis. CONCLUSION Under the background of the fourth industrial revolution, AI might be an effective and efficient tool to assist doctors in the clinical diagnosis of ICH.
Meta-analysis of platelet-rich plasma therapy for anal fistula
Luo Q, Zhou P, Chang S
Journal of cosmetic dermatology. 2022
OBJECTIVE To systematically evaluate the efficacy of platelet-rich plasma (PRP) in treating anal fistula. METHODS PubMed, EMBASE, and Cochrane Library databases were systematically searched for randomized controlled studies (RCTs) and case-control studies published before June 2021 on evaluating the efficacy of platelet-rich plasma (PRP) in treating anal fistula. References of the journals were manually searched for relevant studies. Literature search, screening, data extraction, and bias assessment were carried out by two researcher independently. Stata13.0 and RevMan 5.3 software were used for statistical analysis of the cure rate and recurrence rate of anal fistula. RESULTS A total of 6 case-control studies and 3 RCTs involving 289 patients were included. Meta-analysis showed that the pooled cure rate of all studies was 65% (95% CI 0.53-0.77), p = 0.000, and the pooled recurrence rate of all studies was 12% (95% CI 0.08-0.17). CONCLUSION Platelet-rich plasma is safe and effective in treating anal fistula and should be promoted and further studied in clinical practice.
Comparison of effect of norepinephrine and terlipressin on patients with ARDS combined with septic shock: a prospective single-blind randomized controlled trial
Chen Z, Zhou P, Lu Y, Yang C
Zhonghua Wei Zhong Bing Ji Jiu Yi Xue. 2017;29((2)):111-116.
OBJECTIVE To approach the effect of different vasopressor on hemodynamics, volume responsiveness, fluid volume balance, renal function and prognosis in patients with acute respiratory distress syndrome (ARDS) complicated with septic shock. METHODS A prospective single-blind randomized controlled trial was conducted. ARDS patients with septic shock admitted to the Department of Critical Care Medicine of Jiangxi Provincial People's Hospital from January 1st, 2015 to May 1st, 2016 were enrolled. The patients satisfied ARDS Berlin diagnostic criteria, over 15 years old, needing vasopressor after fluid resuscitation were enrolled. The patients were divided into norepinephrine group (NE group) and terlipressin group (TP group) by randomise number table derived by computer. Patients in TP group were given terlipressin (0.01-0.04 U/min) with an intravenous pump, while those of NE group were given norepinephrine (> 1 mug/min) with an intravenous pump, and the target mean arterial pressure (MAP) was maintained at 65-75 mmHg (1 mmHg = 0.133 kPa). Hemodynamics and extravascular lung water index (EVLWI) were monitored by pulse indicator continuous cardiac output (PiCCO). The volume responsiveness of patient was evaluated by passive leg raising (PLR) test, and cardiac index (CI) change (DeltaCI ≥ 10%) served as positive volume responsiveness. The differences in hemodynamics, EVLWI, oxygenation index (OI), lactate clearance rate (LCR), rate of positive volume responsiveness, urinary output, fluid volume balance, renal function, and prognostic indicators were compared between the two groups. RESULTS Fifty-seven patients with ARDS complicated with septic shock were enrolled, with 26 patients in NE group, and 31 patients in TP group, the baseline data in both groups was balanced with comparability. Compare with NE group, 48-hour and 72-hour heart rate (HR) in TP group was significantly slowed (bpm: 82.1+/-6.8 vs. 87.6+/-7.4, 81.3+/-6.1 vs. 85.6+/-8.3, both P < 0.05), 72-hour central venous pressure (CVP) was significantly decreased (mmHg: 9.4+/-2.6 vs. 10.9+/-3.0, P < 0.05), but no significant difference was found in HR, MAP, CVP, CI, EVLWI, OI and LCR at other time points between the two groups. 48-hour and 72-hour positive volume responsiveness rate in TP group were significantly increased as compared with those of NE group (74.2% vs. 46.2%, 64.5% vs. 38.5%, both P < 0.05), urinary output on the 2nd day (mL/24 h: 2 342.8+/-704.1 vs. 1 944.6+/-684.3) and fluid volume balance (mL: -319.7+/-54.8 vs. -169.6+/-27.2) were significantly decreased (both P < 0.05). There was no significant difference in positive volume responsiveness rate, urine output, fluid volume balance, and the level of serum creatinine at other time points between the two groups. There was no statistically significant difference in the following features between TP group and NE group: duration of mechanical ventilation (days: 8.41+/-2.97 vs. 9.67+/-3.56), length of intensive care unit (ICU) stay (days: 12.84+/-4.47 vs. 14.77+/-5.01), total length of hospital stay (days: 19.34+/-7.37 vs. 21.07+/-8.41), and 28-day mortality (29.0% vs. 30.8%, all P > 0.05). CONCLUSIONS Compared with norepinephrine, terlipressin for ARDS patients with septic shock is more conducive to restrict fluid load, improve the renal perfusion and increase urine output. However, in both groups there was no significant difference in the efficiency of stabilizing hemodynamics, shortening the duration of mechanical ventilation, reducing ICU or hospital days and decreasing 28-day mortality.
Acute normovolemic hemodilution combined with controlled hypotension in patients undergoing liver tumorectomy
Yao XH, Wang B, Xiao ZK, Zhou P, Chen CY, Qing ZH
Nan Fang Yi Ke Da Xue Xue Bao [Journal of Southern Medical University]. 2006;26((6):):828-30.
OBJECTIVE To evaluate the effects of acute normovolemic hemodilution (ANH) combined with controlled hypotension on reducing heterogeneous transfusion and safety during liver tumorectomy. METHODS Thirty patients undergoing elective liver tumorectomy were randomly divided into 3 groups (10 each), namely ANH group (group A), ANH combined with controlled hypotension group (group B) and control group (group C). All the patients were anesthetized via endotracheal intubation. Before the operation, ANH was performed in groups A and B after anesthesia induction, and controlled hypotension was initiated in group B during tumorectomy. Blood transfusion and fluid infusion were carried out routinely in group C. Hb and Hct were measured before operation, after ANH, and immediately, 1 day and 7 days after the operation. The difference in intraoperative blood loss and heterogeneous blood transfusion volume in the 3 groups was observed. RESULTS In group A, heterogeneous blood transfusion was avoided in 6 cases and but given in the other cases for an average of 400 ml. In group C, every patient received heterogeneous blood transfusion (664. 8-/+248. 1 ml), but none of the patients received heterogeneous blood in group B. The difference in transfusion volume between the 3 groups was significant (P<0. 01). Hemodynamics was basically stable during operation in the 3 groups. CONCLUSION ANH combined with controlled hypotension is safe and effective for decreasing and even avoiding homologous blood transfusion in liver tumorectomy.