1
|
Gracheva AS, Kashatnikova DA, Redkin IV, Zakharchenko VE, Kuzovlev AN, Salnikova LE. Genetics and Traumatic Brain Injury: Findings from an Exome-Based Study of a 50-Patient Case Series. Curr Issues Mol Biol 2024; 46:10351-10368. [PMID: 39329968 PMCID: PMC11430351 DOI: 10.3390/cimb46090616] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2024] [Revised: 09/14/2024] [Accepted: 09/16/2024] [Indexed: 09/28/2024] Open
Abstract
Traumatic brain injury (TBI) is the leading cause of global mortality and morbidity. Because TBI is accident-related, the role of genetics in predisposing to TBI has been largely unexplored. However, the likelihood of injury may not be entirely random and may be associated with certain physical and mental characteristics. In this study, we analyzed the exomes of 50 patients undergoing rehabilitation after TBI. Patients were divided into three groups according to rehabilitation outcome: improvement, no change, and deterioration/death. We focused on rare, potentially functional missense and high-impact variants in genes intolerant to these variants. The concordant results from the three independent groups of patients allowed for the suggestion of the existence of a genetic predisposition to TBI, associated with rare functional variations in intolerant genes, with a prevalent dominant mode of inheritance and neurological manifestations in the genetic phenotypes according to the OMIM database. Forty-four of the 50 patients had one or more rare, potentially deleterious variants in one or more neurological genes. Comparison of these results with those of a 50-sampled matched non-TBI cohort revealed significant differences: P = 2.6 × 10-3, OR = 4.89 (1.77-13.47). There were no differences in the distribution of the genes of interest between the TBI patient groups. Our exploratory study provides new insights into the impact of genetics on TBI risk and is the first to address potential genetic susceptibility to TBI.
Collapse
Affiliation(s)
- Alesya S Gracheva
- The Department of Population Genetics, Vavilov Institute of General Genetics, Russian Academy of Sciences, 119991 Moscow, Russia
- The Laboratory of Clinical Pathophysiology of Critical Conditions, Federal Research and Clinical Center of Intensive Care Medicine and Rehabilitology, 107031 Moscow, Russia
| | - Darya A Kashatnikova
- The Laboratory of Ecological Genetics, Vavilov Institute of General Genetics, Russian Academy of Sciences, 119991 Moscow, Russia
- The Laboratory of Molecular Pathophysiology, Lopukhin Federal Research and Clinical Center of Physical-Chemical Medicine of Federal Medical Biological Agency, 119435 Moscow, Russia
| | - Ivan V Redkin
- The Laboratory of Organoprotection in Critical Conditions, Federal Research and Clinical Center of Intensive Care Medicine and Rehabilitology, 107031 Moscow, Russia
| | - Vladislav E Zakharchenko
- The Department of Clinical Laboratory Diagnostics, Federal Research and Clinical Center of Intensive Care Medicine and Rehabilitology, 107031 Moscow, Russia
| | - Artem N Kuzovlev
- The Laboratory of Clinical Pathophysiology of Critical Conditions, Federal Research and Clinical Center of Intensive Care Medicine and Rehabilitology, 107031 Moscow, Russia
| | - Lyubov E Salnikova
- The Laboratory of Clinical Pathophysiology of Critical Conditions, Federal Research and Clinical Center of Intensive Care Medicine and Rehabilitology, 107031 Moscow, Russia
- The Laboratory of Ecological Genetics, Vavilov Institute of General Genetics, Russian Academy of Sciences, 119991 Moscow, Russia
- The Laboratory of Molecular Immunology, National Research Center of Pediatric Hematology, Oncology and Immunology, 117997 Moscow, Russia
| |
Collapse
|
2
|
Hiramatsu R, Minata S, Imaoka S. Investigation of Factors Related to the Week 1 Cumulated Ambulation Score in Patients With Proximal Femoral Fractures Post-surgery Using Decision Tree Analysis. Cureus 2024; 16:e55407. [PMID: 38562354 PMCID: PMC10984705 DOI: 10.7759/cureus.55407] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 03/02/2024] [Indexed: 04/04/2024] Open
Abstract
This study aimed to identify factors associated with the Cumulated Ambulation Score (CAS) in the first week post-surgery (Week 1 CAS) in patients with proximal femoral fractures. Proximal femoral fractures are prevalent in the elderly, with rising incidence rates and significant social and functional implications. The ability to walk postoperatively is a critical determinant of patient prognosis. The study included 53 patients out of 79 who underwent surgery for proximal femoral fractures at the orthopedics department of Oita Oka Hospital from January 2021 to December 2021. Exclusion criteria were pre-existing walking difficulties, inability to be evaluated in the first postoperative week, non-weight bearing post-surgery, and