Utilizing patient-nurse verbal communication in building risk identification models: the missing critical data stream in home healthcare.

BACKGROUND: In the United States, over 12 000 home healthcare agencies annually serve 6+ million patients, mostly aged 65+ years with chronic conditions. One in three of these patients end up visiting emergency department (ED) or being hospitalized. Existing risk identification models based on electronic health record (EHR) data have suboptimal performance in detecting these high-risk patients. OBJECTIVES: To measure the added value of integrating audio-recorded home healthcare patient-nurse verbal communication into a risk identification model built on home healthcare EHR data and clinical notes. METHODS: This pilot study was conducted at one of the largest not-for-profit home healthcare agencies in the United States. We audio-recorded 126 patient-nurse encounters for 47 patients, out of which 8 patients experienced ED visits and hospitalization. The risk model was developed and tested iteratively using: (1) structured data from the Outcome and Assessment Information Set, (2) clinical notes, and (3) verbal communication features. We used various natural language processing methods to model the communication between patients and nurses. RESULTS: Using a Support Vector Machine classifier, trained on the most informative features from OASIS, clinical notes, and verbal communication, we achieved an AUC-ROC = 99.68 and an F1-score = 94.12. By integrating verbal communication into the risk models, the F-1 score improved by 26%. The analysis revealed patients at high risk tended to interact more with risk-associated cues, exhibit more "sadness" and "anxiety," and have extended periods of silence during conversation. CONCLUSION: This innovative study underscores the immense value of incorporating patient-nurse verbal communication in enhancing risk prediction models for hospitalizations and ED visits, suggesting the need for an evolved clinical workflow that integrates routine patient-nurse verbal communication recording into the medical record.

Bringing Artificial Intelligence to the operating room: edge computing for real-time surgical phase recognition.

BACKGROUND: Automation of surgical phase recognition is a key effort toward the development of Computer Vision (CV) algorithms, for workflow optimization and video-based assessment. CV is a form of Artificial Intelligence (AI) that allows interpretation of images through a deep learning (DL)-based algorithm. The improvements in Graphic Processing Unit (GPU) computing devices allow researchers to apply these algorithms for recognition of content in videos in real-time. Edge computing, where data is collected, analyzed, and acted upon in close proximity to the collection source, is essential meet the demands of workflow optimization by providing real-time algorithm application. We implemented a real-time phase recognition workflow and demonstrated its performance on 10 Robotic Inguinal Hernia Repairs (RIHR) to obtain phase predictions during the procedure. METHODS: Our phase recognition algorithm was developed with 211 videos of RIHR originally annotated into 14 surgical phases. Using these videos, a DL model with a ResNet-50 backbone was trained and validated to automatically recognize surgical phases. The model was deployed to a GPU, the Nvidia® Jetson Xavier™ NX edge computing device. RESULTS: This model was tested on 10 inguinal hernia repairs from four surgeons in real-time. The model was improved using post-recording processing methods such as phase merging into seven final phases (peritoneal scoring, mesh placement, preperitoneal dissection, reduction of hernia, out of body, peritoneal closure, and transitionary idle) and averaging of frames. Predictions were made once per second with a processing latency of approximately 250 ms. The accuracy of the real-time predictions ranged from 59.8 to 78.2% with an average accuracy of 68.7%. CONCLUSION: A real-time phase prediction of RIHR using a CV deep learning model was successfully implemented. This real-time CV phase segmentation system can be useful for monitoring surgical progress and be integrated into software to provide hospital workflow optimization.

Is the patient speaking or the nurse? Automatic speaker type identification in patient-nurse audio recordings.

OBJECTIVES: Patient-clinician communication provides valuable explicit and implicit information that may indicate adverse medical conditions and outcomes. However, practical and analytical approaches for audio-recording and analyzing this data stream remain underexplored. This study aimed to 1) analyze patients' and nurses' speech in audio-recorded verbal communication, and 2) develop machine learning (ML) classifiers to effectively differentiate between patient and nurse language. MATERIALS AND METHODS: Pilot studies were conducted at VNS Health, the largest not-for-profit home healthcare agency in the United States, to optimize audio-recording patient-nurse interactions. We recorded and transcribed 46 interactions, resulting in 3494 "utterances" that were annotated to identify the speaker. We employed natural language processing techniques to generate linguistic features and built various ML classifiers to distinguish between patient and nurse language at both individual and encounter levels. RESULTS: A support vector machine classifier trained on selected linguistic features from term frequency-inverse document frequency, Linguistic Inquiry and Word Count, Word2Vec, and Medical Concepts in the Unified Medical Language System achieved the highest performance with an AUC-ROC = 99.01 ± 1.97 and an F1-score = 96.82 ± 4.1. The analysis revealed patients' tendency to use informal language and keywords related to "religion," "home," and "money," while nurses utilized more complex sentences focusing on health-related matters and medical issues and were more likely to ask questions. CONCLUSION: The methods and analytical approach we developed to differentiate patient and nurse language is an important precursor for downstream tasks that aim to analyze patient speech to identify patients at risk of disease and negative health outcomes.

