Skip to main content

A decision support system to determine the amount of wergild and compensation based on forensic medicine clinical examinations



Forensic medicine is crucial in ensuring that the law and justice are carried out as swiftly, effectively, clearly, and accurately as possible. The significant number and interactions of forensic clinical examination variables, the complexity of their differentiation, and the existence of multiple decision-making paths can lead to erroneous decisions that cause irreparable harm to individuals and society. This study aimed to develop and evaluate a decision support system for determining the amount of wergild and compensation based on forensic medicine clinical examinations and the severity of the patient’s injury.


A total of 264 data elements and decision-making rules were identified based on an analysis of information sources and focus group discussions. In addition, a decision tree was used to organize the decision-making rules. Then, a system was developed using algorithms for intelligent decision-making. We included 500 patients in our analysis. This system was ultimately evaluated based on the following criteria: precision and accuracy, sensitivity, specificity, usability, and documentation quality.


The results indicated that the precision and accuracy, sensitivity, and specificity of the system were 100%. Furthermore, the documentation quality (completeness) increased from 78.2 to 100%. The average score for system usability was 4.35 out of 5, indicating a highly acceptable range.


The designed system was effective and beneficial for forensic clinical examinations and quantifying physical damage (wergild and compensation). Therefore, this system can be utilized in forensic medicine’s administrative and clinical processes, and its production and commercialization will result in an adequate market penetration rate. In addition, this will empower forensic medicine physicians and reduce decision-making errors.

Graphical Abstract


Forensic medicine is one of criminal and judicial science’s most prominent and essential components (Fang et al. 2020). Forensic science is a bridge between medical science and legal science, where it utilizes various medical sciences to uncover facts and administer justice. Forensic medicine is responsible for eliminating ambiguity in legal proceedings (Bell et al. 2018; Kelty et al. 2018). The significance of forensic medicine is such that approximately one-third of ambiguities in court cases can be resolved with its assistance. The clinical examination area, deceased and autopsy area, and forensic laboratory area are the three areas that define forensic medicine activities (Eraña-Rojas et al. 2019). Individuals who have been assaulted or injured in any way are referred to the general clinical examination division of forensic medicine to determine the legitimacy or invalidity of their claim (Meilia et al. 2020). According to the statistics, approximately 85% of the cases referred to this department involve injuries caused by accidents and conflicts, as well as resolving ambiguities such as determining the extent of the injury and the amount of compensation and disability (Schmidt et al. 2020).

Instructions and guidelines address the significant number and interactions of clinical examination variables in forensic medical decisions, the complexity of their differentiation, and the existence of multiple decision-making paths in this field. They can lead to an increase in erroneous examinations and decision-making errors (Siddaway et al. 2020). Given that legal doctors are utilized and given priority in the criminal justice system and that the Judicial Council considers the Forensic Medicine Organization’s opinion, any errors in forensic medicine’s examinations and decisions can result in irreparable harm to both individuals and society (Aktas et al. 2018).

With the assistance of human resources, information technology has had a significant impact on facilitating and accelerating affairs in the modern world; forensic medicine is the field that has effectively utilized the knowledge and advanced technology (Torab-Miandoab et al. 2023). Since more than a decade ago, advanced technologies have assisted forensic science in efficiently resolving the mysteries and complexities that arise in this field (Khanagar et al. 2021). Decision support systems in legal fields can promote continuous decision-making, lead to decisiveness in the justice system with transparent legal decisions, and aid in resolving disputes. This is given that forensic decisions are governed by the laws and instructions outlined in the pertinent guidelines. Because forensic decisions involve the relevant policies’ laws, and procedures, experts in this field also base their decisions on these laws. Therefore, in most countries today, forensic medicine uses new and emerging technologies, including decision-support systems, and there is a greater need to design and supply decision-support systems (Coelho et al. 2020). Decision support systems are systems that provide alternative solutions to help solve semi-structured or unstructured problems (Torab-Miandoab et al. 2020; Nisioti et al. 2021; Nazir et al. 2018).

