Author Guidelines
[Update on April 9, 2025]
This guide outlines the structure and formatting requirements for manuscripts submitted to the Journal of Intelligent Computing and Health Informatics (JICHI). Authors are required to strictly follow the provided article template to ensure consistency and quality.
A. Peer Review Policy
JICHI operates a Strict Double-Blind Peer Review. Authors must ensure that the manuscript contains no identifying information. Furthermore, authors are required to remove all metadata/properties from the digital files before submission to prevent identity leakage during the technical screening phase.
B. General Format
All manuscripts submitted to the Journal of Intelligent Computing and Health Informatics (JICHI) must be prepared using the official article template and written using Times New Roman font throughout the document. Research articles should range between 4,000 to 8,000 words (approximately 8–20 pages), while review articles may extend up to 30 pages. The manuscript must follow specific typographic formatting: the title must use font size 20 in bold; author names must use font size 11; affiliations and email addresses must use font size 9; the abstract and keywords section must use font size 10. For section headings such as “1. Introduction,” authors must use font size 12 in bold. The main body text of the manuscript should be written in font size 11, regular. Subsection headings (e.g., 1.1) should use font size 11 in bold, while sub-subsections (e.g., 1.1.1) must be written in font size 11 using bold italic style. Authors must adhere strictly to these formatting specifications to ensure consistency and readability across all submissions.
C. Article Structure
The manuscript must be prepared strictly adhering to the following structure:
C.1. Title
The title must be concise, specific, and informative. JICHI requires a Three-Pillar Construction to ensure that the manuscript’s value proposition is immediately clear to both human readers and indexing algorithms. Every title must explicitly integrate the following components:
- The Method (Technique): Identify the primary algorithm, model, or framework used (e.g., Multi-scale CNN, Metaheuristic-optimized Transformer, Blockchain-enabled Federated Learning).
- The Objective (Purpose): Specify the exact medical or health informatics problem being addressed (e.g., Early Sepsis Prediction, MRI Image Segmentation, Electronic Health Record Security).
- The Significance (Performance/Attribute): Use an adjective or phrase that highlights the paper’s unique contribution or technical advantage (e.g., Robust, Efficient, Low-latency, High-precision, Interpretable).
Mandatory Template: [Significance] [Method] for [Objective] or [Method] for [Significance] [Objective]
Formulaic Examples:
- "Robust [Significance] Residual U-Net [Method] for Automated COVID-19 Lesion Segmentation [Objective]."
- "Privacy-Preserving [Significance] Symmetry-based Encryption [Method] in Telemedicine Data Exchange [Objective]."
C.2. Author and Affiliation Format
All author names must be written consistently using the format: Firstname Lastname. For authors with a single name (mononym), the name should be written in full without abbreviation or separation. Each author’s name must be followed by a superscript number corresponding to their institutional affiliation.
Affiliations should include only the official name of the university or higher education institution, excluding the names of departments, faculties, or programs. The institution’s name must be followed by the city and country. Institutional email addresses for each author must be clearly provided and placed directly alongside or below the corresponding affiliation.
The corresponding author must be clearly indicated by placing an asterisk (*) after the name and specifying "Corresponding Author: Full Name" below the list of affiliations. E.g:
Ahmad Ilham¹, Dewi Lestari², and Mudyawati Kamaruddin¹,*
¹ Universitas Muhammadiyah Semarang, Semarang, Indonesia; ahmad.ilham@unimus.ac.id, mudywatikamaruddin@unimus.ac.id
² Universitas Gadjah Mada, Yogyakarta, Indonesia; dewi.lestari@ugm.ac.id
*Corresponding Author: Ahmad Ilham
C.3. Abstract
The abstract must be a self-contained, concise, and powerful summary of the research (200–250 words). It is prohibited to use citations, undefined abbreviations, or vague claims. Authors must strictly adhere to the following 5-pillar flow:
- Pillar 1: Context [WHAT] (1-2 sentences). Establish the significance of the research area within health informatics or intelligent computing.
- Pillar 2: Problem [WHY] (1-2 sentences). Identify the specific technical gap, limitation of existing SOTA, or the clinical challenge being addressed.
- Pillar 3: Method [HOW] (2-3 sentences). Describe the proposed solution, algorithm, or framework. Mention specific architectures (e.g., "A hybrid CNN-Transformer model") and key mathematical approaches.