Surgical Phase Recognition in Inguinal Hernia Repair-AI-Based Confirmatory Baseline and Exploration of Competitive Models.

Video-recorded robotic-assisted surgeries allow the use of automated computer vision and artificial intelligence/deep learning methods for quality assessment and workflow analysis in surgical phase recognition. We considered a dataset of 209 videos of robotic-assisted laparoscopic inguinal hernia repair (RALIHR) collected from 8 surgeons, defined rigorous ground-truth annotation rules, then pre-processed and annotated the videos. We deployed seven deep learning models to establish the baseline accuracy for surgical phase recognition and explored four advanced architectures. For rapid execution of the studies, we initially engaged three dozen MS-level engineering students in a competitive classroom setting, followed by focused research. We unified the data processing pipeline in a confirmatory study, and explored a number of scenarios which differ in how the DL networks were trained and evaluated. For the scenario with 21 validation videos of all surgeons, the Video Swin Transformer model achieved ~0.85 validation accuracy, and the Perceiver IO model achieved ~0.84. Our studies affirm the necessity of close collaborative research between medical experts and engineers for developing automated surgical phase recognition models deployable in clinical settings.

An assessment of burden of hospital-acquired pneumonia among abdominal surgical patients in tertiary university hospital in Serbia: A matched nested case-control study.

Background: In the population of abdominal surgical patients hospital-acquired pneumonia (HAP) significantly increases morbidity and mortality. Patients and methods: Through regular hospital surveillance of patients who received abdominal operations, we identified postoperative HAP from 2007 to 2019. In an initial nested case-control study, every surgical patient with HAP was compared with three control patients without HAP. Control patients were matched to the cases by age, gender, the American Society of Anesthesiologists score, and type of surgical operation. Also, the patients with HAP, who died were compared with those who survived. Results: Multivariate logistic regression analysis (MLRA) revealed that other postoperative infections, length of intensive care unit stay, use of H2RA, use of PPI/ H2RA, multiple transfusion, and use of vancomycin in surgical prophylaxis were independent RFs for occurrence of HAP. Also, MLRA identified that age, lenght of hospital stay, use of mechanical ventilation and ceftriaxone in HAP therapy were indepedenttly associated with poor outcome of HAP. All Acinetobacter baumannii isolates were resistant to aminoglycoside antimicrobial agents and showed carbapenem resistance. The most frequently used antibiotics in patients with HAP and without HAP were vancomycin and metronidazole, respectively. Conclusion: Our study provided an insight into the burden of HAP in abdominal surgical patients, and highlighted several priority areas and targets for quality improvement.

Speech recognition can help evaluate shared decision making and predict medication adherence in primary care setting.

OBJECTIVE: Asthma is a common chronic illness affecting 19 million US adults. Inhaled corticosteroids are a safe and effective treatment for asthma, yet, medication adherence among patients remains poor. Shared decision-making, a patient activation strategy, can improve patient adherence to inhaled corticosteroids. This study aimed to explore whether audio-recorded patient-primary care provider encounters can be used to: 1. Evaluate the level of patient-perceived shared decision-making during the encounter, and 2. Predict levels of patient's inhaled corticosteroid adherence. MATERIALS AND METHODS: Shared decision-making and inhaled corticosteroid adherence were assessed using the SDM Questionnaire-9 and the Medication Adherence Report Scale for Asthma (MARS-A). Speech-to-text algorithms were used to automatically transcribe 80 audio-recorded encounters between primary care providers and asthmatic patients. Machine learning algorithms (Naive Bayes, Support Vector Machines, Decision Tree) were applied to achieve the study's predictive goals. RESULTS: The accuracy of automated speech-to-text transcription was relatively high (ROUGE F-score = .9). Machine learning algorithms achieved good predictive performance for shared decision-making (the highest F-score = .88 for the Naive Bayes) and inhaled corticosteroid adherence (the highest F-score = .87 for the Support Vector Machines). DISCUSSION: This was the first study that trained machine learning algorithms on a dataset of audio-recorded patient-primary care provider encounters to successfully evaluate the quality of SDM and predict patient inhaled corticosteroid adherence. CONCLUSION: Machine learning approaches can help primary care providers identify patients at risk for poor medication adherence and evaluate the quality of care by measuring levels of shared decision-making. Further work should explore the replicability of our results in larger samples and additional health domains.