Forensic affairs have expanded and developed into vast domains, necessitating active forensic personnel's use of up-to-date information and communication technologies to organize their performance consistently and precisely (Arshad et al. 2018). The explosive growth of forensic information heightens the need for innovative methods to manage and gain data access (Montasari and Hill 2019). Considering the need for forensic experts, judges, and law enforcement professionals to acquire and apply current knowledge of forensic medicine to make expert opinions more scientific in this field, the continuous use of information systems such as decision-making is crucial (Horsman 2019).

Due to the significance of forensic medicine and the implications of its decisions, on the one hand, and the expansion of knowledge and the complexity of decision-making in the field of forensic examinations, on the other hand, the use of information systems, particularly decision support systems, has gained significant importance. Because of the limited number of forensic experts and their unequal distribution across the country, in some provinces, no forensic experts are working in the medical organization, and general physicians are also used in these centers. The organization’s managers emphasize using auxiliary systems in the complex, cognitive, and time-consuming process of forensic medical decision-making. Currently, such systems do not exist or are not used by the nation’s forensic medicine organization (Cherrington et al. 2020; Haines et al. 2018).

To this end, the current study aimed to design and evaluate the decision support system of forensic medical examinations so that forensic doctors can perform forensic medical examinations more quickly, accurately, and appropriately using this system, thereby improving decision-making (determining the amount of wergild and compensation).


The study employed a descriptive-developmental approach conducted in three phases: descriptive, developmental, and evaluative. Pre-existing methods from the field were adopted and customized for each phase. The research environment during the descriptive and developmental phases was the Health Information Technology Laboratory of the Faculty of Medical Information and Management in Tabriz University of Medical Sciences, while the evaluation phase took place at the General Forensic Medicine Department of the East Azerbaijan province.

In the descriptive study phase, a review of published literature and gray sources from global websites specializing in forensic medicine was conducted to identify information needs, data elements, and guidelines for forensic clinical examination protocols and related decision-making. Additionally, three 2-h focus group meetings were held with 9 experts in forensic medicine, health information management and medical informatics. The purposive sampling method was used to identify recognized experts. Potential experts were identified from publications on forensic medicine and health information systems in databases. The experts were eligible to participate in focus group meetings if they were specialists in health information management, health information technology, forensic medicine, and medical informatics and had a work experience of 5 years or more in related field, had at least 5 articles on health information systems or forensic medicine within the last 10 years, and also lived in Tabriz-Iran.

During the first session, the items extracted in the form of a checklist, which was set on a five-point Likert scale from very important to not important, were provided to the members of the focus group for review, and the items that received scores of important and very important were approved. At the following meeting, information requirements and data elements were extracted from confirmed cases. In the subsequent step, another meeting was held with the selected team members to determine the decision-making algorithms (decision-making model). Thus, all types of injuries were categorized and then a certain amount of compensation and wergild was determined for each of them. The decision-making model was determined based on the results of the previous studies and the software yEd Graph Editor. All cases were examined using qualitative analysis.

During the development study phase, existing architectures used in decision support systems were examined and a new architecture was implemented, incorporating modern technologies and intelligentization methods. Scrum approach of agile methodology was used to develop the system based on the intelligentization methods, decision tree algorithm, and framework determined in the previous phase, and its results were presented based on the architecture and design procedure. In the current research, rule-based reasoning forms the decision points of forensic clinical examinations and physical damage determination based on the if-then representation of previously extracted knowledge. In this phase, MVC (Model-View-Controller) Core technology, a database utilizing MongoDB (Database) and SQL (Structured Query Language) server software, system logic employing Visual Studio software, the core 5 integrated environment, and Ajax, Java, and C# programming languages. The system’s user interface was developed using Visual Studio and HTML (HyperText Markup Language), CSS (cascading style sheets), and bootstrap programming languages in a bilingual format (English and Persian). In this phase, data analysis methods are not applicable.