- Pillar 4: Results [WHAT FOUND] (2-3 sentences). Present significant quantitative findings. Use metrics like Accuracy, F1-score, $p$-value, or processing speed. Compare these directly against a baseline.
- Pillar 5: Implication [WHAT IT MEANS] (1 sentence). Conclude with the practical or theoretical impact of the work on the field of medical science or intelligent systems.
C.4. - 1. Introduction
The Introduction must serve as a logical roadmap that justifies the necessity of the research. Authors are required to follow the CARS (Create a Research Space) model, ensuring a transition from a broad field overview to the specific technical contribution. This section should typically range between 1,000 to 1,500 words to ensure a comprehensive gap analysis.
a) Context
- Centrality Claim: Authors must state the importance of the research area (e.g., the role of AI in medical diagnostics) backed by high-impact citations from the last 2–5 years.
- Topic Generalization: Provide a brief overview of current trends, established practices, and the evolution of the technology in the relevant healthcare or computing domain.
b) Gap Analysis
- Counter-claiming or Indicating a Gap: This is the most critical part of a manuscript. Authors must explicitly identify the limitations of existing State-of-the-Art (SOTA) methods.
- Problem Specificity: Why do current algorithms fail in specific clinical scenarios? Is it a matter of computational complexity, lack of interpretability (XAI), or poor generalization on imbalanced medical datasets? The transition from "what we know" to "what is missing" must be academically rigorous.
c) Solution & Contribution
- Outlining Purposes: Clearly state the primary objective of the proposed work.
- Explicit Technical Contributions: Authors must list at least three distinct contributions in a bulleted format. For example: (1) Proposed a novel hybrid architecture that integrates [Method A] and [Method B] to enhance feature extraction; (2) Developed a customized loss function to address the class imbalance problem inherent in [Specific Dataset]. (3) Achieved a significant reduction in computational latency, making the model suitable for edge-computing in real-time health monitoring.
- Principal Findings: Briefly mention the most significant result (e.g., "The proposed model outperformed the baseline by 4.5% in AUC-ROC").
- Structure of the Paper: A concluding paragraph outlining the remaining sections of the manuscript (e.g., "Section 2 discusses the Preliminaries, Section 3 details the Methodology...").
Editorial Note for Authors: A common reason for immediate rejection (Desk Reject) in JICHI is an Introduction that is too "vague" or "descriptive." We do not accept introductions that only define what AI is; we require a technical argument that demonstrates the author’s mastery of the current scientific landscape.
C.5. - 2. Preliminaries
The Preliminaries section serves as the formal theoretical foundation of the manuscript. It is not a Literature Review. Instead, it is a rigorous presentation of the mathematical notations, definitions, and baseline theories required to understand the proposed methodology. Readers should not need to consult external textbooks to understand the core equations in your paper.
A) Sub-Section & Sub-Sub-Section Naming Convention
To demonstrate authority, avoid generic titles. Sub-section titles must link the theory to its function in your research.
- Weak (Generic): "2.1. Convolutional Neural Networks (CNN)"
- Strong (Functional): "2.1. Convolutional Neural Networks for Hierarchical Feature Extraction"
- Weak (Generic): "2.2. Fuzzy Sets"
- Strong (Functional): "2.2. Interval-Valued Fuzzy Sets in Decision Making under Uncertainty"
B) Detailed Requirements
Authors are required to address the following components:
- Formal Notations and Symbols (The "Table of Notations")
Authors must provide a consistent set of mathematical notations. All variables, sets, matrices, and operators must be defined using formal academic conventions.
- Requirement: If the paper contains more than 10 mathematical symbols, a Table of Notations (Nomenclature) must be inserted at the beginning of this section.
- Example:
Let \(\mathcal{D} = \{ (x_i, y_i) \}_{i=1}^N\) denote a dataset of \(N\) samples...
- Rigorous Definitions (Sub-sections)
Provide precise mathematical definitions for the core concepts. Do not define general terms (e.g., "What is AI?"); focus on the specific mathematical constructs used.
- Sub-sub-section Depth: If using a complex theory, break it down using logical hierarchy:
- 2.1. Graph Theory Foundations
- 2.1.1. Definition of Hypergraphs
- 2.1.2. The Laplacian Matrix Spectrum
Guardrail: Every definition presented here must be used later in the Methodology. If a defined equation is never referenced in Section 3, remove it.