Do nurses document all discussions of patient problems and nursing interventions in the electronic health record? A pilot study in home healthcare.

Objective: To assess the overlap of information between electronic health record (EHR) and patient-nurse verbal communication in home healthcare (HHC). Methods: Patient-nurse verbal communications during home visits were recorded between February 16, 2021 and September 2, 2021 with patients being served in an organization located in the Northeast United States. Twenty-two audio recordings for 15 patients were transcribed. To compare overlap of information, manual annotations of problems and interventions were made on transcriptions as well as information from EHR including structured data and clinical notes corresponding to HHC visits. Results: About 30% (1534/5118) of utterances (ie, spoken language preceding/following silence or a change of speaker) were identified as including problems or interventions. A total of 216 problems and 492 interventions were identified through verbal communication among all the patients in the study. Approximately 50.5% of the problems and 20.8% of the interventions discussed during the verbal communication were not documented in the EHR. Preliminary results showed that statistical differences between racial groups were observed in a comparison of problems and interventions. Discussion: This study was the first to investigate the extent that problems and interventions were mentioned in patient-nurse verbal communication during HHC visits and whether this information was documented in EHR. Our analysis identified gaps in information overlap and possible racial disparities. Conclusion: Our results highlight the value of analyzing communications between HHC patients and nurses. Future studies should explore ways to capture information in verbal communication using automated speech recognition.

Audio Recording Patient-Nurse Verbal Communications in Home Health Care Settings: Pilot Feasibility and Usability Study.

BACKGROUND: Patients' spontaneous speech can act as a biomarker for identifying pathological entities, such as mental illness. Despite this potential, audio recording patients' spontaneous speech is not part of clinical workflows, and health care organizations often do not have dedicated policies regarding the audio recording of clinical encounters. No previous studies have investigated the best practical approach for integrating audio recording of patient-clinician encounters into clinical workflows, particularly in the home health care (HHC) setting. OBJECTIVE: This study aimed to evaluate the functionality and usability of several audio-recording devices for the audio recording of patient-nurse verbal communications in the HHC settings and elicit HHC stakeholder (patients and nurses) perspectives about the facilitators of and barriers to integrating audio recordings into clinical workflows. METHODS: This study was conducted at a large urban HHC agency located in New York, United States. We evaluated the usability and functionality of 7 audio-recording devices in a laboratory (controlled) setting. A total of 3 devices-Saramonic Blink500, Sony ICD-TX6, and Black Vox 365-were further evaluated in a clinical setting (patients' homes) by HHC nurses who completed the System Usability Scale questionnaire and participated in a short, structured interview to elicit feedback about each device. We also evaluated the accuracy of the automatic transcription of audio-recorded encounters for the 3 devices using the Amazon Web Service Transcribe. Word error rate was used to measure the accuracy of automated speech transcription. To understand the facilitators of and barriers to integrating audio recording of encounters into clinical workflows, we conducted semistructured interviews with 3 HHC nurses and 10 HHC patients. Thematic analysis was used to analyze the transcribed interviews. RESULTS: Saramonic Blink500 received the best overall evaluation score. The System Usability Scale score and word error rate for Saramonic Blink500 were 65% and 26%, respectively, and nurses found it easier to approach patients using this device than with the other 2 devices. Overall, patients found the process of audio recording to be satisfactory and convenient, with minimal impact on their communication with nurses. Although, in general, nurses also found the process easy to learn and satisfactory, they suggested that the audio recording of HHC encounters can affect their communication patterns. In addition, nurses were not aware of the potential to use audio-recorded encounters to improve health care services. Nurses also indicated that they would need to involve their managers to determine how audio recordings could be integrated into their clinical workflows and for any ongoing use of audio recordings during patient care management. CONCLUSIONS: This study established the feasibility of audio recording HHC patient-nurse encounters. Training HHC nurses about the importance of the audio-recording process and the support of clinical managers are essential factors for successful implementation.