complications during hospitalization. The physical therapy program followed Oita Oka Hospital's clinical path, starting ambulation with a walker within the first week post-surgery. Data collected included patient background, surgical techniques, pre-injury ambulatory status, and pre-admission residential environment. Physical function assessments one week postoperatively included range of motion (ROM), manual muscle testing (MMT), pain evaluation (NRS), and CAS. Statistical analyses involved the Shapiro-Wilk test, independent t-test, Mann-Whitney U test, chi-square test, and decision tree analysis using classification and regression trees (CART). Patients were categorized into 'favorable' and 'poor' groups based on Week 1 CAS. Significant differences in dementia presence and pre-admission living environment were noted between groups. Knee extension MMT at Week 1 postoperatively showed a significant difference. The decision tree analysis identified knee extension MMT as the primary variable, with a threshold of 3.5. In patients with MMT below 3.5, dementia presence was a secondary factor, with 81% in the poor CAS group. In patients with MMT above 3.5, knee extension strength continued to be significant. The model's accuracy was 64%, with precision at 71%, recall at 63%, and an F1-score of 0.67. The study highlights knee extension MMT and dementia presence as significant factors influencing Week 1 CAS in patients with proximal femoral fractures. The poor CAS group had a higher proportion of dementia and weaker knee extension MMT. Dementia hinders rehabilitation effectiveness, impacting recovery in knee extension strength and CAS. The decision tree analysis provided an intuitive understanding of variable interrelationships, emphasizing knee extension strength as the primary factor, followed by dementia in cases with lower MMT scores. This study elucidated factors related to Week 1 CAS in postoperative patients with proximal femoral fractures. Knee extension MMT emerged as the initial factor, followed by the presence of dementia, influencing Week 1 CAS. These findings are crucial for rehabilitation planning and long-term prognostic predictions in this patient population. However, the study's limitations include potential selection bias and a small sample size, necessitating further research for enhanced predictive accuracy.
Collapse
|
3
|
Huang D, Xie Y, Zhang C. Effects of comprehensive nursing intervention on pressure ulcer after traumatic brain injury surgery: A meta-analysis. Int Wound J 2024; 21:e14494. [PMID: 37986704 PMCID: PMC10898394 DOI: 10.1111/iwj.14494] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2023] [Revised: 10/26/2023] [Accepted: 11/01/2023] [Indexed: 11/22/2023] Open
Abstract
Pressure ulcers (PUs) are a common complication in postoperative patients with traumatic brain injury, and this study used a meta-analysis to assess the effects of comprehensive nursing applied in PUs intervention in postoperative patients with traumatic brain injury. A computerised systematic search of the PubMed, EMBASE, Cochrane Library, China National Knowledge Infrastructure, Chinese Biomedical Literature Database (CBM), VIP and Wanfang databases was performed to collect publicly available articles on randomised controlled trials (RCTs) on the effects of comprehensive nursing interventions in postoperative patients with traumatic brain injury published up to August 2023. Two researchers independently completed the search and screening of the literature, extraction of data and quality assessment of the included literature based on the inclusion and exclusion criteria. Meta-analysis was performed using RevMan 5.4 software. Twenty-eight articles were finally included, for a cumulative count of 2641 patients, of which 1324 were in the intervention group and 1317 in the control group. The results of the meta-analysis showed that, compared with conventional nursing, comprehensive nursing intervention helped to reduce the incidence of PUs in postoperative patients with traumatic brain injury (5.14% vs. 19.67%, odds ratio [OR]: 0.22, 95% confidence interval [CI]: 0.16-0.29, p < 0.00001) and reduced the incidence of postoperative complications (7.87% vs. 25.84%, OR: 0.22, 95% CI: 0.11-0.43, p < 0.0001), while increasing patient satisfaction (96.67% vs. 75.33%, OR: 9.5, 95% CI: 3.63-24.88, p < 0.00001). This study concludes that a comprehensive nursing intervention applied to postoperative patients with traumatic brain injury can significantly reduce the incidence of PUs and postoperative complications as well as improve nursing satisfaction, and it is recommended for clinical promotion. However, due to the limitations of the studies' number and quality, more high-quality, large-sample RCTs are needed to further validate the conclusions of this study.