- Baseline Theory/Model
If the proposed method modifies an existing algorithm (e.g., a standard Genetic Algorithm or U-Net), the original mathematical structure of that baseline must be summarized here. This establishes a "Mathematical Benchmark," allowing the reader to clearly distinguish between the standard equation (in Section 2) and your modified equation (in Section 3).
- Problem Mapping (Transition to Method)
Conclude this section by mapping these general theories to the specific domain of the paper.
- Example: In the context of this study, the nodes of the graph (Def. 2.1) represent patients, while the edges represent the similarity in their Electronic Health Records.
C.6. - 3. Methodology
The Methodology section must transcend mere description; it must provide a rigorous justification of the proposed solution. Authors are required to present their methodology through four critical dimensions:
3.1. System Architecture and Conceptual Framework
Authors must provide a high-level overview of the proposed system. This includes a "System Architecture" diagram that illustrates the data flow from input (e.g., raw medical signals, EHR datasets) through the processing stages to the final output.
Action: Each component within the architecture must be defined by its functional role, explaining how it interacts with subsequent modules to solve the research problem.
3.2. Formal Mathematical Formulation & Theoretical Analysis
To meet high-impact publication standards, authors must transcend descriptive equations. This section must rigorously map the real-world healthcare problem into a solvable mathematical structure.
A) Sub-Section Naming Convention
Avoid generic titles like "Mathematical Model." Titles must be descriptive and specific to your contribution.
Sub-chapter Title Formula:
[Adjective/Attribute] + [Core Concept] + [Context/Constraint]
Transformation Examples:
- Weak Level (Generic): "Mathematical Formulation"
- Medium Level (Descriptive): "Optimization Problem Formulation"
- Strong Level (JICHI Standard): "Stochastic Multi-Objective Optimization for Resource Allocation"
- "Game Changer" Level (Highly Specific): "Formulation of the Novel Hybrid Loss Function for Class-Imbalanced Tumor Segmentation"
B) Detailed Requirements
Authors are required to address the following components strictly:
- Problem Mapping & Decision Variables
- Clearly define the decision variables (e.g.,
xij), state space (𝒮), and parameters. - Table of Notations: A summary table of all mathematical symbols is mandatory to ensure consistency.
- Clinical/Technical Interpretation: Do not just write
min J(θ). Explicitly explain why minimizing this function translates to better health outcomes (e.g., "Minimizing the regularization term Ω(θ) corresponds to reducing overfitting on rare disease cases").
- Optimization Constraints & Feasible Region
- Explicitly define the set of constraints
𝒞 (e.g., resource limits, safety thresholds). - Distinguish between Hard Constraints (mandatory safety limits) and Soft Constraints (penalized violations).
- Example:
s.t. ∑ xi ≤ Cmax
(where Cmax denotes maximum ICU capacity). - Visual Aid: Ideally, include a conceptual diagram illustrating the feasible region defined by these constraints, especially for resource allocation problems.
- Modeling Assumptions (CRITICAL)
Authors must explicitly list the simplifications made to model the real-world problem. For example: "We assume the patient arrival rate follows a Poisson process" or "Feature independence is assumed for the Naive Bayes module." This transparency is required to protect the validity of the study during peer review. - Theoretical Derivation & Novelty (The "Proof" Requirement)
- If a new loss function, heuristic operator, or architectural block is proposed, provide a step-by-step logical derivation.
- Justification: Authors must justify the modification using Theorems/Lemmas (for pure optimization) or Analytical Justification (for Deep Learning/Neural Networks).
- Guardrail: Claims of "stability," "convergence speed," or "error bounds" must be mathematically proven or empirically justified with gradient analysis or ablation studies, not just stated.
- Convergence & Complexity Analysis
- Convergence: For iterative algorithms (Metaheuristics/Deep Learning), discuss the theoretical guarantee of convergence. Does the algorithm converge to a global or local optimum? Use Lyapunov stability or contraction mapping arguments where applicable.
- Complexity: Provide the Big-O notation for Time and Space complexity (e.g.,
O(N2 log N)). This is crucial to demonstrate the algorithm's scalability on large-scale medical datasets. A comparison table with baseline algorithms' complexity is highly recommended.
3.3. Algorithmic Implementation (Pseudocode)
To ensure technical reproducibility, a formal Pseudocode block is mandatory. It should not be a mere copy of the programming code but a high-level functional representation:
- Structure: Must include clear Inputs (parameters, datasets), Process (the core logic/loop), and Outputs (results, trained models).
- Standardization: Use standard algorithmic conventions (e.g.,
Initialize, While, For Each, Return).