Risk factors for Clostridium difficile infection in surgical patients hospitalized in a tertiary hospital in Belgrade, Serbia: a case-control study.

BACKGROUND: The objective of this study was to investigate independent risk factors (RFs) connected with healthcare-associated (HA) Clostridium difficile infection (CDI) in surgical patients, its frequency per surgical wards and in-hospital-mortality at a single hospital. METHODS: Risk factors for the infection were prospectively assessed among surgical patients with laboratory confirmed HA CDI and compared with a control group without HA CDI. RESULTS: The overall incidence rate of HA CDI was 2.6 per 10000 patient-days. Significant independent RFs for HA CDI were the use of carbapenems (P = 0.007, OR: 10.62, 95% CI: 1.93-58.4), the admission to intensive care unit (P = 0.004, OR:3.00, 95% CI:1.41-6.40), and the administration of 3rd generation cephalosporins (P = 0.014, OR:2.27, 95% CI:1.18-4.39). Patients with HA CDI had significantly higher in-hospital mortality compared to controls (P: 0.007; OR: 8.95; 95% CI: 1.84-43.43). CONCLUSIONS: CDI is an important HA infection in population of surgical patients and this study emphasizes the importance of the wise use of antibiotics, and other infection control strategies in order to prevent HA CDI, and to decrease the incidence and in-hospital mortality rate.

C-reactive protein in drainage fluid as a predictor of anastomotic leakage after elective colorectal resection.

BACKGROUND/AIM: C-reactive protein (CRP) is considered to be an indicator of postoperative complications in. abdominal surgery. The aim of this study was to determine the significance of serial measurement of CRP in drainage fluid in the detection of anastomotic leakage (AL) in patients with colorectal resection. METHODS: CRP values in serum and drainage fluid, respectively, were measured on the first, third, fifth, and seventh postoperative day (POD) in 150 patients with colorectal resection and primary anastomosis. The values obtained were compared between the groups of patient without complications of surgical treatment and those with AL. RESULTS: Clinically evident AL was observed in 15 patients--in two (4.2%) patients with left colonic surgery, and 13 (12.6%) patients with colorectal anastomosis. Mean values of CRP were higher in the patients with AL than in the patients without complications, both in serum and drainage fluid, with the most significant differences recorded on the PODs 5 and 7 (p < 0.001). Correlation analysis showed a positive correlation between serum and drainage fluid CRP levels in both groups of patients. Serum and drainage fluid CRP values on the PODs 5 and 7 are most important in the detection of AL. In 80% of patients with CRP values in the drainage fluid of 53 mg/L for the POD 5 and 42 mg/L for the POD 7 AL was observed. The method specificity was 77% for the POD 5, and 83% for the POD 7. All the patients with CRP values in drainage fluid above 108 mg/L on the POD 5 and 93 mg/L on the POD 7 had AL. CONCLUSION: Serial measurement of CRP in drainage fluid can reliably be used in the detection of AL in patients with colorectal resection. The most significant values obtained on the PODs 5 and 7 were positively correlated with the values registered in

Diagnostic value of serial measurement of C-reactive protein in serum and matrix metalloproteinase-9 in drainage fluid in the detection of infectious complications and anastomotic leakage in patients with colorectal resection.

BACKGROUND/AIM: Postoperative infectious complications are one of the most important problems in surgical treatment of colorectal cancer (CRC), being present in up to 40% of patients. The aim of this paper was to establish the significance of serial measurement of C-reactive protein (CRP) in serum and matrix metalloproteinase-9 (MMP-9) in drainage fluid for the detection of infectious complications and anastomotic leakage (AL) in patients with colorectal resection. METHODS: CRP and MMP-9 values in serum and drainage fluid, respectively, were measured on the first, third, fifth, and seventh postoperative day (POD) in 150 patients with colorectal resection and primary anastomosis. The values obtained were compared between the patients without complicatons and those with surgical site and remote infections and AL. RESULTS: Surgical site infections (SSIs) were observed in 41 (27.3%), and remote infections in 10 (6.7%) patients. Clinically evident AL was observed in 15 (10/6) patients. In 82% of the patients with SSIs, serum CRP value on POD 5 exceeded 82 mg/L, with 81% specificity. AL was reported in 85% and 92% of the patients on PODs 5 and 7, respectively, with CRP values of 77 mg/L and 90 mg/L, respectively. The specificity was 77% for POD 5 and 88% for POD 7. All the patients with CRP values exceeding 139 mg/L on POD 5 had some of SSIs and/or AL. The mean values of MMP-9 were not statistically different between the group without complications (n = 99) and the group with AL (n = 15). CONCLUSION: Serial measurement of CRP is recommended for screening of infectious complications of colorectal resection. Patients with CRP values above 139 mg/L on POD 5 cannot be discharged from hospital, and require an intensive search for infectious complications, particularly AL. MMP-9 measurement in drainage fluid is not relevant in the detection of AL in patients with colorectal resection.