Collapse
Affiliation(s)
- Dong‐Hua Huang
- Department of Cardiovascular MedicineGanzhou City People's HospitalGanzhouChina
| | - Yan‐Cai Xie
- Department of Information CentreGanzhou City People's HospitalGanzhouChina
| | - Cui‐Lian Zhang
- Department of Cardiovascular MedicineGanzhou City People's HospitalGanzhouChina
| |
Collapse
|
4
|
Harris KA, Zhou Y, Jou S, Greenwald BD. Disorders of Consciousness Programs: Components, Organization, and Implementation. Phys Med Rehabil Clin N Am 2024; 35:65-77. [PMID: 37993194 DOI: 10.1016/j.pmr.2023.06.014] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2023]
Abstract
Rehabilitation of patients with disorders of consciousness (DoC) presents unique challenges requiring comprehensive and specialized care. This article reviews the components, organization, and implementation of an inpatient DoC program under the framework of recent evidence-based practice guidelines and minimum competency recommendations. The evidence and clinical applications of these recommendations are elaborated upon with the goal of offering providers a reference to translate guidelines into clinical practice.
Collapse
Affiliation(s)
- Kristen A Harris
- JFK Johnson Rehabilitation Institute/Hackensack Meridian School of Medicine, Rutgers Robert Wood Johnson Medical School, 65 James Street, Edison, NJ 08820, USA.
| | - Yi Zhou
- JFK Johnson Rehabilitation Institute/Hackensack Meridian School of Medicine, Rutgers Robert Wood Johnson Medical School, 65 James Street, Edison, NJ 08820, USA
| | - Stacey Jou
- JFK Johnson Rehabilitation Institute/Hackensack Meridian School of Medicine, Rutgers Robert Wood Johnson Medical School, 65 James Street, Edison, NJ 08820, USA
| | - Brian D Greenwald
- JFK Johnson Rehabilitation Institute/Hackensack Meridian School of Medicine, Rutgers Robert Wood Johnson Medical School, 65 James Street, Edison, NJ 08820, USA
| |
Collapse
|
5
|
Woo JE, Azariah A, Reed EA, Gut N. Medical, Neurologic, and Neuromusculoskeletal Complications. Phys Med Rehabil Clin N Am 2024; 35:127-144. [PMID: 37993183 DOI: 10.1016/j.pmr.2023.06.024] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2023]
Abstract
For patients with disorders of consciousness (DoC), treating the medical, neurologic, and neuromuscular complications not only stabilizes their medical disturbances, but minimizes confounding factors that may obscure the ability to accurately identify the level of consciousness and increase the chance of patients' neurologic and functional recovery. Lack of reliable communication and low-level function of patients with DoC make it challenging to diagnose some of the complications. Skilled clinical observation will be imperative to appropriately care for the patients.