In the evaluation study phase, the designed system was subjected to the opinions and votes of users (legal doctors) and evaluated using the System Usability Scale tool and the key indicators of accuracy and precision, sensitivity, specificity, applicability, and documentation quality (completeness).

Files of all patients referred to the General Department of Forensic Medicine of East Azerbaijan Province (Tabriz, Iran) from April 2022 to August 2022 during the shift of forensic doctors collaborating in the research were included in the dataset. There were no exclusion criteria at this stage. The co-legal physician recorded the data simultaneously on paper-based forms and in the smart system, and the results of the system’s decisions were compared to the outcomes of expert doctors’ decisions. Notably, this system is intended for the forensic doctor who examines the patient and investigates his case; therefore, the patient’s information will be accessible only to the forensic doctor conducting the investigation and will not be shared with any other parties. Consequently, it can be concluded that the privacy and secrecy of patient information will be fully maintained. Due to the reasons above, there is no need to obtain informed consent from the people referring to the forensic organization, as their information was not included in the study phase, and the objective was to evaluate the system’s functionality.

The evaluation of the smart system was based on the final data set of 500 cases and the SUS (System Usability Scale) questionnaire completed by the relevant experts. A confusion matrix was used to accurately evaluate the system’s classification and decision-making model, where the relevant process is the opinion of a gold-standard forensic doctor. Accuracy, sensitivity, and specificity were determined using the following equations: TP denotes the true positive rate, TN represents the true negative rate, FP denotes the false positive rate, and FN is the false negative rate.

$$\textrm{Sensitivity}=\frac{\textrm{TP}}{\textrm{TP}+\textrm{FN}}\left(\%\right)\kern0.75em \textrm{Specificity}=\frac{\textrm{TN}}{\textrm{TN}+\textrm{FP}}\left(\%\right)$$
$$Accuracy=\frac{TP+ TN}{Total}\left(\%\right)$$

Two evaluators (collaborating forensic doctor in the research) assessed the completeness of the paper documents and determined the number and distribution of complete or incomplete records. A document was deemed incomplete if it was missing one or more pieces of data in any format. The following equations were used to calculate the completeness of the documentation:

$${\displaystyle \begin{array}{c} Completeness=\frac{Totalcompleterecords}{Totalrecords}\left(\%\right),\\ {} Incompleteness=\left(\left(1- completenes\right)\times 100\right)\%.\end{array}}$$

The confusion matrix and Microsoft Excel software were used for statistical analysis in system evaluation.


In this study, 57.14% of the focus group members were forensic experts, while 42.86% were technical experts (health information management, health information technology, and medical informatics). Furthermore, 57.14% of the participants were employed by a forensic organization, while a university employed 42.86%. Moreover, 57.14% had over 5 years of professional experience. The characteristics and qualifications of the participants in the focus group sessions are listed in Table 1.

Table 1 Characteristics of study participants

The extraction of 264 data elements (decision-making protocols according to types of physical damage based on forensic clinical examinations) was performed. As shown in Table 2, the lower limb was the most organized, with 36 categories, whereas psycho-behavioral disorders and burns were the least organized, with two categories each. In addition, the categories of hearing loss in one ear and lower limb fractures had the most data elements with 55 elements, whereas the organ defects caused by pericardial diseases had the least with one element. The determined functional and non-functional system requirements are also shown in Table 3.

Table 2 Information requirements and data elements of the decision support system for determining the amount of wergild and compensation based on forensic medical exams
Table 3 Functional and non-functional requirements of the decision support system for determining the amount of wergild and compensation based on forensic medical exams

The extracted rules, which included 1420 RBR (Rule-Based Reasoning) methodologies, were created in the rule-based engine and used to calculate wergild and compensation based on forensic medicine clinical examinations. A part of the knowledge representation process is depicted as a decision tree in Fig. 1.