3.4. Computational Complexity Analysis (Big-O)
To satisfy the requirements of "Intelligent Computing," authors must provide a theoretical analysis of the algorithm's efficiency:
- Time Complexity: Analyze the worst-case scenario $O(n)$ relative to the input size or iterations.
- Space Complexity: Define the memory requirements of the proposed model during execution.
- Significance: This analysis proves the scalability of the method for large-scale healthcare data or real-time clinical applications.
3.5. Experimental Setup and Environment
Authors must provide a comprehensive disclosure of the experimental environment to ensure reproducibility. This includes hardware specifications (e.g., GPU/CPU models, RAM), software versions (e.g., Python 3.x, PyTorch/TensorFlow versions), and the specific hyperparameter configurations used to achieve the reported results.
C.7. - 4. Results and Discussion
This section must transcend a mere descriptive report of data. It requires a rigorous analytical bridge between the experimental outcomes and the theoretical foundations proposed in the Methodology.
4.1. Statement of Results and Visual Representation
Data must be presented using high-resolution, professional-grade visualizations (300 DPI). Tables and figures should be self-explanatory. The accompanying text must prioritize the identification of significant trends, anomalies, and key performance indicators (KPIs) rather than simply repeating numerical values already present in the tables.
4.2. Statistical Significance Validation
To meet high-quality standards, claims of superiority must be supported by rigorous statistical testing. For computational comparisons, authors are required to perform non-parametric tests such as the Wilcoxon Signed-Rank Test (for pairwise comparison) or the Friedman Test with a post-hoc Nemenyi Test (for multiple-model comparison). A result is considered significant only if the p-value is less than 0.05:
\[ p < 0.05 \]
4.3. Comprehensive Evaluation Metrics (Health Informatics Context)
In the domain of intelligent health computing, "Accuracy" is insufficient. Authors must report a multi-dimensional metric suite, including Sensitivity (Recall), Specificity, F1-Score, Precision, and the Area Under the ROC Curve (AUC-ROC). This is critical for assessing model performance on imbalanced medical datasets.
4.4. Ablation Study
Authors must conduct an ablation study to systematically evaluate the contribution of each component or module within the proposed architecture. This analysis justifies the complexity of the model and proves that every proposed modification is essential to the overall performance gain.
4.5. Discussion and Scientific Argumentation
The discussion must address the "Why" behind the "What." Authors should interpret the results by linking them back to the mathematical properties or algorithmic mechanisms described in the Methodology. Furthermore, a Contextual Comparison is required; authors must explicitly discuss how their findings align with, contradict, or advance the current State-of-the-Art (SOTA) literature cited in the Introduction. Mere repetition of result values is strictly prohibited.
C.8. - 5. Conclusion & Future Works
The conclusion must follow a strict five-step logical flow (approximately 300–500 words). It should avoid repeating the Abstract and must not introduce any new data or arguments that were not previously discussed in the Results section.
Step 1: Restatement of Research Objectives Begin by concisely restating the core problem and the primary objective of the study. This anchors the reader back to the initial research question and sets the stage for the final verdict.
Example: "This study aimed to address the high computational latency in real-time cardiac arrhythmia detection by proposing a Lightweight Hybrid Gated Recurrent Unit (LH-GRU) model."
Step 2: Summary of Principal Findings (Quantitative & Qualitative) Summarize the key outcomes. While the Results section contains granular data, the Conclusion should highlight the most significant high-level metrics and the "why" behind them.
Example: "The experimental results demonstrated that the proposed architecture achieved a 98.4% F1-score while reducing inference time by 40% compared to state-of-the-art LSTM models, effectively balancing accuracy and speed."
Step 3: Practical and Theoretical Implications Clearly state the "So What?" factor. How does this research change the current practice in Health Informatics? What theoretical gap in Intelligent Computing did it fill? This section highlights the Significance pillar of your title.
Example: "The findings suggest that the integration of edge computing with optimized deep learning can facilitate remote patient monitoring in resource-constrained environments, providing a scalable solution for public health systems."
Step 4: Mandatory Statement of Limitations To maintain scientific integrity (a requirement for Q1/Q2), the author must honestly acknowledge the boundaries of the study. This prevents over-generalization and shows that the author understands the context of their work.
Example: "Despite its performance, the current study is limited by the use of a single-center dataset, which may not fully represent the demographic diversity of global patient populations."