Collapse
Affiliation(s)
- Jean E Woo
- TIRR Memorial Hermann, 1333 Moursund Street, Houston, TX 77030, USA; H. Ben Taub Department of Physical Medicine and Rehabilitation, Baylor College of Medicine, 7200 Cambridge Street, Houston, TX 77030, USA.
| | - Abana Azariah
- TIRR Memorial Hermann, 1333 Moursund Street, Houston, TX 77030, USA; Department of Physical Medicine and Rehabilitation, McGovern Medical School, The University of Texas Health Science Center at Houston, 1333 Moursund Street, Houston, TX 77030, USA
| | - Eboni A Reed
- H. Ben Taub Department of Physical Medicine and Rehabilitation, Baylor College of Medicine, 7200 Cambridge Street, Houston, TX 77030, USA
| | - Nicholas Gut
- Department of Physical Medicine and Rehabilitation, McGovern Medical School, The University of Texas Health Science Center at Houston, 1333 Moursund Street, Houston, TX 77030, USA
| |
Collapse
|
6
|
Pellicciari L, Lucca LF, DE Tanti A, Formisano R, Estraneo A, Cava FC, Saviola D, LA Porta F. The structure of the Early Rehabilitation Barthel Index (ERBI) should be modified: evidence from a Rasch analysis study. Eur J Phys Rehabil Med 2023; 59:458-473. [PMID: 37534887 PMCID: PMC10595071 DOI: 10.23736/s1973-9087.23.07908-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2023] [Revised: 05/16/2023] [Accepted: 06/28/2023] [Indexed: 08/04/2023]
Abstract
BACKGROUND The Early Rehabilitation Barthel Index (ERBI) comprises seven items of the Early Rehabilitation Index and ten items of the Barthel Index. The ERBI is usually used to measure functional changes in patients with severe acquired brain injury (sABI), but its measurement properties have yet to be extensively assessed. AIM To study the unidimensionality and internal construct validity (ICV) of the ERBI through Confirmatory Factor Analysis (CFA), Mokken Analysis (MA), and Rasch Analysis (RA). DESIGN Multicenter prospective study. SETTING Inpatients from five intensive rehabilitation centers. POPULATION Two hundred and forty-seven subjects with sABI. METHODS ERBI was administered on admission and discharge to study its unidimensionality through CFA and MA and its ICV, reliability, and targeting through RA. RESULTS The preliminary analyses showed a lack of unidimensionality (RMSEA=0.460 >0.06; SRMR=0.176 >0.06; CFI=1.000 >0.950; TLI=1.000 >0.950). According to CFA, "Confusional state" and "Behavioral disturbance" items showed low factor loadings (<0.40), whereas these two items composed a separate scale within the MA. Furthermore, the baseline RA showed that three items misfitted ("Mechanical ventilation," "Confusional state," "Behavioral disturbances") and a lack of conformity of several ICV requirements. After deletion of three misfitting items and further non-structural modifications (i.e., testlets creation to absorb local dependence between items and item misfit), the solution obtained showed adequate ICV, adequate reliability for measurements at the individual level (PSI>0.85), although with a frank floor effect. This final solution was successfully replicated in a total sample of the subjects. After post-hoc modifications of the score structure of two out of three misfitting items, the subsequent CFA (RMSEA=0.044 <0.06; SRMR=0.056 <0.06; CFI=1.000 >0.950 TLI=1.000 >0.950) and MA showed the resolution of the unidimensional issues. CONCLUSIONS Although the ERBI is a potentially valuable tool for measuring functioning in the coma-to-community continuum, our analyses suggested its lack of ICV, partly due to an incorrect scoring design of some items. A new perspective multicenter study is proposed to validate a modified version of the ERBI that overcomes the problems highlighted in this analysis. CLINICAL REHABILITATION IMPACT Our results do not support the use of the original structure of the ERBI in clinical practice and research, as a lack of ICV was highlighted.