Fig. 1
figure 1

A part of the decision-making rules framework

This study utilized a comprehensive architecture. The architecture consists of seven major components: user- and case-specific data, a database, a rule base, an inference engine, an explanation system, an editor for the rule base, and a user interface. Figure 2 illustrates the system’s architecture.

Fig. 2
figure 2

The architecture used in the system

The registration and login module is the first system module. This module has a fixed access level for forensic data entry specialists. First, the forensic physician registers and enters his information into the system. Next, they log into the system using the established username and password. The next module is the decision support module of the system, in which the forensic doctor selects the injured organ or system based on the anatomical position, and at each stage of clinical examination, they select the results of the clinical examination in the system, and finally, based on the amount of injuries and damages selected in the system and also based on the decision rules of the system, the system suggests the final decision on the amount of compensation and wergild) Based on the decision rules extracted in the descriptive phase, a certain amount of compensation and wergild has been determined for each injury and damage depending on its type(. After proposing a decision from the system, the forensic doctor can either approve the system’s proposed decision or modify the decision. In addition, an output of the examination result and the amount of compensation and wergild is produced at the end of the process. The system guides the user throughout all stages of decision-making regarding available instructions and rules. The system is designed bilingually in English and Persian. Figure 3 depicts the system’s decision-making module.

Fig. 3
figure 3

Decision support module of the system

From April 1401 to August 1401, 500 patient files were submitted to the General Department of Forensic Medicine of East Azerbaijan Province (Tabriz, Iran) as part of the evaluation phase data. Among the investigated cases, 59.6% were related to men and 40.4% were related to women. Also, 42% of them were married and 58% were single. Their average age was 29.61 years. Also, most of them had basic education or were illiterate.

The evaluation of the system’s accuracy, sensitivity, and specificity revealed that its accuracy, sensitivity, and specificity were 100% (Table 4). Comparing the traditional method to using the system indicated that among the 500 records collected using the system, the documentation of all 500 cases (100%) was also complete, whereas using the traditional method, only 391 cases (78.2%) were complete, and 109 contained one or more incomplete items.

Table 4 Confusion matrix for the rule-based reasoning model used to determine the amount of wergild and compensation

Table 5 displays the results of the SUS evaluation conducted by the relevant experts. The average score for the system’s usability was 4.35 out of 5, indicating its excellent usability. In addition, according to the evaluators, the system improves forensic physicians’ concentration during clinical examinations and greatly assists physicians with examination and decision-making.

Table 5 the system’s usability score


The current study used an intelligent decision support system to determine the amount of physical injury wergild and compensation based on forensic clinical examinations. Based on forensic clinical examinations, 264 data elements and information required for determining protocols appropriate to physical injuries were identified. The primary task in data collection is identifying and determining information needs and data elements for information systems to function properly (Akbari et al. 2022).

According to the review of studies conducted in this research, there is no uniform standard or format for collecting data in this field in Iran. As a result, determining the information needs and data elements is required to specify the protocols of the decision-making system in Iran for determining the amount of physical damage based on forensic clinical examinations. Defining and implementing data elements for collecting required data, determining the appropriate protocol and system performance, uniformity of reporting methods, interoperability of reported results, improved report comparison, providing a guide for future research, and fostering knowledge production. It is performed on demand (Jason et al. 2012). The current study includes all cases. Collecting relevant data elements at the point of clinical examination and decision-making aids forensic physicians, ultimately leading to improved interoperability (Ahmadi et al. 2014).

This study described the framework and decision-making model of the system using the decision tree model. A decision tree is a graphical representation of a decision process or series of decisions; this is a decision-making tool consisting of a graph or tree-like model that depicts decisions and their potential outcomes. The obtained predictions in each decision tree model represent the laws and rules based on which the decision maker makes their decisions (Li et al. 2022). All activities and actions performed by people or systems in all fields result from decision-making, and correct and appropriate decision-making is especially important in forensic medicine. Consequently, the decision-making process is primarily based on the model. When making decisions, the goal is to use models to arrive at the best possible decision (Earwaker et al. 2020).