Step 5: Future Research Directions Provide a concrete bridge to future studies based on the limitations mentioned. This guides other researchers and increases the likelihood of the paper being cited as a foundation for subsequent work.
Example: "Future work will focus on evaluating the model's robustness against adversarial attacks in clinical settings and expanding the dataset to include multi-ethnic clinical records."
Author Contributions
A short paragraph specifying their individual contributions must be provided for research articles with several authors (mandatory for more than 1 author). The following statements should be used “Conceptualization: X.X. and Y.Y.; Methodology: X.X.; Software: X.X.; Validation: X.X., Y.Y. and Z.Z.; Formal analysis: X.X.; Investigation: X.X.; Resources: X.X.; Data curation: X.X.; Writing—original draft preparation: X.X.; Writing—review and editing: X.X.; Visualization: X.X.; Supervision: X.X.; Project administration: X.X.; Funding acquisition: Y.Y.”
Funding
Please add: “This research received no external funding” or “This research was funded by NAME OF FUNDER, grant number XXX”. Check carefully that the details given are accurate and use the standard spelling of funding agency names. Any errors may affect your future funding (mandatory).
Data Availability Statement
We encourage all authors of articles published in journals to share their research data. This section provides details regarding where data supporting reported results can be found, including links to publicly archived datasets analyzed or generated during the study. Where no new data were created or data unavailable due to privacy or ethical restrictions, a statement is still required.
Institutional Review Board Statement
For studies involving humans or animals, authors must include a statement that the study was conducted according to the guidelines of the Declaration of Helsinki and approved by the Institutional Review Board (IRB) or Ethics Committee of their institution. Please state the approval code and date. If ethical approval was not required, authors must provide a justification (e.g., "The study utilized a publicly available dataset (MIMIC-III)...").
Acknowledgments
In this section, you can acknowledge any support given that is not covered by the author contribution or funding sections. This may include administrative and technical support or donations in kind (e.g., materials used for experiments). Additionally, A statement of AI tools usage transparency has been included in the Acknowledgement section, if applicable.
Conflicts of Interest
Declare conflicts of interest or state (mandatory), “The authors declare no conflict of interest.” Authors must identify and declare any personal circumstances or interests that may be perceived as inappropriately influencing the representation or interpretation of reported research results. Any role of the funders in the study's design; in the collection, analysis, or interpretation of data; in the writing of the manuscript; or in the decision to publish the results must be declared in this section. If there is no role, please state, “The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; or in the decision to publish the results”.
Generative AI Policy
Authors must disclose the use of Generative AI tools (e.g., ChatGPT, GrammarlyGO) in the writing process within the Acknowledgments section. AI tools cannot be listed as authors. The authors are fully responsible for the accuracy and integrity of the content generated by these tools.
References
References must follow the Vancouver citation style and include a minimum of 25–40 scholarly sources. We strongly recommend using bibliography management tools such as Mendeley, EndNote, or Zotero. Authors are required to prioritize recent literature; at least 70% of the references should be from the last 5 to 7 years, particularly those indexed in Scopus, Web of Science (WoS), or reputable international databases. References should primarily consist of peer-reviewed journal articles and conference proceedings. Authoritative websites (e.g., WHO, CDC) may be cited for statistical data but should not replace academic literature. Digital Object Identifiers (DOIs) must be included for all references where available.
D. Additional Information
- Mathematical Notation: Equations must be numbered and cited in the main text.
- Theorems and Proofs: Include numbered theorems, lemmas, propositions, examples, and optional proof sections.
- Figures and Tables: All figures and tables must be professionally presented, properly labeled, and explicitly cited within the main text. They should be inserted immediately after their first mention, ideally positioned at the top or bottom of a column, though substantial elements may span across both columns. Captions must be distinct and correctly placed: below the image for figures (e.g., Figure 1. Description) and above the body for tables (e.g., Table 1. Description). To ensure high-quality reproduction, authors are strongly encouraged to use vector formats (EPS, PDF, SVG) for charts and diagrams; for bitmap images, high-resolution formats (TIFF, PNG) with a minimum of 300 DPI are required. Tables must be submitted as editable text rather than images. Citations should remain consistent throughout the manuscript (e.g., "Figure 2 shows..."), and all visual content must be legible and meet rigorous professional publishing standards.
- Limit on Self-Citations: Self-citation of the authors' own work should be limited to no more than 10-15% of the total references and must be strictly relevant. Excessive self-citation or citation stacking will result in immediate rejection or a request for revision.