Collapse
Affiliation(s)
| | | | | | | | | | - Francesca C Cava
- Montecatone Rehabilitation Institute, Montecatone, Bologna, Italy
| | | | - Fabio LA Porta
- IRCCS Istituto delle Scienze Neurologiche di Bologna, Bologna, Italy -
| |
Collapse
|
7
|
de Oliveira DV, Vieira RDCA, Pipek LZ, de Sousa RMC, de Souza CPE, Santana-Santos E, Paiva WS. Long-Term Outcomes in Severe Traumatic Brain Injury and Associated Factors: A Prospective Cohort Study. J Clin Med 2022; 11:6466. [PMID: 36362693 PMCID: PMC9655294 DOI: 10.3390/jcm11216466] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2022] [Revised: 10/14/2022] [Accepted: 10/26/2022] [Indexed: 04/03/2024] Open
Abstract
OBJECTIVE The presence of focal lesion (FL) after a severe traumatic brain injury is an important factor in determining morbidity and mortality. Despite this relevance, few studies show the pattern of recovery of patients with severe traumatic brain injury (TBI) with FL within one year. The objective of this study was to identify the pattern of recovery, independence to perform activities of daily living (ADL), and factors associated with mortality and unfavorable outcome at six and twelve months after severe TBI with FL. METHODOLOGY This is a prospective cohort, with data collected at admission, hospital discharge, three, six, and twelve months after TBI. RESULTS The study included 131 adults with a mean age of 34.08 years. At twelve months, 39% of the participants died, 80% were functionally independent by the Glasgow Outcome Scale Extended, 79% by the Disability Rating Scale, 79% were independent for performing ADLs by the Katz Index, and 53.9% by the Lawton Scale. Report of alcohol intake, sedation time, length of stay in intensive care (ICU LOS), Glasgow Coma Scale, trauma severity indices, hyperglycemia, blood glucose, and infection were associated with death. At six and twelve months, tachypnea, age, ICU LOS, trauma severity indices, respiratory rate, multiple radiographic injuries, and cardiac rate were associated with dependence. CONCLUSIONS Patients have satisfactory functional recovery up to twelve months after trauma, with an accentuated improvement in the first three months. Clinical and sociodemographic variables were associated with post-trauma outcomes. Almost all victims of severe TBI with focal lesions evolved to death or independence.
Collapse
Affiliation(s)
- Daniel Vieira de Oliveira
- Hospital das Clínicas, Faculdade de Medicina FMUSP, Universidade de Sao Paulo, Rua Dr. Enéas de Carvalho Aguiar, 255, Sao Paulo 05403-010, SP, Brazil
| | | | - Leonardo Zumerkorn Pipek
- Hospital das Clínicas, Faculdade de Medicina FMUSP, Universidade de Sao Paulo, Rua Dr. Enéas de Carvalho Aguiar, 255, Sao Paulo 05403-010, SP, Brazil
| | | | | | | | - Wellingson Silva Paiva
- Hospital das Clínicas, Faculdade de Medicina FMUSP, Universidade de Sao Paulo, Rua Dr. Enéas de Carvalho Aguiar, 255, Sao Paulo 05403-010, SP, Brazil
| |
Collapse
|
8
|
Cerasa A, Tartarisco G, Bruschetta R, Ciancarelli I, Morone G, Calabrò RS, Pioggia G, Tonin P, Iosa M. Predicting Outcome in Patients with Brain Injury: Differences between Machine Learning versus Conventional Statistics. Biomedicines 2022; 10:biomedicines10092267. [PMID: 36140369 PMCID: PMC9496389 DOI: 10.3390/biomedicines10092267] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2022] [Revised: 09/06/2022] [Accepted: 09/09/2022] [Indexed: 11/29/2022] Open
Abstract
Defining reliable tools for early prediction of outcome is the main target for physicians to guide care decisions in patients with brain injury. The application of machine learning (ML) is rapidly increasing in this field of study, but with a poor translation to clinical practice. This is basically dependent on the uncertainty about the advantages of this novel technique with respect to traditional approaches. In this review we address the main differences between ML techniques and traditional statistics (such as logistic regression, LR) applied for predicting outcome in patients with stroke and traumatic brain injury (TBI). Thirteen papers directly addressing the different performance among ML and LR methods were included in this review. Basically, ML algorithms do not outperform traditional regression approaches for outcome prediction in brain injury. Better performance of specific ML algorithms (such as Artificial neural networks) was mainly described in the stroke domain, but the high heterogeneity in features extracted from low-dimensional clinical data reduces the enthusiasm for applying this powerful method in clinical practice. To better capture and predict the dynamic changes in patients with brain injury during intensive care courses ML algorithms should be extended to high-dimensional data extracted from neuroimaging (structural and fMRI), EEG and genetics.