Decision support systems can be viewed as a collection that is fully compatible with business intelligence. This study utilized a business intelligence approach involving knowledge discovery and visualization techniques to provide a comprehensive view of business intelligence in determining the amount of wergild and compensation based on forensic medicine clinical examinations. Business intelligence tools are utilized to collect, analyze, and disseminate data so that knowledge workers can make informed decisions. Integrating business intelligence tools, such as decision support systems, can improve data analysis and decision support issues (Bhattad and Jain 2020).

Most forensic medicine and medical informatics studies are utilized in crimes, murders, and suicides to identify the victims and the injured, generate hypotheses, and establish the time and cause of death, among other factors. To this end, Noor and Nubli (2017) developed a system known as iDepis. This system is a type of decision support system that employs a variety of statistical analyses and algorithms to determine the location and cause of death. This highly reliable system guides forensic experts in managing decomposing bodies (Noor and Nubli 2017). While in the current study, the system determines the amount of physical damage based on clinical examinations and the compensation and wergild. Nevertheless, the results of evaluating the accuracy of both systems were satisfactory.

Costantini et al. (2019) conducted a study titled “Research on Digital Forensics and Artificial Intelligence.” This study aimed to develop hypotheses that can be used as courtroom evidence. According to the findings of this study, artificial intelligence can be used to evaluate evidence and make appropriate decisions (Costantini et al. 2019). Consequently, the cited research differs from the present one in terms of its objective and methodology, but its evaluation results are entirely consistent with ours.

The results of the present study indicated that the documentation quality increased from 78.2 to 100%. A review of studies revealed that in 64% of papers, completeness was the most frequently assessed aspect of data quality (Sugiarti 2020). The potential benefits of an intelligent system in healthcare documentation include enhanced documentation quality, increased communication between users, reduced paperwork, and provided cost savings. Electronic records permit real-time access, which expedites data searches and boosts physician productivity (Jedwab et al. 2019).

Most studies that have designed decision support systems for forensic medicine have employed machine learning algorithms (Yeow et al. 2014; Shen et al. 2006; Oatley et al. 2006), whereas the system developed in this study uses a rule-based approach according to the nature of the process. Our investigation employs knowledge-based methods as opposed to machine learning algorithms. In comparison to machine learning methods, the results of some studies indicate a high degree of accuracy (approximately 100%) (Hyung et al. 2020). The current research suggests that the knowledge scope should be available to developers in evidence-based diagnosis. This is because knowledge-based methods result in transparency and a design that stakeholders more easily understand.

The inference process of several machine learning algorithms, such as artificial neural networks, is vague to expert interpretation, whereas the knowledge-based algorithm behaves like a white box. Analyzing the path to solving a problem in numerous forensic challenges is essential. Due to the unpredictability of forensic medicine, knowledge-based methods assist in examining the relationships between rules and outcomes (Khanam et al. 2019).

As a result of the system’s extremely high accuracy, the use of this system improves compliance with instructions. This increase occurs because the system simplifies instructions and calculations, reducing complexity (Goud et al. 2010). This result was comparable to similar research (Karlsson 1998; Mapes et al. 2019).

To the extent that information systems, such as decision support systems, have permeated the forensic medicine system, they have not been as effective. Usability issues with these systems account for most of these inefficiencies. Usability has a substantial effect on the acceptance and intended application of systems. Without this capability, users cannot obtain the system’s features and functions’ potential benefits. Usability is, therefore, crucial for the successful application and use of these systems. However, in the majority of this research’s studies, this important factor was overlooked when evaluating the systems, whereas the results of this study indicate that the designed system has the highest score at this point of evaluation.

Due to their busy schedules and time constraints, coordinating meeting times with forensic doctors to extract and approve decision rules and evaluate and approve the system was the most significant limitation of this study. The research team best managed this limitation by utilizing remote communication infrastructure and careful planning.