Giant esophageal fibrovascular polyp with clinical behaviour of inflammatory pseudotumor: a case report and the literature review.

INTRODUCTION: Esophageal fibrovascular polyps are rare, benign, intraluminal, submucosal tumor-like lesions, characterized by pedunculated masses which can demonstrate enormous growth. The most frequent symptoms are dysphagia, vomiting and weight loss. Fibrovascular polyps with long stalks can regurgitate into the airways and cause asphyxia. Esophageal inflammatory pseudotumor is extremely rare lesion accompanied with various systemic manifestations as fever, anemia and thrombocytosis. CASE REPORT: We presented a 29-year-old man complaining of a long-lasting fever and dysphagia. He was found to have huge pedunculated submucosal tumor of esophagus, surgically completely resected. Histopathological examination showed that this giant tumor, 24 x 9 x 6 cm, was a fibrovascular polyp. The postoperative course was uneventful. The preoperative fever, anemia and thrombocytosis disappeared and did not recur in the postoperative course. CONCLUSION: We reported a patient with giant esophageal pedunculated tumor with clinical manifestations of inflammatory pseudotumor and histopathological picture of fibrovascular polyp, that we have not found described in the literature before.

Procalcitonin and BISAP score versus C-reactive protein and APACHE II score in early assessment of severity and outcome of acute pancreatitis.

BACKGROUND/AIM: Early assessment of severity and continuous monitoring of patients are the key factors for adequate treatment of acute pancreatitis (AP). The aim of this study was to determine the value of procalcitonin (PCT) and Bedside Index for Severity in Acute Pancreatitis (BISAP) scoring system as prognostic markers in early stages of AP with comparison to other established indicators such as C-reactive protein (CRP) and Acute Physiology and Chronic Health Evaluation (APACHE) II score. METHODS: This prospective study included 51 patients (29 with severe AP). In the first 24 h of admission in all patients the APACHE II score and BISAP score, CRP and PCT serum concentrations were determined. The values of PCT serum concentrations and BISAP score were compared with values of CRP serum concentrations and APACHE II score, in relation to the severity and outcome of the disease. RESULTS: Values of PCT, CRP, BISAP score and APACHE II score, measured at 24 h of admission, were significantly elevated in patients with severe form of the disease. In predicting severity of AP at 24 h of admission, sensitivity and specificity of the BISAP score were 74% and 59%, respectively, APACHE II score 89% and 69%, respectively, CRP 75% and 86%, respectively, and PCT 86% and 63%, respectively. It was found that PCT is highly significant predictor of the disease outcome (p < 0,001). CONCLUSION: In early assessment of AP severity, PCT has better predictive value than CRP, and similar to the APACHE II score. APACHE II score is a stronger predictor of the disease severity than BISAP score. PCT is a good predictor of AP outcome.

Thyroidectomy with LigaSure.

PURPOSE: A new method for ensuring hemostasis during thyroid surgery has recently been introduced. This technique, electrothermal (LigaSure) and ultrasound blood vessel sealing, is still experimental. The aim of the present study was to evaluate the applications and efficacy of LigaSure by analyzing the duration of the surgery and the rate of complications of the surgical procedure. METHODS: A total of 23 patients who underwent the LigaSure operation (n(LS) group) were analyzed in a prospective nonrandomized/partly randomized clinical study, and were compared with patients who underwent treatment using the conventional (ligature) surgical technique. RESULTS: At our institutions, 187 patients were treated surgically for thyroid disease in 2006, and 23 of these patients were treated using LigaSure. The complication rate in the patients treated with LigaSure (n(LS): 4.3%) was lower than those who received conventional ligature surgery. However, given the small number of patients, this difference was not statistically significant (retrospective group n(1): 10.7%; nonrandomized group n(2): 9.8%; and randomized group n(3): 9.1%). The length of surgery in the LigaSure group (n(LS) = 65 ± 3 min) was significantly shorter (P < 0.001) compared with both nonrandomized (n(2) = 71 ± 6 min) and randomized (n(3) = 70 ± 4 min) patients who received a conventional ligature. CONCLUSIONS: The application of LigaSure using meticulous surgical technique provides a new option for a safe thyroidectomy. Moreover, the duration of the LigaSure procedure is significantly shorter, and there are fewer complications as compared with the classic surgical thyroidectomy technique.