Collapse
Affiliation(s)
- Antonio Cerasa
- Institute for Biomedical Research and Innovation (IRIB), National Research Council of Italy, 98164 Messina, Italy
- Pharmacotechnology Documentation and Transfer Unit, Preclinical and Translational Pharmacology, Department of Pharmacy, Health Science and Nutrition, University of Calabria, 87036 Rende, Italy
- S. Anna Institute, 88900 Crotone, Italy
- Correspondence:
| | - Gennaro Tartarisco
- Institute for Biomedical Research and Innovation (IRIB), National Research Council of Italy, 98164 Messina, Italy
| | - Roberta Bruschetta
- Institute for Biomedical Research and Innovation (IRIB), National Research Council of Italy, 98164 Messina, Italy
- Department of Engineering, Università Campus Bio-Medico di Roma, Via Alvaro del Portillo 21, 00128 Rome, Italy
| | - Irene Ciancarelli
- Department of Life, Health and Environmental Sciences, University of L’Aquila, 67100 L’Aquila, Italy
| | - Giovanni Morone
- Department of Life, Health and Environmental Sciences, University of L’Aquila, 67100 L’Aquila, Italy
- San Raffaele Sulmona Institute, 67039 Sulmona, Italy
| | | | - Giovanni Pioggia
- Institute for Biomedical Research and Innovation (IRIB), National Research Council of Italy, 98164 Messina, Italy
| | | | - Marco Iosa
- IRCCS Centro Neurolesi “Bonino-Pulejo”, 98123 Messina, Italy
- Department of Psychology, Sapienza University of Rome, 00185 Rome, Italy
- Santa Lucia Foundation IRCSS, 00179 Rome, Italy
| |
Collapse
|
9
|
Liuzzi P, Magliacano A, De Bellis F, Mannini A, Estraneo A. Predicting outcome of patients with prolonged disorders of consciousness using machine learning models based on medical complexity. Sci Rep 2022; 12:13471. [PMID: 35931703 PMCID: PMC9356130 DOI: 10.1038/s41598-022-17561-w] [Citation(s) in RCA: 14] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/20/2022] [Accepted: 07/27/2022] [Indexed: 12/25/2022] Open
Abstract
Patients with severe acquired brain injury and prolonged disorders of consciousness (pDoC) are characterized by high clinical complexity and high risk to develop medical complications. The present multi-center longitudinal study aimed at investigating the impact of medical complications on the prediction of clinical outcome by means of machine learning models. Patients with pDoC were consecutively enrolled at admission in 23 intensive neurorehabilitation units (IRU) and followed-up at 6 months from onset via the Glasgow Outcome Scale-Extended (GOSE). Demographic and clinical data at study entry and medical complications developed within 3 months from admission were collected. Machine learning models were developed, targeting neurological outcomes at 6 months from brain injury using data collected at admission. Then, after concatenating predictions of such models to the medical complications collected within 3 months, a cascade model was developed. One hundred seventy six patients with pDoC (M: 123, median age 60.2 years) were included in the analysis. At admission, the best performing solution (k-Nearest Neighbors regression, KNN) resulted in a median validation error of 0.59 points [IQR 0.14] and a classification accuracy of dichotomized GOS-E of 88.6%. Coherently, at 3 months, the best model resulted in a median validation error of 0.49 points [IQR 0.11] and a classification accuracy of 92.6%. Interpreting the admission KNN showed how the negative effect of older age is strengthened when patients' communication levels are high and ameliorated when no communication is present. The model trained at 3 months showed appropriate adaptation of the admission prediction according to the severity of the developed medical complexity in the first 3 months. In this work, we developed and cross-validated an interpretable decision support tool capable of distinguishing patients which will reach sufficient independence levels at 6 months (GOS-E > 4). Furthermore, we provide an updated prediction at 3 months, keeping in consideration the rehabilitative path and the risen medical complexity.