This study successfully developed and evaluated a decision support system for determining the amount of wergild and compensation based on forensic medicine clinical examinations and the severity of the patient’s injury. The system incorporated a comprehensive set of 264 data elements and utilized intelligent decision-making algorithms, resulting in 100% accuracy, sensitivity, and specificity. With improved documentation quality and high usability scores, the system proved to be effective in quantifying physical damage and empowering forensic medicine physicians. The implementation of this system in forensic medicine’s administrative and clinical processes holds significant potential for improving decision-making accuracy and reducing errors. Furthermore, considering the system’s robust performance and the demand for such solutions in the market, its production and commercialization can lead to successful market penetration. Ultimately, the adoption of this decision support system has the potential to enhance the efficiency, clarity, and accuracy of law and justice proceedings, bringing about positive societal impact. Further research and development can explore opportunities for enhancing the system’s functionalities, expanding its application domains, and ensuring its compatibility with existing forensic medicine frameworks. By continually refining and advancing decision support technologies in this field, we can strive for better outcomes, increased fairness, and enhanced outcomes for individuals and society as a whole.

Availability of data and materials

The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.







Structured query language


HyperText Markup Language


Cascading style sheets


System Usability Scale


True positive


True negative


False positive


False negative


Rule-based reasoning


  • Ahmadi M, Mohammadi A, Chraghbaigi R, Fathi T, Baghini MSJIRCMJ (2014) Developing a minimum data set of the information management system for orthopedic injuries in iran. Iran Red Crescent Med J 16(7):e17020

    Article  PubMed  PubMed Central  Google Scholar 

  • Akbari N, Safdari R, Mansourian A, Ehtesham HJMEJOC (2022) Development of a national consensus minimum data set for the diagnosis and treatment of oral cancer: towards precision management. Mid East J Cancer 13:343–351

    Google Scholar 

  • Aktas, N., Gulacti, U., Lok, U., Aydin, İ., Borta, T., Celik, M. J. B. O. E. & Trauma 2018. Characteristics of the traumatic forensic cases admitted to emergency department and errors in the forensic report writing Bull Emerg Trauma 6, 64.

  • Arshad H, Jantan AB, Abiodun OIJJOIPS (2018) Digital forensics: review of issues in scientific validation of digital evidence. J Inform Process Syst 14

  • Bell S, Sah S, Albright TD, Gates SJ Jr, Denton MB, Casadevall AJPOTNAOS (2018) A call for more science in forensic science. Proc Natl Acad Sci 115:4541–4544

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Bhattad PB, Jain VJC (2020) Artificial intelligence in modern medicine–the evolving necessity of the present and role in transforming the future of medical care. Cureus 12

  • Cherrington M, Lu Z, Xu Q, Airehrour D, Madanian S, Dyrkacz A (2020) Deep learning decision support for sustainable asset management. In: Advances in Asset Management and Condition Monitoring: COMADEM 2019. Springer

    Google Scholar 

  • Coelho JDO, Curate F, Navega D (2020) Osteomics: decision support systems for forensic anthropologists. Statistics and probability in forensic anthropology. Elsevier

    Google Scholar 

  • Costantini S, de Gasperis G, Olivieri RJAOM, Intelligence A (2019) Digital forensics and investigations meet artificial intelligence. Ann Math Artif Intell 86:193–229

    Article  Google Scholar 

  • Earwaker H, Nakhaeizadeh S, Smit NM, Morgan RMJS, Justice (2020) A cultural change to enable improved decision-making in forensic science: a six phased approach. Sci Justice 60:9–19

    Article  PubMed  Google Scholar 

  • Eraña-Rojas IE, Cabrera MVL, Barrientos ER, Membrillo-Hernández JJJOF, Medicine L (2019) A challenge based learning experience in forensic medicine. J Forensic Legal Med 68:101873

    Article  Google Scholar 

  • Fang Y, Lan Q, Xie T, Liu Y, Mei S, Zhu BJFYXZZ (2020) New opportunities and challenges for forensic medicine in the era of artificial intelligence technology. Fa yi xue za zhi 36:77–85