[Detection of free cancer cells in peritoneal cavity in patients surgically treated for gastric adenocarcinoma].

BACKGROUND/AIM: Peritoneal metastasis is a leading cause of therapeutic failure after an operative treatment of patients with gastric adenocarcinoma. Free cancer cells might induce or indicate an early peritoneal seeding with a subsequent peritoneal metastasis. The aim of this study was to determine the frequency of the presence of free cancer cells in the peritoneal cavity in the patients surgically treated for gastric adenocarcinoma, and its relation to certain clinical, operative and pathohistological paramethers. METHODS: Inside a period from April 2000, and April 2004, the total of 100 patients underwent intraoperative peritoneal lavage for cytological examination. Immediately after the laparotomy, 200 ml physiologic saline, heated to 37 degrees C, was introduced into the abdominal cavity, mannualy dispersed and collected from the region around the gastric tumor and the pouch of Douglas. The nucleated cell layer was smeared on four glass slides for every patient and dyed with May-Grünwald-Giemsa stain. The cytological findings were defined as positive or negative according to the presence of cancer cells. The frequency of positive cytological findings was compared to the location and the diameter of the cancer, pathohistological type of carcinoma, pathohistological stage of the disease, lymph node and the liver and/or peritoneal metastases and the type of surgical procedure. RESULTS: Free cancer cells were found in 24 (24%) of the patients, while in 76 (76%) of them cytological findings were negative. A statistically highly significant difference (p < or = 0.001) in the frequency of positive cytological finding was found between the groups of patients with and without cancer invasion of serosa, with cancer diameters > 5 cm and < or = 5 cm, in the stage of disease I, II and III, IV, with macroscopically present and without metastases, with re section and D2 lymphadenectomy and palliative procedure. Free cancer cells were statistically more frequently (p < or = 0.05) detected in the patients with lymph nodes metastases comparing to the patients with out lymph nodes involvement. The results of the univariate analysis showed that the cancer diameter > 5 cm, tumor invasion of serosa, pathohistological stage of the disease III and IV and macroscopically visible metastases were the most important risk factors for the free cancer cells detection. CONCLUSION: Peritoneal lavage cytology was shown to be a useful tool for the detection of the group of patients with greatest risk of peritoneal dissemination. The frequency of positive cytological findings was highly associated with the diameter of the tumor and the cancer invasion of serosa. Cytological examination of peritoneal lavage fluid improved the accuracy of staging and selection of patients who might have benefit from neoadjuvant chemotherapy.

[Early complications following radical surgical treatment of patients with gastric adenocarcinoma].

BACKGROUND/AIM: Surgical treatment of patients with gastric adenocarcinoma means the total excision of a tumor and the pathways of its spreading with the risk of operational complications as low as possible. The aim of this study was to evaluate the type and frequency of early postoperative complications and mortality after a radical surgical treatment of patients with gastric adenocarcinoma. METHODS: Complication rates and postoperative mortality were studied in 70 consecutive patients in whom a radical surgical procedure, gastrectomy (total or subtotal) with D2 lymphadenectomy, was performed. In the early postoperative period, the frequencies of general and specific complications were detected. The frequencies of complications were compared between the groups of patients according to the defined clinical, operative and pathohistological paramethers. RESULTS: The overall morbidity and mortality rates were 27.14% and 5.71%, respectively Pancreatic fistula in five, and pleural effusion in three patients were the most frequently registered complications. Three of four deaths occured in patients older than 70 years, with the stage III and IV of the disease, and in all of them total gastrectomy with splenectomy was performed. A statistically significant difference (p < 0.05) in complication rates was found between the groups of patients with and without splenectomy and with the tumors > 5 cm and < or = 5 cm. CONCLUSION: Radical surgical treatment of patients with gastric adenocarcinoma might be done with an acceptable morbidity and mortality if it is performed by the surgeons with the experience in D2 lymphadenectomy technique. A diameter of the tumor > 5 cm, and splenectomy, and/or splenopancreatectomy are the most important risk factors for the occurrence of complications and modifications of D2 lymphadenectomy technique with limited indications for splenic and/or pancreas resection can improve treatment results. An individual approach and the appropriate selection of the surgical procedure are necessary in patients older than 70 years.