Collapse
Affiliation(s)
- Piergiuseppe Liuzzi
- IRCCS Fondazione Don Carlo Gnocchi ONLUS, Via di Scandicci 269, Florence, Italy.,Scuola Superiore Sant'Anna, Istituto di BioRobotica, Viale Rinaldo Piaggio 34, Pontedera, Italy
| | - Alfonso Magliacano
- Fondazione Don Carlo Gnocchi ONLUS, Scientific Institute for Research and Health Care, Via Quadrivio, Sant'Angelo dei Lombardi, Italy
| | - Francesco De Bellis
- Fondazione Don Carlo Gnocchi ONLUS, Scientific Institute for Research and Health Care, Via Quadrivio, Sant'Angelo dei Lombardi, Italy
| | - Andrea Mannini
- IRCCS Fondazione Don Carlo Gnocchi ONLUS, Via di Scandicci 269, Florence, Italy.
| | - Anna Estraneo
- Fondazione Don Carlo Gnocchi ONLUS, Scientific Institute for Research and Health Care, Via Quadrivio, Sant'Angelo dei Lombardi, Italy.,Unità di Neurologia, Santa Maria della Pietà General Hospital, Via della Repubblica 7, Nola, Italy
| |
Collapse
|
10
|
Predicting Outcome of Traumatic Brain Injury: Is Machine Learning the Best Way? Biomedicines 2022; 10:biomedicines10030686. [PMID: 35327488 PMCID: PMC8945356 DOI: 10.3390/biomedicines10030686] [Citation(s) in RCA: 14] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/10/2022] [Revised: 03/02/2022] [Accepted: 03/14/2022] [Indexed: 12/04/2022] Open
Abstract
One of the main challenges in traumatic brain injury (TBI) patients is to achieve an early and definite prognosis. Despite the recent development of algorithms based on artificial intelligence for the identification of these prognostic factors relevant for clinical practice, the literature lacks a rigorous comparison among classical regression and machine learning (ML) models. This study aims at providing this comparison on a sample of TBI patients evaluated at baseline (T0), after 3 months from the event (T1), and at discharge (T2). A Classical Linear Regression Model (LM) was compared with independent performances of Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), Naïve Bayes (NB) and Decision Tree (DT) algorithms, together with an ensemble ML approach. The accuracy was similar among LM and ML algorithms on the analyzed sample when two classes of outcome (Positive vs. Negative) approach was used, whereas the NB algorithm showed the worst performance. This study highlights the utility of comparing traditional regression modeling to ML, particularly when using a small number of reliable predictor variables after TBI. The dataset of clinical data used to train ML algorithms will be publicly available to other researchers for future comparisons.
Collapse
|
11
|
Xiao A, Callaway CW, Coppler PJ. Long-term Outcomes of Post-Cardiac Arrest Patients with Severe Neurological and Functional Impairments at Hospital Discharge. Resuscitation 2022; 174:93-101. [PMID: 35189302 PMCID: PMC10404449 DOI: 10.1016/j.resuscitation.2022.02.011] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/25/2021] [Revised: 02/10/2022] [Accepted: 02/12/2022] [Indexed: 12/22/2022]
Abstract
BACKGROUND Patients resuscitated from cardiac arrest who have severe neurological or functional disability at discharge require high-intensity long-term support. However, few data describe the long-term survival and health-care utilization for these patients. METHODS We identified a cohort of cardiac arrest survivors ≥ 18 years of age, treated at a single center in Western Pennsylvania from January 2010 to December 2019, with a modified Rankin scale (mRS) of 5 at hospital discharge. We recorded demographics, cardiac arrest characteristics, and neurological exam at hospital discharge. We characterized long term survival and mortality through December 31, 2020 through National Death Index query. We described survival time overall and in subgroups using Kaplan-Meier curves and compared using log-rank tests.We linked cases with administrative data to determine 30, 90 day, and one-year hospital readmission rate. For subjects unable to follow commands at discharge, we reviewed records from index hospitalization to the present to describe improvement in neurological status and return home. RESULTS We screened 2,687 patients of which 975 survived to discharge. We identified 190 subjects with mRS of 5 at hospital discharge who were sent to non-hospice settings. Of these, 43 (23%) did not follow commands at discharge. One-year mortality was 38% (n = 71) with a median survival time of 4.2 years (IQR 0.3-10.9). Duration of survival was shorter in older subjects but did not differ based on, sex, or ability to follow commands at hospital discharge. Within the first year of discharge, 58% (n = 111) of subjects had at least one hospitalization with a median length of stay of 8 days [IQR 3-19]. Of subjects who did not follow commands at hospital discharge, 5/43 (11%) followed commands and 9 (21%) were reportedly living at home on subsequent encounters. CONCLUSIONS Of survivors treated over a decade at our institution, 20% (n = 190) were discharged from the hospital with severe functional disability. One-year mortality was 38%, and hospital readmissions were frequent. Few patients discharged unable to follow commands regained the ability over the period of observation, but many did return to living at home. These data can help inform decision maker expectations for patient trajectory and life expectancy.