    CAS  PubMed  Google Scholar 

  • Goud R, van Engen-Verheul M, De Keizer NF, Bal R, Hasman A, Hellemans IM, Peek NJIJOMI (2010) The effect of computerized decision support on barriers to guideline implementation: a qualitative study in outpatient cardiac rehabilitation. Int J Med Inform 79:430–437

    Article  PubMed  Google Scholar 

  • Haines A, Perkins E, Evans EA, Mccabe RJMHRJ (2018) Multidisciplinary team functioning and decision making within forensic mental health. Mental Health Rev J 23:185–196

    Article  Google Scholar 

  • Horsman GJDI (2019) Formalising investigative decision making in digital forensics: Proposing the Digital Evidence Reporting and Decision Support (DERDS) FRAMEWORK. Digit Invest 28:146–151

    Article  Google Scholar 

  • Hyung W-G, Kim S, Jo J-KJE, Construction & Management, A (2020) Improved similarity measure in case-based reasoning: a case study of construction cost estimation. Eng Constr Archit Manag 27:561–578

    Article  Google Scholar 

  • Jason LA, Unger ER, Dimitrakoff JD, Fagin AP, Houghton M, Cook DB, Marshall GD Jr, Klimas N, Snell CJB, Behavior, & Immunity (2012) Minimum data elements for research reports on CFS. Brain Behav Immun 26:401–406

    Article  PubMed  PubMed Central  Google Scholar 

  • Jedwab RM, Chalmers C, Dobroff N, Redley BJC (2019) Measuring nursing benefits of an electronic medical record system: a scoping review. Collegian 26:562–582

    Article  Google Scholar 

  • Karlsson TJFSI (1998) Multivariate analysis (Forensiometrics')—a new tool in forensic medicine: differentiation between sharp force homicide and suicide. Forensic Sci Int 94:183–200

    Article  CAS  PubMed  Google Scholar 

  • Kelty SF, Julian R, Bruenisholz E, Wilson-Wilde LJFSI (2018) Dismantling the justice silos: flowcharting the role and expertise of forensic science, forensic medicine and allied health in adult sexual assault investigations. Forensic Sci Int 285:21–28

    Article  PubMed  Google Scholar 

  • Khanagar SB, Vishwanathaiah S, Naik S, Al-Kheraif AA, Divakar DD, Sarode SC, Bhandi S, Patil SJLM (2021) Application and performance of artificial intelligence technology in forensic odontology–a systematic review. Leg Med 48:101826

    Article  Google Scholar 

  • Khanam SA, Liu F, Chen Y-PPJH-CC, Sciences I (2019) Comprehensive structured knowledge base system construction with natural language presentation. Hum-centric Comput Inf Sci 9:1–32

    Article  Google Scholar 

  • Li X, Yi S, Cundy AB, Chen WJJOCP (2022) Sustainable decision-making for contaminated site risk management: a decision tree model using machine learning algorithms. J Clean Prod 371:133612

    Article  Google Scholar 

  • Mapes AA, Stoel RD, de Poot C, Vergeer P, Huyck MJS, Justice (2019) Decision support for using mobile Rapid DNA analysis at the crime scene. Sci Justice 59:29–45

    Article  CAS  PubMed  Google Scholar 

  • Meilia PDI, Freeman MD, Herkutanto, Zeegers MPJFS, Medicine & Pathology (2020) A review of causal inference in forensic medicine. Forensic Sci Med Pathol 16:313–320

    Article  PubMed  PubMed Central  Google Scholar 

  • Montasari R, Hill R (2019) Next-generation digital forensics: challenges and future paradigms. In: 2019 IEEE 12th International conference on global security, safety and sustainability (ICGS3). IEEE, pp 205–212

    Chapter  Google Scholar 

  • Nazir S, Shahzad S, Mahfooz S, Nazir MJIAJIT (2018) Fuzzy logic based decision support system for component security evaluation. Int Arab J Inf Technol 15:224–231