Collapse
|
12
|
Zhang B, Huang K, Karri J, O’Brien K, DiTommaso C, Li S. Many Faces of the Hidden Souls: Medical and Neurological Complications and Comorbidities in Disorders of Consciousness. Brain Sci 2021; 11:brainsci11050608. [PMID: 34068604 PMCID: PMC8151666 DOI: 10.3390/brainsci11050608] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/06/2021] [Revised: 05/03/2021] [Accepted: 05/08/2021] [Indexed: 11/16/2022] Open
Abstract
Early and goal-directed management of complications and comorbidities is imperative to facilitate neurorecovery and to optimize outcomes of disorders of consciousness (DoC). This is the first large retrospective cohort study on the primary medical and neurological complications and comorbidities in persons with DoC. A total of 146 patients admitted to a specialized inpatient DoC rehabilitation program from 1 January 2014 to 31 October 2018 were included. The incidences of those conditions since their initial brain injuries were reviewed per documentation. They were categorized into reversible causes of DoC, confounders and mimics, and other medical/neurological conditions. The common complications and comorbidities included pneumonia (73.3%), pain (75.3%), pressure ulcers (70.5%), oral and limb apraxia (67.1%), urinary tract infection (69.2%), and 4-limb spasticity (52.7%). Reversible causes of DoC occurred very commonly. Conditions that may confound the diagnosis of DoC occurred at surprisingly high rates. Conditions that may be a source of pain occurred not infrequently. Among those that may diminish or confound the level of consciousness, 4.8 ± 2.0 conditions were identified per patient. In conclusion, high rates of various complications and comorbidities occurred in persons with DoC. Correcting reversible causes, identifying confounders and mimics, and managing general consequences need to be seriously considered in clinical practice.
Collapse
Affiliation(s)
- Bei Zhang
- Department of Physical Medicine and Rehabilitation, McGovern Medical School, University of Texas Health Science Center at Houston, Houston, TX 77030, USA; (B.Z.); (K.H.)
- TIRR Disorders of Consciousness Program, TIRR Memorial Hermann Hospital, Houston, TX 77030, USA; (J.K.)
| | - Karen Huang
- Department of Physical Medicine and Rehabilitation, McGovern Medical School, University of Texas Health Science Center at Houston, Houston, TX 77030, USA; (B.Z.); (K.H.)
- TIRR Disorders of Consciousness Program, TIRR Memorial Hermann Hospital, Houston, TX 77030, USA; (J.K.)
| | - Jay Karri
- TIRR Disorders of Consciousness Program, TIRR Memorial Hermann Hospital, Houston, TX 77030, USA; (J.K.)
- H. Ben Taub Department of Physical Medicine and Rehabilitation, Baylor College of Medicine, Houston, TX 77030, USA
| | - Katherine O’Brien
- TIRR Disorders of Consciousness Program, TIRR Memorial Hermann Hospital, Houston, TX 77030, USA; (J.K.)
- H. Ben Taub Department of Physical Medicine and Rehabilitation, Baylor College of Medicine, Houston, TX 77030, USA
| | | | - Sheng Li
- Department of Physical Medicine and Rehabilitation, McGovern Medical School, University of Texas Health Science Center at Houston, Houston, TX 77030, USA; (B.Z.); (K.H.)
- TIRR Disorders of Consciousness Program, TIRR Memorial Hermann Hospital, Houston, TX 77030, USA; (J.K.)
- Correspondence:
| |
Collapse
|