    Google Scholar 

  • Nisioti A, Loukas G, Laszka A, Panaousis EJITOIF, Security (2021) Data-driven decision support for optimizing cyber forensic investigations. IEEE Trans Inf Forensics Secur 16:2397–2412

    Article  Google Scholar 

  • Noor NMM, Nubli AHA (2017) Decision support system for postmortem interval (iDepis) using stages of decomposition. In: Symposium on Innovation and Creativity (iMIT-SIC). International Malaysia-Indonesia Thailand, pp 437–443

    Google Scholar 

  • Oatley G, Ewart B, Zeleznikow JJAI, Law (2006) Decision support systems for police: lessons from the application of data mining techniques to “soft” forensic evidence. Artif Intell Law 14:35–100

    Article  Google Scholar 

  • Schmidt U, Oramary D, Kamin K, Buschmann CT, Kleber CJWJOS (2020) Synergistic effects of forensic medicine and traumatology: comparison of clinical diagnosis autopsy findings in trauma-related deaths. World J Surg 44:1137–1148

    Article  PubMed  Google Scholar 

  • Shen Q, Keppens J, Aitken C, Schafer B, Lee MJL, Probability & Risk (2006) A scenario-driven decision support system for serious crime investigation. Law Probab Risk 5:87–117

    Article  Google Scholar 

  • Siddaway AP, Quinlivan L, Kapur N, O'Connor RC, de Beurs D (2020) Cautions, concerns, and future directions for using machine learning in relation to mental health problems and clinical and forensic risks: A brief comment on “Model complexity improves the prediction of nonsuicidal self-injury”(Fox et al., 2019). J Consult Clinic Psychol 88(4):384–387.

    Article  Google Scholar 

  • Sugiarti I (2020) Legal protection of patient rights to completeness and confidentiality in management of medical record documents. In: 2nd Bakti Tunas Husada-Health Science International Conference (BTH-HSIC 2019). Atlantis Press, pp 179–191

    Google Scholar 

  • Torab-Miandoab A, Samad-Soltani T, Jodati A, Rezaei-Hachesu PJBMI, Making D (2023) Interoperability of heterogeneous health information systems: a systematic literature review. BMC Med Inform Decis Mak 23:18

    Article  PubMed  PubMed Central  Google Scholar 

  • Torab-Miandoab A, Samad-Soltani T, Shams-Vahdati S, Rezaei-Hachesu PJTJOEM (2020) An intelligent system for improving adherence to guidelines on acute stroke. Turk J Emerg Med 20:118

    Article  PubMed  PubMed Central  Google Scholar 

  • Yeow WL, Mahmud R, Raj RGJESWA (2014) An application of case-based reasoning with machine learning for forensic autopsy. Expert Syst Appl 41:3497–3505

    Article  Google Scholar 

Download references


This study as an MSc dissertation with thesis number 64,775 was done in School of Health Management and Medical Informatics of Tabriz University of Medical Sciences. The authors appreciate the assistance and cooperation of the forensic experts of the East Azerbaijan Province Forensic Medicine Organization.


No funding or grants were obtained.

Author information

Authors and Affiliations



BS and TSS conceived the original idea. SHC designed the study. ATM collected data. ATM and SHC analyzed and interpreted the data. ATM and PRH prepared the first manuscript draft. All authors contributed significantly and critically to the final manuscript.

Corresponding author

Correspondence to Taha Samad Soltani.

Ethics declarations

Ethics approval and consent to participate

This article does not contain any studies with human participants or animals performed by any of the authors. The Ethics Committee of Tabriz University of Medical Sciences has confirmed this research (IR.TBZMED.REC.1400.875).

Consent for publication

Not applicable.

Competing interests

The authors declare that they have no competing interests.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Habibi-Chenaran, S., Samadirad, B., Miandoab, A.T. et al. A decision support system to determine the amount of wergild and compensation based on forensic medicine clinical examinations. Egypt J Forensic Sci 14, 10 (2024).

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: